{"id":27059900,"url":"https://github.com/robmarkcole/satellite-image-deep-learning","last_synced_at":"2025-04-05T13:01:41.259Z","repository":{"id":37318903,"uuid":"129712017","full_name":"satellite-image-deep-learning/techniques","owner":"satellite-image-deep-learning","description":"Techniques for deep learning with satellite \u0026 aerial imagery","archived":false,"fork":false,"pushed_at":"2025-03-23T14:58:46.000Z","size":30643,"stargazers_count":9193,"open_issues_count":4,"forks_count":1554,"subscribers_count":280,"default_branch":"master","last_synced_at":"2025-04-02T17:17:00.468Z","etag":null,"topics":["convolutional-neural-networks","dataset","datasets","deep-learning","deep-neural-networks","earth-observation","image-classification","keras","machine-learning","object-detection","python","pytorch","remote-sensing","satellite-data","satellite-imagery","satellite-images","sentinel","tensorflow"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/satellite-image-deep-learning.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null},"funding":{"github":"robmarkcole"}},"created_at":"2018-04-16T08:42:09.000Z","updated_at":"2025-04-02T07:04:43.000Z","dependencies_parsed_at":"2024-03-27T06:28:17.402Z","dependency_job_id":"602e3ca2-9d09-417f-aea8-076e1ed71ff6","html_url":"https://github.com/satellite-image-deep-learning/techniques","commit_stats":{"total_commits":1292,"total_committers":24,"mean_commits":"53.833333333333336","dds":0.04566563467492257,"last_synced_commit":"bb676caeac5b8f59ad92d2281084a624a41f7d0b"},"previous_names":["robmarkcole/satellite-image-deep-learning"],"tags_count":22,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/satellite-image-deep-learning%2Ftechniques","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/satellite-image-deep-learning%2Ftechniques/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/satellite-image-deep-learning%2Ftechniques/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/satellite-image-deep-learning%2Ftechniques/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/satellite-image-deep-learning","download_url":"https://codeload.github.com/satellite-image-deep-learning/techniques/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247339145,"owners_count":20923013,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["convolutional-neural-networks","dataset","datasets","deep-learning","deep-neural-networks","earth-observation","image-classification","keras","machine-learning","object-detection","python","pytorch","remote-sensing","satellite-data","satellite-imagery","satellite-images","sentinel","tensorflow"],"created_at":"2025-04-05T13:01:31.720Z","updated_at":"2025-04-05T13:01:41.164Z","avatar_url":"https://github.com/satellite-image-deep-learning.png","language":null,"funding_links":["https://github.com/sponsors/robmarkcole"],"categories":["Sensor Processing","Others","References and other awesome lists","Deep learning and Machine Learning","Citation","Examples/Notebooks"],"sub_categories":["Image Processing","Testing your code","Datasets table"],"readme":"\u003cdiv align=\"center\"\u003e\n  \u003cp\u003e\n    \u003ca href=\"https://www.satellite-image-deep-learning.com/\"\u003e\n        \u003cimg src=\"images/logo.png\" width=\"700\"\u003e\n    \u003c/a\u003e\n\u003c/p\u003e\n\n# 👉 [satellite-image-deep-learning.com](https://www.satellite-image-deep-learning.com/) 👈\n\n\u003c/div\u003e\n\n## Introduction\n\nDeep learning has revolutionized the analysis and interpretation of satellite and aerial imagery, addressing unique challenges such as vast image sizes and a wide array of object classes. This repository provides an exhaustive overview of deep learning techniques specifically tailored for satellite and aerial image processing. It covers a range of architectures, models, and algorithms suited for key tasks like classification, segmentation, and object detection.\n\n**How to use this repository:** use `Command + F` (Mac) or `CTRL + F` (Windows) to search this page for e.g. 'SAM'\n\n## Techniques\n\n- [Classification](https://github.com/satellite-image-deep-learning/techniques?tab=readme-ov-file#classification)\n- [Segmentation](https://github.com/satellite-image-deep-learning/techniques?tab=readme-ov-file#segmentation)\n- [Object detection](https://github.com/satellite-image-deep-learning/techniques?tab=readme-ov-file#object-detection)\n- [Regression](https://github.com/satellite-image-deep-learning/techniques?tab=readme-ov-file#regression)\n- [Cloud detection \u0026 removal](https://github.com/satellite-image-deep-learning/techniques?tab=readme-ov-file#cloud-detection--removal)\n- [Change detection](https://github.com/satellite-image-deep-learning/techniques?tab=readme-ov-file#change-detection)\n- [Time series](https://github.com/satellite-image-deep-learning/techniques?tab=readme-ov-file#time-series)\n- [Crop classification](https://github.com/satellite-image-deep-learning/techniques?tab=readme-ov-file#crop-classification)\n- [Crop yield \u0026 vegetation forecasting](https://github.com/satellite-image-deep-learning/techniques?tab=readme-ov-file#crop-yield--vegetation-forecasting)\n- [Generative networks](https://github.com/satellite-image-deep-learning/techniques?tab=readme-ov-file#generative-networks)\n- [Autoencoders, dimensionality reduction, image embeddings \u0026 similarity search](https://github.com/satellite-image-deep-learning/techniques?tab=readme-ov-file#autoencoders-dimensionality-reduction-image-embeddings--similarity-search)\n- [Few \u0026 zero shot learning](https://github.com/satellite-image-deep-learning/techniques?tab=readme-ov-file#few--zero-shot-learning)\n- [Self-supervised, unsupervised \u0026 contrastive learning](https://github.com/satellite-image-deep-learning/techniques?tab=readme-ov-file#self-supervised-unsupervised--contrastive-learning)\n- [SAR](https://github.com/satellite-image-deep-learning/techniques?tab=readme-ov-file#sar)\n- [Large vision \u0026 language models (LLMs \u0026 LVMs)](https://github.com/satellite-image-deep-learning/techniques?tab=readme-ov-file#large-vision--language-models-llms--lvms)\n- [Foundational models](https://github.com/satellite-image-deep-learning/techniques?tab=readme-ov-file#foundational-models)\n\n#\n## Classification\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"images/merced.png\" width=\"600\"\u003e\n  \u003cbr\u003e\n  \u003cb\u003eThe UC merced dataset is a well known classification dataset.\u003c/b\u003e\n\u003c/p\u003e\n\nClassification is a fundamental task in remote sensing data analysis, where the goal is to assign a semantic label to each image, such as 'urban', 'forest', 'agricultural land', etc. The process of assigning labels to an image is known as image-level classification. However, in some cases, a single image might contain multiple different land cover types, such as a forest with a river running through it, or a city with both residential and commercial areas. In these cases, image-level classification becomes more complex and involves assigning multiple labels to a single image. This can be accomplished using a combination of feature extraction and machine learning algorithms to accurately identify the different land cover types. It is important to note that image-level classification should not be confused with pixel-level classification, also known as semantic segmentation. While image-level classification assigns a single label to an entire image, semantic segmentation assigns a label to each individual pixel in an image, resulting in a highly detailed and accurate representation of the land cover types in an image. Read [A brief introduction to satellite image classification with neural networks](https://medium.com/@robmarkcole/a-brief-introduction-to-satellite-image-classification-with-neural-networks-3ce28be15683)\n\n- Land classification on Sentinel 2 data using a [simple sklearn cluster algorithm](https://github.com/acgeospatial/Satellite_Imagery_Python/blob/master/Clustering_KMeans-Sentinel2.ipynb)\n  \n- [Multi-Label Classification of Satellite Photos of the Amazon Rainforest using keras](https://machinelearningmastery.com/how-to-develop-a-convolutional-neural-network-to-classify-satellite-photos-of-the-amazon-rainforest/)\n\n- [EuroSat-Satellite-CNN-and-ResNet](https://github.com/Rumeysakeskin/EuroSat-Satellite-CNN-and-ResNet) -\u003e Classifying custom image datasets by creating Convolutional Neural Networks and Residual Networks from scratch with PyTorch\n\n- [Detecting Informal Settlements from Satellite Imagery using fine-tuning of ResNet-50 classifier](https://blog.goodaudience.com/detecting-informal-settlements-using-satellite-imagery-and-convolutional-neural-networks-d571a819bf44) with [repo](https://github.com/dymaxionlabs/ap-latam)\n\n-  [Land-Cover-Classification-using-Sentinel-2-Dataset](https://github.com/raoofnaushad/Land-Cover-Classification-using-Sentinel-2-Dataset) -\u003e [well written Medium article](https://raoofnaushad7.medium.com/applying-deep-learning-on-satellite-imagery-classification-5f2588b932c1) accompanying this repo but using the EuroSAT dataset\n\n- [Slums mapping from pretrained CNN network](https://github.com/deepankverma/slums_detection) on VHR (Pleiades: 0.5m) and MR (Sentinel: 10m) imagery\n\n- [Comparing urban environments using satellite imagery and convolutional neural networks](https://github.com/adrianalbert/urban-environments) -\u003e includes interesting study of the image embedding features extracted for each image on the Urban Atlas dataset\n\n- [RSI-CB](https://github.com/lehaifeng/RSI-CB) -\u003e A Large Scale Remote Sensing Image Classification Benchmark via Crowdsource Data. See also [Remote-sensing-image-classification](https://github.com/aashishrai3799/Remote-sensing-image-classification)\n\n- [NAIP_PoolDetection](https://github.com/annaptasznik/NAIP_PoolDetection) -\u003e modelled as an object recognition problem, a CNN is used to identify images as being swimming pools or something else - specifically a street, rooftop, or lawn\n\n- [Land Use and Land Cover Classification using a ResNet Deep Learning Architecture](https://www.luigiselmi.eu/eo/lulc-classification-deeplearning.html) -\u003e uses fastai and the EuroSAT dataset\n\n- [Vision Transformers Use Case: Satellite Image Classification without CNNs](https://medium.com/nerd-for-tech/vision-transformers-use-case-satellite-image-classification-without-cnns-2c4dbeb06f87)\n\n- [WaterNet](https://github.com/treigerm/WaterNet) -\u003e a CNN that identifies water in satellite images\n\n- [Road-Network-Classification](https://github.com/ualsg/Road-Network-Classification) -\u003e Road network classification model using ResNet-34, road classes organic, gridiron, radial and no pattern\n\n- [Scaling AI to map every school on the planet](https://developmentseed.org/blog/2021-03-18-ai-enabling-school-mapping)\n\n- [satellite-crosswalk-classification](https://github.com/rodrigoberriel/satellite-crosswalk-classification)\n\n- [Implementation of the 3D-CNN model for land cover classification](https://medium.com/geekculture/remote-sensing-deep-learning-for-land-cover-classification-of-satellite-imagery-using-python-6a7b4c4f570f) -\u003e uses the Sundarbans dataset, with [repo](https://github.com/syamkakarla98/Satellite_Imagery_Analysis)\n\n- [SSTN](https://github.com/zilongzhong/SSTN) -\u003e Spectral-Spatial Transformer Network for Hyperspectral Image Classification: A FAS Framework\n\n- [SatellitePollutionCNN](https://github.com/arnavbansal1/SatellitePollutionCNN) -\u003e A novel algorithm to predict air pollution levels with state-of-art accuracy using deep learning and GoogleMaps satellite images\n\n- [PropertyClassification](https://github.com/Sardhendu/PropertyClassification) -\u003e Classifying the type of property given Real Estate, satellite and Street view Images\n\n- [remote-sense-quickstart](https://github.com/CarryHJR/remote-sense-quickstart) -\u003e classification on a number of datasets, including with attention visualization\n\n- [Satellite image classification using multiple machine learning algorithms](https://github.com/tanmay-delhikar/satellite-image-analysis-ml)\n\n- [satsense](https://github.com/DynaSlum/satsense) -\u003e land use/cover classification using classical features including HoG \u0026 NDVI\n\n- [PyTorch_UCMerced_LandUse](https://github.com/GeneralLi95/PyTorch_UCMerced_LandUse)\n\n- [EuroSAT-image-classification](https://github.com/artemisart/EuroSAT-image-classification)\n\n- [landcover_classification](https://github.com/reidfalconer/landcover_classification) -\u003e using fast.ai on EuroSAT\n\n- [IGARSS2020_BWMS](https://github.com/jiankang1991/IGARSS2020_BWMS) -\u003e Band-Wise Multi-Scale CNN Architecture for Remote Sensing Image Scene Classification with a novel CNN architecture for the feature embedding of high-dimensional RS images\n\n- [image.classification.on.EuroSAT](https://github.com/canturan10/image.classification.on.EuroSAT) -\u003e solution in pure pytorch\n\n- [hurricane_damage](https://github.com/allankapoor/hurricane_damage) -\u003e Post-hurricane structure damage assessment based on aerial imagery\n\n- [openai-drivendata-challenge](https://github.com/buildwithcycy/openai-drivendata-challenge) -\u003e Using deep learning to classify the building material of rooftops (aerial imagery from South America)\n\n- [is-it-abandoned](https://github.com/zach-brown-18/is-it-abandoned) -\u003e Can we tell if a house is abandoned based on aerial LIDAR imagery?\n\n- [BoulderAreaDetector](https://github.com/pszemraj/BoulderAreaDetector) -\u003e CNN to classify whether a satellite image shows an area would be a good rock climbing spot or not\n\n- [ISPRS_S2FL](https://github.com/danfenghong/ISPRS_S2FL) -\u003e Multimodal Remote Sensing Benchmark Datasets for Land Cover Classification with A Shared and Specific Feature Learning Model\n\n- [Brazilian-Coffee-Detection](https://github.com/MrSquidward/Brazilian-Coffee-Detection) -\u003e uses Keras with public dataset\n\n- [tf-crash-severity](https://github.com/SoySauceNZ/tf-crash-severity) -\u003e predict the crash severity for given road features contained within satellite images\n\n- [ensemble_LCLU](https://github.com/burakekim/ensemble_LCLU) -\u003e Deep neural network ensembles for remote sensing land cover and land use classification\n\n- [cerraNet](https://github.com/MirandaMat/cerraNet-v2) -\u003e contextually classify the types of use and coverage in the Brazilian Cerrado\n\n- [Urban-Analysis-Using-Satellite-Imagery](https://github.com/mominali12/Urban-Analysis-Using-Satellite-Imagery) -\u003e classify urban area as planned or unplanned using a combination of segmentation and classification\n\n- [ChipClassification](https://github.com/yurithefury/ChipClassification) -\u003e Deep learning for multi-modal classification of cloud, shadow and land cover scenes in PlanetScope and Sentinel-2 imagery\n\n- [DeeplearningClassficationLandsat-tImages](https://github.com/VinayarajPoliyapram/DeeplearningClassficationLandsat-tImages) -\u003e Water/Ice/Land Classification Using Large-Scale Medium Resolution Landsat Satellite Images\n\n- [wildfire-detection-from-satellite-images-ml](https://github.com/shrey24/wildfire-detection-from-satellite-images-ml) -\u003e detect whether an image contains a wildfire, with example flask web app\n\n- [mining-discovery-with-deep-learning](https://github.com/remis/mining-discovery-with-deep-learning) -\u003e Mining and Tailings Dam Detection in Satellite Imagery Using Deep Learning\n\n- [e-Farmerce-platform](https://github.com/efarmerce/e-Farmerce-platform) -\u003e classify crop type\n\n- [sentinel2-deep-learning](https://github.com/d-smit/sentinel2-deep-learning) -\u003e Novel Training Methodologies for Land Classification of Sentinel-2 Imagery\n\n- [RSSC-transfer](https://github.com/risojevicv/RSSC-transfer) -\u003e The Role of Pre-Training in High-Resolution Remote Sensing Scene Classification\n\n- [Classifying Geo-Referenced Photos and Satellite Images for Supporting Terrain Classification](https://github.com/jorgemspereira/Classifying-Geo-Referenced-Photos) -\u003e detect floods\n\n- [Pay-More-Attention](https://github.com/williamzhao95/Pay-More-Attention) -\u003e Remote Sensing Image Scene Classification Based on an Enhanced Attention Module\n\n- [Remote Sensing Image Classification via Improved Cross-Entropy Loss and Transfer Learning Strategy Based on Deep Convolutional Neural Networks](https://github.com/AliBahri94/Remote-Sensing-Image-Classification-via-Improved-Cross-Entropy-Loss-and-Transfer-Learning-Strategy)\n\n- [DenseNet40-for-HRRSISC](https://github.com/BiQiWHU/DenseNet40-for-HRRSISC) -\u003e DenseNet40 for remote sensing image scene classification, uses UC Merced Dataset\n\n- [SKAL](https://github.com/hw2hwei/SKAL) -\u003e Looking Closer at the Scene: Multiscale Representation Learning for Remote Sensing Image Scene Classification\n\n- [potsdam-tensorflow-practice](https://github.com/medicinely/potsdam-tensorflow-practice) -\u003e image classification of Potsdam dataset using tensorflow\n\n- [SAFF](https://github.com/zh-hike/SAFF) -\u003e Self-Attention-Based Deep Feature Fusion for Remote Sensing Scene Classification\n\n- [GLNET](https://github.com/wuchangsheng951/GLNET) -\u003e Convolutional Neural Networks Based Remote Sensing Scene Classification under Clear and Cloudy Environments\n\n- [Remote-sensing-image-classification](https://github.com/hiteshK03/Remote-sensing-image-classification) -\u003e transfer learning using pytorch to classify remote sensing data into three classes: aircrafts, ships, none\n\n- [remote_sensing_pretrained_models](https://github.com/lsh1994/remote_sensing_pretrained_models) -\u003e as an alternative to fine tuning on models pretrained on ImageNet, here some CNN are pretrained on the RSD46-WHU \u0026 AID datasets\n\n- [CNN_AircraftDetection](https://github.com/UKMIITB/CNN_AircraftDetection) -\u003e CNN for aircraft detection in satellite images using keras\n\n- [OBIC-GCN](https://github.com/CVEO/OBIC-GCN) -\u003e Object-based Classification Framework of Remote Sensing Images with Graph Convolutional Networks\n\n- [aitlas-arena](https://github.com/biasvariancelabs/aitlas-arena) -\u003e An open-source benchmark framework for evaluating state-of-the-art deep learning approaches for image classification in Earth Observation (EO)\n\n- [droughtwatch](https://github.com/wandb/droughtwatch) -\u003e Satellite-based Prediction of Forage Conditions for Livestock in Northern Kenya\n\n- [JSTARS_2020_DPN-HRA](https://github.com/B-Xi/JSTARS_2020_DPN-HRA) -\u003e Deep Prototypical Networks With Hybrid Residual Attention for Hyperspectral Image Classification\n\n- [SIGNA](https://github.com/kyle-one/SIGNA) -\u003e Semantic Interleaving Global Channel Attention for Multilabel Remote Sensing Image Classification\n\n- [PBDL](https://github.com/Usman1021/PBDL) -\u003e Patch-Based Discriminative Learning for Remote Sensing Scene Classification\n\n- [EmergencyNet](https://github.com/ckyrkou/EmergencyNet) -\u003e identify fire and other emergencies from a drone\n\n- [satellite-deforestation](https://github.com/drewhibbard/satellite-deforestation) -\u003e Using Satellite Imagery to Identify the Leading Indicators of Deforestation, applied to the Kaggle Challenge Understanding the Amazon from Space\n\n- [RSMLC](https://github.com/marjanstoimchev/RSMLC) -\u003e Deep Network Architectures as Feature Extractors for Multi-Label Classification of Remote Sensing Images\n\n- [FireRisk](https://github.com/CharmonyShen/FireRisk) -\u003e A Remote Sensing Dataset for Fire Risk Assessment with Benchmarks Using Supervised and Self-supervised Learning\n\n- [flood_susceptibility_mapping](https://github.com/omarseleem92/flood_susceptibility_mapping) -\u003e Towards urban flood susceptibility mapping using data-driven models in Berlin, Germany\n\n- [tick-tick-bloom](https://github.com/drivendataorg/tick-tick-bloom) -\u003e Winners of the Tick Tick Bloom: Harmful Algal Bloom Detection Challenge. Task was to predict severity of algae bloom, winners used decision trees\n\n- [Estimating coal power plant operation from satellite images with computer vision](https://transitionzero.medium.com/estimating-coal-power-plant-operation-from-satellite-images-with-computer-vision-b966af56919e) -\u003e use Sentinel 2 data to identify if a coal power plant is on or off, with dataset and repo\n\n- [Building-detection-and-roof-type-recognition](https://github.com/loosgagnet/Building-detection-and-roof-type-recognition) -\u003e A CNN-Based Approach for Automatic Building Detection and Recognition of Roof Types Using a Single Aerial Image\n\n- [Performance Comparison of Multispectral Channels for Land Use Classification](https://github.com/tejasri19/EuroSAT_data_analysis) -\u003e Implemented ResNet-50, ResNet-101, ResNet-152, Vision Transformer on RGB and multispectral versions of EuroSAT dataset.\n\n- [SNN4Space](https://github.com/AndrzejKucik/SNN4Space) -\u003e project which investigates the feasibility of deploying spiking neural networks (SNN) in land cover and land use classification tasks\n\n- [vessel-classification](https://github.com/GlobalFishingWatch/vessel-classification) -\u003e classify vessels and identify fishing behavior based on AIS data\n\n- [RSMamba](https://github.com/KyanChen/RSMamba) -\u003e Remote Sensing Image Classification with State Space Model\n\n- [BirdSAT](https://github.com/mvrl/BirdSAT) -\u003e Cross-View Contrastive Masked Autoencoders for Bird Species Classification and Mapping\n\n- [EGNNA_WND](https://github.com/stevinc/EGNNA_WND) -\u003e Estimating the presence of the West Nile Disease employing Graph Neural network\n\n- [cyfi](https://github.com/drivendataorg/cyfi) -\u003e Estimate cyanobacteria density based on Sentinel-2 satellite imagery\n\n- [3DGAN-ViT](https://github.com/aj1365/3DGAN-ViT) -\u003e A deep learning framework based on generative adversarial networks and vision transformer for complex wetland classification puplished in [International Journal of Applied Earth Observation and Geoinformation](https://www.sciencedirect.com/science/article/pii/S1569843222002837)\n\n- [EfficientBigEarthNet](https://github.com/Orion-AI-Lab/EfficientBigEarthNet) -\u003e Code and models from the paper [Benchmarking and scaling of deep learning models for land cover image classification](https://www.sciencedirect.com/science/article/pii/S0924271622003057).\n\n- [automatic_solar_pv_detection](https://github.com/KennSmithDS/automatic_solar_pv_detection) -\u003e Automatic Solar PV Panel Image Classification with Deep Neural Network Transfer Learning\n\n- [U-netR](https://github.com/JonathanVSV/U-netR) -\u003e Land Use Land Cover Classification with U-Net: Advantages of Combining Sentinel-1 and Sentinel-2 Imagery [paper](https://doi.org/10.3390/rs13183600)\n\n#\n## Segmentation\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"images/segmentation.png\" width=\"500\"\u003e\n  \u003cbr\u003e\n  \u003cb\u003e(left) a satellite image and (right) the semantic classes in the image.\u003c/b\u003e\n\u003c/p\u003e\n\nImage segmentation is a crucial step in image analysis and computer vision, with the goal of dividing an image into semantically meaningful segments or regions. The process of image segmentation assigns a class label to each pixel in an image, effectively transforming an image from a 2D grid of pixels into a 2D grid of pixels with assigned class labels. One common application of image segmentation is road or building segmentation, where the goal is to identify and separate roads and buildings from other features within an image. To accomplish this task, single class models are often trained to differentiate between roads and background, or buildings and background. These models are designed to recognize specific features, such as color, texture, and shape, that are characteristic of roads or buildings, and use this information to assign class labels to the pixels in an image. Another common application of image segmentation is land use or crop type classification, where the goal is to identify and map different land cover types within an image. In this case, multi-class models are typically used to recognize and differentiate between multiple classes within an image, such as forests, urban areas, and agricultural land. These models are capable of recognizing complex relationships between different land cover types, allowing for a more comprehensive understanding of the image content. Read [A brief introduction to satellite image segmentation with neural networks](https://medium.com/@robmarkcole/a-brief-introduction-to-satellite-image-segmentation-with-neural-networks-33ea732d5bce). **Note** that many articles which refer to 'hyperspectral land classification' are often actually describing semantic segmentation.\n\n### Segmentation - Land use \u0026 land cover\n\n- [nga-deep-learning](https://github.com/jordancaraballo/nga-deep-learning) -\u003e performs semantic segmentation on high resultion GeoTIF data using a modified U-Net \u0026 Keras, published by NASA researchers\n\n- [Automatic Detection of Landfill Using Deep Learning](https://github.com/AnupamaRajkumar/LandfillDetection_SemanticSegmentation)\n\n- [SpectralNET](https://github.com/tanmay-ty/SpectralNET) -\u003e a 2D wavelet CNN for Hyperspectral Image Classification, uses Salinas Scene dataset \u0026 Keras\n\n- [laika](https://github.com/datasciencecampus/laika) -\u003e The goal of this repo is to research potential sources of satellite image data and to implement various algorithms for satellite image segmentation\n\n- [PEARL](https://www.landcover.io/) -\u003e a human-in-the-loop AI tool to drastically reduce the time required to produce an accurate Land Use/Land Cover (LULC) map, [blog post](http://devseed.com/blog/2021-05-17-pearl-ai-land-cover), uses Microsoft Planetary Computer and ML models run locally in the browser. Code for [backelnd](https://github.com/developmentseed/pearl-backend) and [frontend](https://github.com/developmentseed/pearl-frontend)\n\n- [Land Cover Classification with U-Net](https://baratam-tarunkumar.medium.com/land-cover-classification-with-u-net-aa618ea64a1b) -\u003e Satellite Image Multi-Class Semantic Segmentation Task with PyTorch Implementation of U-Net, uses DeepGlobe Land Cover Segmentation dataset, with [code](https://github.com/TarunKumar1995-glitch/land_cover_classification_unet)\n\n- [Multi-class semantic segmentation of satellite images using U-Net](https://github.com/rogerxujiang/dstl_unet) using DSTL dataset, tensorflow 1 \u0026 python 2.7. \n\n- [Codebase for multi class land cover classification with U-Net](https://github.com/jaeeolma/lulc_ml) accompanying a masters thesis, uses Keras\n\n- [dubai-satellite-imagery-segmentation](https://github.com/ayushdabra/dubai-satellite-imagery-segmentation) -\u003e due to the small dataset, image augmentation was used\n\n- [CDL-Segmentation](https://github.com/asimniazi63/CDL-Segmentation) -\u003e Deep Learning Based Land Cover and Crop Type Classification: A Comparative Study. Compares UNet, SegNet \u0026 DeepLabv3+\n\n- [LoveDA](https://github.com/Junjue-Wang/LoveDA) -\u003e A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation\n\n- [Satellite Imagery Semantic Segmentation with CNN](https://joshting.medium.com/satellite-imagery-segmentation-with-convolutional-neural-networks-f9254de3b907) -\u003e 7 different segmentation classes, DeepGlobe Land Cover Classification Challenge dataset, with [repo](https://github.com/justjoshtings/satellite_image_segmentation)\n\n- [Aerial Semantic Segmentation using U-Net Deep Learning Model](https://medium.com/@rehman.aimal/aerial-semantic-segmentation-using-u-net-deep-learning-model-3356a53c915f) medium article, with [repo](https://github.com/aimalrehman92/Multiclass-Semantic-Segmentation-with-U-NET)\n\n- [UNet-Satellite-Image-Segmentation](https://github.com/YudeWang/UNet-Satellite-Image-Segmentation) -\u003e A Tensorflow implentation of light UNet semantic segmentation framework\n\n- [DeepGlobe Land Cover Classification Challenge solution](https://github.com/GeneralLi95/deepglobe_land_cover_classification_with_deeplabv3plus)\n\n- [Semantic-segmentation-with-PyTorch-Satellite-Imagery](https://github.com/JenAlchimowicz/Semantic-segmentation-with-PyTorch-Satellite-Imagery) -\u003e predict 25 classes on RGB imagery taken to assess the damage after Hurricane Harvey\n\n- [Semantic Segmentation With Sentinel-2 Imagery](https://github.com/pavlo-seimskyi/semantic-segmentation-satellite-imagery) -\u003e uses LandCoverNet dataset and fast.ai\n\n- [CNN_Enhanced_GCN](https://github.com/qichaoliu/CNN_Enhanced_GCN) -\u003e CNN-Enhanced Graph Convolutional Network With Pixel- and Superpixel-Level Feature Fusion for Hyperspectral Image Classification\n\n- [LULCMapping-WV3images-CORINE-DLMethods](https://github.com/esertel/LULCMapping-WV3images-CORINE-DLMethods) -\u003e Land Use and Land Cover Mapping Using Deep Learning Based Segmentation Approaches and VHR Worldview-3 Images\n\n- [MCANet](https://github.com/yisun98/SOLC) -\u003e A joint semantic segmentation framework of optical and SAR images for land use classification. Uses [WHU-OPT-SAR-dataset](https://github.com/AmberHen/WHU-OPT-SAR-dataset)\n\n- [MUnet-LUC](https://github.com/abhi170599/MUnet-LUC)\n\n- [land-cover](https://github.com/lucashu1/land-cover) -\u003e Model Generalization in Deep Learning Applications for Land Cover Mapping\n\n- [generalizablersc](https://github.com/dgominski/generalizablersc) -\u003e Cross-dataset Learning for Generalizable Land Use Scene Classification\n\n- [Large-scale-Automatic-Identification-of-Urban-Vacant-Land](https://github.com/SkydustZ/Large-scale-Automatic-Identification-of-Urban-Vacant-Land) -\u003e Large-scale automatic identification of urban vacant land using semantic segmentation of high-resolution remote sensing images\n\n- [SSLTransformerRS](https://github.com/HSG-AIML/SSLTransformerRS) -\u003e Self-supervised Vision Transformers for Land-cover Segmentation and\n  Classification\n\n- [aerial-tile-segmentation](https://github.com/mrsebai/aerial-tile-segmentation) -\u003e Large satellite image semantic segmentation into 6 classes using Tensorflow 2.0 and ISPRS benchmark dataset\n\n- [LULCMapping-WV3images-CORINE-DLMethods](https://github.com/burakekim/LULCMapping-WV3images-CORINE-DLMethods) -\u003e Land Use and Land Cover Mapping Using Deep Learning Based Segmentation Approaches and VHR Worldview-3 Images\n\n- [DCSA-Net](https://github.com/Julia90/DCSA-Net) -\u003e Dynamic Convolution Self-Attention Network for Land-Cover Classification in VHR Remote-Sensing Images\n\n- [CHeGCN-CNN_enhanced_Heterogeneous_Graph](https://github.com/Liuzhizhiooo/CHeGCN-CNN_enhanced_Heterogeneous_Graph) -\u003e CNN-Enhanced Heterogeneous Graph Convolutional Network: Inferring Land Use from Land Cover with a Case Study of Park Segmentation\n\n- [TCSVT_2022_DGSSC](https://github.com/B-Xi/TCSVT_2022_DGSSC) -\u003e DGSSC: A Deep Generative Spectral-Spatial Classifier for Imbalanced Hyperspectral Imagery\n\n- [DeepForest-Wetland-Paper](https://github.com/aj1365/DeepForest-Wetland-Paper) -\u003e Deep Forest classifier for wetland mapping using the combination of Sentinel-1 and Sentinel-2 data, GIScience \u0026 Remote Sensing\n\n- [Wetland_UNet](https://github.com/conservation-innovation-center/Wetland_UNet) -\u003e UNet models that can delineate wetlands using remote sensing data input including bands from Sentinel-2 LiDAR and geomorphons. By the Conservation Innovation Center of Chesapeake Conservancy and Defenders of Wildlife\n\n- [DPA](https://github.com/x-ytong/DPA) -\u003e DPA is an unsupervised domain adaptation (UDA) method applied to different satellite images for larg-scale land cover mapping.\n\n- [dynamicworld](https://github.com/google/dynamicworld) -\u003e Dynamic World, Near real-time global 10 m land use land cover mapping\n\n- [spada](https://github.com/links-ads/spada) -\u003e Land Cover Segmentation with Sparse Annotations from Sentinel-2 Imagery\n\n- [M3SPADA](https://github.com/ecapliez/M3SPADA) -\u003e  Multi-Sensor Temporal Unsupervised Domain Adaptation for Land Cover Mapping with spatial pseudo labelling and adversarial learning\n\n- [GLNet](https://github.com/VITA-Group/GLNet) -\u003e Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images\n\n- [LoveNAS](https://github.com/Junjue-Wang/LoveNAS) -\u003e LoveNAS: Towards Multi-Scene Land-Cover Mapping via Hierarchical Searching Adaptive Network\n\n- [FLAIR-2 challenge](https://github.com/IGNF/FLAIR-2) -\u003e Semantic segmentation and domain adaptation challenge proposed by the French National Institute of Geographical and Forest Information (IGN)\n\n- [flair-2 8th place solution](https://github.com/association-rosia/flair-2)\n\n- [igarss-spada](https://github.com/links-ads/spada) -\u003e Dataset and code for the paper Land Cover Segmentation with Sparse Annotations from Sentinel-2 Imagery [IGARSS 2023](https://arxiv.org/abs/2306.16252). \n\n### Segmentation - Vegetation, deforestation, crops \u0026 crop boundaries\n\nNote that deforestation detection may be treated as a segmentation task or a change detection task\n\n- [DetecTree](https://github.com/martibosch/detectree) -\u003e Tree detection from aerial imagery in Python, a LightGBM classifier of tree/non-tree pixels from aerial imagery\n\n- [Сrор field boundary detection: approaches and main challenges](https://medium.com/geekculture/%D1%81r%D0%BE%D1%80-field-boundary-detection-approaches-and-main-challenges-46e37dd276bc) -\u003e Medium article, covering historical and modern approaches\n\n- [kenya-crop-mask](https://github.com/nasaharvest/kenya-crop-mask) -\u003e Annual and in-season crop mapping in Kenya - LSTM classifier to classify pixels as containing crop or not, and a multi-spectral forecaster that provides a 12 month time series given a partial input. Dataset downloaded from GEE and pytorch lightning used for training\n\n- [Tree species classification from from airborne LiDAR and hyperspectral data using 3D convolutional neural networks](https://github.com/jaeeolma/tree-detection-evo)\n\n- [crop-type-classification](https://medium.com/nerd-for-tech/crop-type-classification-cf5cc2593396) -\u003e using Sentinel 1 \u0026 2 data with a U-Net + LSTM, more features (i.e. bands) and higher resolution produced better results (article, no code)\n\n- [Find sports fields using Mask R-CNN and overlay on open-street-map](https://github.com/jremillard/images-to-osm)\n\n- [An LSTM to generate a crop mask for Togo](https://github.com/nasaharvest/togo-crop-mask)\n\n- [DeepSatModels](https://github.com/michaeltrs/DeepSatModels) -\u003e Context-self contrastive pretraining for crop type semantic segmentation\n\n- [farm-pin-crop-detection-challenge](https://github.com/simongrest/farm-pin-crop-detection-challenge) -\u003e Using eo-learn and fastai to identify crops from multi-spectral remote sensing data\n\n- [Detecting Agricultural Croplands from Sentinel-2 Satellite Imagery](https://medium.com/radiant-earth-insights/detecting-agricultural-croplands-from-sentinel-2-satellite-imagery-a025735d3bd8) -\u003e We developed UNet-Agri, a benchmark machine learning model that classifies croplands using open-access Sentinel-2 imagery at 10m spatial resolution\n\n- [DeepTreeAttention](https://github.com/weecology/DeepTreeAttention) -\u003e Implementation of Hang et al. 2020 \"Hyperspectral Image Classification with Attention Aided CNNs\" for tree species prediction\n\n- [Crop-Classification](https://github.com/bhavesh907/Crop-Classification) -\u003e crop classification using multi temporal satellite images\n\n- [ParcelDelineation](https://github.com/sustainlab-group/ParcelDelineation) -\u003e using a French polygons dataset and unet in keras\n\n- [crop-mask](https://github.com/nasaharvest/crop-mask) -\u003e End-to-end workflow for generating high resolution cropland maps, uses GEE \u0026 LSTM model\n\n- [DeepCropMapping](https://github.com/Lab-IDEAS/DeepCropMapping) -\u003e A multi-temporal deep learning approach with improved spatial generalizability for dynamic corn and soybean mapping, uses LSTM\n\n- [ResUnet-a](https://github.com/Akhilesh64/ResUnet-a) -\u003e a deep learning framework for semantic segmentation of remotely sensed data\n\n- [DSD_paper_2020](https://github.com/JacobJeppesen/DSD_paper_2020) -\u003e Crop Type Classification based on Machine Learning with Multitemporal Sentinel-1 Data\n\n- [MR-DNN](https://github.com/yasir2afaq/Multi-resolution-deep-neural-network) -\u003e extract rice field from Landsat 8 satellite imagery\n\n- [deep_learning_forest_monitoring](https://github.com/waldeland/deep_learning_forest_monitoring) -\u003e Forest mapping and monitoring of the African continent using Sentinel-2 data and deep learning\n\n- [global-cropland-mapping](https://github.com/Charly-tian/global-cropland-mapping) -\u003e global multi-temporal cropland mapping\n\n- [U-Net for Semantic Segmentation of Soyabean Crop Fields with SAR images](https://joaootavionf007.medium.com/u-net-for-semantic-segmentation-of-soyabeans-crop-fields-with-sar-images-604232e49315)\n\n- [UNet-RemoteSensing](https://github.com/aryanVijaywargia/UNet-RemoteSensing) -\u003e uses 7 bands of Landsat and keras\n\n- [Landuse_DL](https://github.com/yghlc/Landuse_DL) -\u003e delineate landforms due to the thawing of ice-rich permafrost\n\n- [canopy](https://github.com/jonathanventura/canopy) -\u003e A Convolutional Neural Network Classifier Identifies Tree Species in Mixed-Conifer Forest from Hyperspectral Imagery\n\n- [RandomForest-Classification](https://github.com/florianbeyer/RandomForest-Classification) -\u003e Multisensor data to derive peatland vegetation communities using a fixed-wing unmanned aerial vehicle\n\n- [forest_change_detection](https://github.com/QuantuMobileSoftware/forest_change_detection) -\u003e forest change segmentation with time-dependent models, including Siamese, UNet-LSTM, UNet-diff, UNet3D models\n\n- [cultionet](https://github.com/jgrss/cultionet) -\u003e segmentation of cultivated land, built on PyTorch Geometric and PyTorch Lightning\n\n- [sentinel-tree-cover](https://github.com/wri/sentinel-tree-cover) -\u003e A global method to identify trees outside of closed-canopy forests with medium-resolution satellite imagery\n\n- [crop-type-detection-ICLR-2020](https://github.com/RadiantMLHub/crop-type-detection-ICLR-2020) -\u003e Winning Solutions from Crop Type Detection Competition at CV4A workshop, ICLR 2020\n\n- [Crop identification using satellite imagery](https://write.agrevolution.in/crop-identification-using-satellite-imagery-introduction-83d79344f9ee) -\u003e Medium article, introduction to crop identification\n\n- [S4A-Models](https://github.com/Orion-AI-Lab/S4A-Models) -\u003e Various experiments on the Sen4AgriNet dataset\n\n- [attention-mechanism-unet](https://github.com/davej23/attention-mechanism-unet) -\u003e An attention-based U-Net for detecting deforestation within satellite sensor imagery\n\n- [Cocoa_plantations_detection](https://github.com/antoine-spahr/Cocoa_plantations_detection) -\u003e Detecting cocoa plantation in Ivory Coast using Sentinel-2 remote sensing data using KNN, SVM, Random Forest and MLP\n\n- [SummerCrop_Deeplearning](https://github.com/AgriRS/SummerCrop_Deeplearning) -\u003e A Transferable Learning Classification Model and Carbon Sequestration Estimation of Crops in Farmland Ecosystem\n\n- [DeepForest](https://deepforest.readthedocs.io/en/latest/index.html) is a python package for training and predicting individual tree crowns from airborne RGB imagery\n\n- [Official repository for the \"Identifying trees on satellite images\" challenge from Omdena](https://github.com/cienciaydatos/ai-challenge-trees)\n\n- [Counting-Trees-using-Satellite-Images](https://github.com/A2Amir/Counting-Trees-using-Satellite-Images) -\u003e create an inventory of incoming and outgoing trees for an annual tree inspections, uses keras \u0026 semantic segmentation\n\n- [2020 Nature paper - An unexpectedly large count of trees in the West African Sahara and Sahel](https://www.nature.com/articles/s41586-020-2824-5) -\u003e tree detection framework based on U-Net \u0026 tensorflow 2 with code [here](https://github.com/ankitkariryaa/An-unexpectedly-large-count-of-trees-in-the-western-Sahara-and-Sahel/tree/v1.0.0)\n\n- [TreeDetection](https://github.com/AmirNiaraki/TreeDetection) -\u003e A color-based classifier to detect the trees in google image data along with tree visual localization and crown size calculations via OpenCV\n\n- [PTDM](https://github.com/hr8yhtzb/PTDM) -\u003e Pomelo Tree Detection Method Based on Attention Mechanism and Cross-Layer Feature Fusion\n\n- [urban-tree-detection](https://github.com/jonathanventura/urban-tree-detection) -\u003e Individual Tree Detection in Large-Scale Urban Environments using High-Resolution Multispectral Imagery. With [dataset](https://github.com/jonathanventura/urban-tree-detection-data)\n\n- [BioMassters_baseline](https://github.com/fnands/BioMassters_baseline) -\u003e a basic pytorch lightning baseline using a UNet for getting started with the [BioMassters challenge](https://www.drivendata.org/competitions/99/biomass-estimation/) (biomass estimation)\n\n- [Biomassters winners](https://github.com/drivendataorg/the-biomassters) -\u003e top 3 solutions\n\n- [kbrodt biomassters solution](https://github.com/kbrodt/biomassters) -\u003e 1st place solution\n\n- [quqixun biomassters solution](https://github.com/quqixun/BioMassters)\n\n- [biomass-estimation](https://github.com/azavea/biomass-estimation) -\u003e from Azavea, applied to Sentinel 1 \u0026 2\n\n- [3DUNetGSFormer](https://github.com/aj1365/3DUNetGSFormer) -\u003e A deep learning pipeline for complex wetland mapping using generative adversarial networks and Swin transformer\n\n- [SEANet_torch](https://github.com/long123524/SEANet_torch) -\u003e Using a semantic edge-aware multi-task neural network to delineate agricultural parcels from remote sensing images\n\n- [arborizer](https://github.com/RaffiBienz/arborizer) -\u003e Tree crowns segmentation and classification\n\n- [ReUse](https://github.com/priamus-lab/ReUse) -\u003e REgressive Unet for Carbon Storage and Above-Ground Biomass Estimation\n\n- [unet-sentinel](https://github.com/eliasqueirogavieira/unet-sentinel) -\u003e UNet to handle Sentinel-1 SAR images to identify deforestation\n\n- [MaskedSST](https://github.com/HSG-AIML/MaskedSST) -\u003e Masked Vision Transformers for Hyperspectral Image Classification\n\n- [UNet-defmapping](https://github.com/bragagnololu/UNet-defmapping) -\u003e master's thesis using UNet to map deforestation using Sentinel-2 Level 2A images, applied to Amazon and Atlantic Rainforest dataset\n\n- [cvpr-multiearth-deforestation-segmentation](https://github.com/h2oai/cvpr-multiearth-deforestation-segmentation) -\u003e multimodal Unet entry to the CVPR Multiearth 2023 deforestation challenge\n\n- [supervised-wheat-classification-using-pytorchs-torchgeo](https://medium.com/@sulemanhamdani10/supervised-wheat-classification-using-pytorchs-torchgeo-combining-satellite-imagery-and-python-fc7f95c82e) -\u003e supervised wheat classification using torchgeo\n\n- [TransUNetplus2](https://github.com/aj1365/TransUNetplus2) -\u003e TransU-Net++: Rethinking attention gated TransU-Net for deforestation mapping. Uses the Amazon and Atlantic forest dataset\n\n- [A high-resolution canopy height model of the Earth](https://github.com/langnico/global-canopy-height-model#a-high-resolution-canopy-height-model-of-the-earth) -\u003e A high-resolution canopy height model of the Earth\n\n- [Radiant Earth Spot the Crop Challenge](https://github.com/radiantearth/spot-the-crop-challenge) -\u003e Winning models from the Radiant Earth Spot the Crop Challenge, uses a time-series of Sentinel-2 multispectral data to classify crops in the Western Cape of South Africa. [Another solution](https://github.com/DariusTheGeek/Radiant-Earth-Spot-the-Crop-XL-Challenge)\n\n- [transfer-field-delineation](https://github.com/kerner-lab/transfer-field-delineation) -\u003e Multi-Region Transfer Learning for Segmentation of Crop Field Boundaries in Satellite Images with Limited Labels\n\n- [mowing-detection](https://github.com/lucas-batier/mowing-detection) -\u003e Automatic detection of mowing and grazing from Sentinel images\n\n- [PTAViT3D and PTAViT3DCA](https://github.com/feevos/tfcl) -\u003e Tackling fluffy clouds: field boundaries detection using time series of S2 and/or S1 imagery\n\n- [ai4boundaries](https://github.com/waldnerf/ai4boundaries) -\u003e a Python package that facilitates download of the AI4boundaries data set\n\n- [Nasa_harvest_field_boundary_competition](https://github.com/radiantearth/Nasa_harvest_field_boundary_competition) -\u003e Nasa Harvest Rwanda Field Boundary Detection Challenge Tutorial\n\n- [UTB_codes](https://github.com/zhu-xlab/UTB_codes) -\u003e The Urban Tree Canopy Cover in Brazil [article](https://nkszjx.github.io/projects/UTB.html)\n\n- [nasa_harvest_boundary_detection_challenge](https://github.com/geoaigroup/nasa_harvest_boundary_detection_challenge) -\u003e the 4th place solution for NASA Harvest Field Boundary Detection Challenge on Zindi.\n\n- [rainforest-segmentation](https://github.com/jcblsn/rainforest-segmentation) -\u003e Identifying and tracking deforestation in the Amazon Rainforest using state-of-the-art deep learning models and multispectral satellite imagery.\n\n### Segmentation - Water, coastlines, rivers \u0026 floods\n\n- [pytorch-waterbody-segmentation](https://github.com/gauthamk02/pytorch-waterbody-segmentation) -\u003e UNET model trained on the Satellite Images of Water Bodies dataset from Kaggle. The model is deployed on Hugging Face Spaces\n\n- [Flood Detection and Analysis using UNET with Resnet-34 as the back bone](https://github.com/orion29/Satellite-Image-Segmentation-for-Flood-Damage-Analysis) uses fastai\n\n- [Automatic Flood Detection from Satellite Images Using Deep Learning](https://medium.com/@omercaliskan99/automatic-flood-detection-from-satellite-images-using-deep-learning-f14fafd369e0)\n\n- [UNSOAT used fastai to train a Unet to perform semantic segmentation on satellite imageries to detect water](https://forums.fast.ai/t/unosat-used-fastai-ai-for-their-floodai-model-discussion-on-how-to-move-forward/78468)\n\n- [Semi-Supervised Classification and Segmentation on High Resolution Aerial Images - Solving the FloodNet problem](https://sahilkhose.medium.com/paper-presentation-e9bd0f3fb0bf)\n\n- [Houston_flooding](https://github.com/Lichtphyz/Houston_flooding) -\u003e labeling each pixel as either flooded or not using data from Hurricane Harvey. Dataset consisted of pre and post flood images, and a ground truth floodwater mask was created using unsupervised clustering (with DBScan) of image pixels with human cluster verification/adjustment\n\n- [ml4floods](https://github.com/spaceml-org/ml4floods) -\u003e An ecosystem of data, models and code pipelines to tackle flooding with ML\n\n- [A comprehensive guide to getting started with the ETCI Flood Detection competition](https://medium.com/cloud-to-street/jumpstart-your-machine-learning-satellite-competition-submission-2443b40d0a5a) -\u003e using Sentinel1 SAR \u0026 pytorch\n\n- [Map Floodwater of SAR Imagery with SageMaker](https://github.com/JayThibs/map-floodwater-sar-imagery-on-sagemaker) -\u003e applied to Sentinel-1 dataset\n\n- [1st place solution for STAC Overflow: Map Floodwater from Radar Imagery hosted by Microsoft AI for Earth](https://github.com/sweetlhare/STAC-Overflow) -\u003e combines Unet with Catboostclassifier, taking their maxima, not the average\n\n- [hydra-floods](https://github.com/Servir-Mekong/hydra-floods) -\u003e an open source Python application for downloading, processing, and delivering surface water maps derived from remote sensing data\n\n- [CoastSat](https://github.com/kvos/CoastSat) -\u003e tool for mapping coastlines which has an extension [CoastSeg](https://github.com/dbuscombe-usgs/CoastSeg) using segmentation models\n\n- [Satellite_Flood_Segmentation_of_Harvey](https://github.com/morgan-tam/Satellite_Flood_Segmentation_of_Harvey) -\u003e explores both deep learning and traditional kmeans\n\n- [Flood Event Detection Utilizing Satellite Images](https://github.com/KonstantinosF/Flood-Detection---Satellite-Images)\n\n- [ETCI-2021-Competition-on-Flood-Detection](https://github.com/sidgan/ETCI-2021-Competition-on-Flood-Detection) -\u003e Experiments on Flood Segmentation on Sentinel-1 SAR Imagery with Cyclical Pseudo Labeling and Noisy Student Training\n\n- [FDSI](https://github.com/keillernogueira/FDSI) -\u003e Flood Detection in Satellite Images - 2017 Multimedia Satellite Task\n\n- [deepwatermap](https://github.com/isikdogan/deepwatermap) -\u003e a deep model that segments water on multispectral images\n\n- [rivamap](https://github.com/isikdogan/rivamap) -\u003e an automated river analysis and mapping engine\n\n- [deep-water](https://github.com/maxbeber/deep-water) -\u003e track changes in water level\n\n- [WatNet](https://github.com/xinluo2018/WatNet) -\u003e A deep ConvNet for surface water mapping based on Sentinel-2 image, uses the [Earth Surface Water Dataset](https://zenodo.org/record/5205674#.YoMjyZPMK3I)\n\n- [A-U-Net-for-Flood-Extent-Mapping](https://github.com/jorgemspereira/A-U-Net-for-Flood-Extent-Mapping)\n\n- [floatingobjects](https://github.com/ESA-PhiLab/floatingobjects) -\u003e TOWARDS DETECTING FLOATING OBJECTS ON A GLOBAL SCALE WITHLEARNED SPATIAL FEATURES USING SENTINEL 2. Uses U-Net \u0026 pytorch\n\n- [SpaceNet8](https://github.com/SpaceNetChallenge/SpaceNet8) -\u003e baseline Unet solution to detect flooded roads and buildings\n\n- [dlsim](https://github.com/nyokoya/dlsim) -\u003e Breaking the Limits of Remote Sensing by Simulation and Deep Learning for Flood and Debris Flow Mapping\n\n- [Water-HRNet](https://github.com/faye0078/Water-Extraction) -\u003e HRNet trained on Sentinel 2\n\n- [semantic segmentation model to identify newly developed or flooded land](https://github.com/Azure/pixel_level_land_classification) using NAIP imagery provided by the Chesapeake Conservancy, training on MS Azure\n\n- [BandNet](https://github.com/IamShubhamGupto/BandNet) -\u003e Analysis and application of multispectral data for water segmentation using machine learning. Uses Sentinel-2 data\n\n- [mmflood](https://github.com/edornd/mmflood) -\u003e MMFlood: A Multimodal Dataset for Flood Delineation From Satellite Imagery (Sentinel 1 SAR)\n\n- [Urban_flooding](https://github.com/omarseleem92/Urban_flooding) -\u003e Towards transferable data-driven models to predict urban pluvial flood water depth in Berlin, Germany\n\n- [Flood-Mapping-Using-Satellite-Images](https://github.com/KonstantinosF/Flood-Mapping-Using-Satellite-Images) -\u003e masters thesis comparing Random Forest \u0026 Unet\n\n- [MECNet](https://github.com/zhilyzhang/MECNet) -\u003e Rich CNN features for water-body segmentation from very high resolution aerial and satellite imagery\n\n- [SWRNET](https://github.com/trongan93/swrnet) -\u003e A Deep Learning Approach for Small Surface Water Area Recognition Onboard Satellite\n\n- [elwha-segmentation](https://github.com/StefanTodoran/elwha-segmentation) -\u003e fine-tuning Meta's Segment Anything (SAM) for bird's eye view river pixel segmentation\n\n- [RiverSnap](https://github.com/ArminMoghimi/RiverSnap) -\u003e code for paper: A Comparative Performance Analysis of Popular Deep Learning Models and Segment Anything Model (SAM) for River Water Segmentation in Close-Range Remote Sensing Imagery\n\n- [SAR-water-segmentation](https://github.com/myeungun/SAR-water-segmentation) -\u003e Deep Learning based Water Segmentation Using KOMPSAT-5 SAR Images\n\n### Segmentation - Fire, smoke \u0026 burn areas\n\n- [SatelliteVu-AWS-Disaster-Response-Hackathon](https://github.com/SatelliteVu/SatelliteVu-AWS-Disaster-Response-Hackathon) -\u003e fire spread prediction using classical ML \u0026 deep learning\n\n- [Wild Fire Detection](https://github.com/yueureka/WildFireDetection) using U-Net trained on Databricks \u0026 Keras, semantic segmentation\n\n- [A Practical Method for High-Resolution Burned Area Monitoring Using Sentinel-2 and VIIRS](https://github.com/mnpinto/FireHR)\n\n- [IndustrialSmokePlumeDetection](https://github.com/HSG-AIML/IndustrialSmokePlumeDetection) -\u003e using Sentinel-2 \u0026 a modified ResNet-50\n\n- [burned-area-detection](https://github.com/dymaxionlabs/burned-area-detection) -\u003e uses Sentinel-2\n\n- [rescue](https://github.com/dbdmg/rescue) -\u003e Attention to fires: multi-channel deep-learning models forwildfire severity prediction\n\n- [smoke_segmentation](https://github.com/jeffwen/smoke_segmentation) -\u003e Segmenting smoke plumes and predicting density from GOES imagery\n\n- [wildfire-detection](https://github.com/amanbasu/wildfire-detection) -\u003e Using Vision Transformers for enhanced wildfire detection in satellite images\n\n- [Burned_Area_Detection](https://github.com/prhuppertz/Burned_Area_Detection) -\u003e Detecting Burned Areas with Sentinel-2 data\n\n- [burned-area-baseline](https://github.com/lccol/burned-area-baseline) -\u003e baseline unet model accompanying the Satellite Burned Area Dataset (Sentinel 1 \u0026 2)\n\n- [burned-area-seg](https://github.com/links-ads/burned-area-seg) -\u003e Burned area segmentation from Sentinel-2 using multi-task learning\n\n- [chabud2023](https://github.com/developmentseed/chabud2023) -\u003e Change detection for Burned area Delineation (ChaBuD) ECML/PKDD 2023 challenge\n\n- [Post Wildfire Burnt-up Detection using Siamese-UNet](https://github.com/kavyagupta/chabud) -\u003e on Chadbud dataset\n\n- [vit-burned-detection](https://github.com/DarthReca/vit-burned-detection) -\u003e Vision transformers in burned area delineation\n\n### Segmentation - Landslides\n\n- [landslide-sar-unet](https://github.com/iprapas/landslide-sar-unet) -\u003e Deep Learning for Rapid Landslide Detection using Synthetic Aperture Radar (SAR) Datacubes\n\n- [landslide-mapping-with-cnn](https://github.com/nprksh/landslide-mapping-with-cnn) -\u003e A new strategy to map landslides with a generalized convolutional neural network\n\n- [Relict_landslides_CNN_kmeans](https://github.com/SPAMLab/data_sharing/tree/main/Relict_landslides_CNN_kmeans) -\u003e Relict landslide detection in rainforest areas using a combination of k-means clustering algorithm and Deep-Learning semantic segmentation models\n\n- [Landslide-mapping-on-SAR-data-by-Attention-U-Net](https://github.com/lorenzonava96/Landslide-mapping-on-SAR-data-by-Attention-U-Net) -\u003e Rapid Mapping of landslide on SAR data by Attention U-net\n\n- [SAR-landslide-detection-pretraining](https://github.com/VMBoehm/SAR-landslide-detection-pretraining) -\u003e SAR-based landslide classification pretraining leads to better segmentation\n\n- [Landslide mapping from Sentinel-2 imagery through change detection](https://github.com/links-ads/igarss-landslide-delineation)\n\n### Segmentation - Glaciers\n\n- [HED-UNet](https://github.com/khdlr/HED-UNet) -\u003e a model for simultaneous semantic segmentation and edge detection, examples provided are glacier fronts and building footprints using the Inria Aerial Image Labeling dataset\n\n- [glacier_mapping](https://github.com/krisrs1128/glacier_mapping) -\u003e Mapping glaciers in the Hindu Kush Himalaya, Landsat 7 images, Shapefile labels of the glaciers, Unet with dropout\n\n- [glacier-detect-ML](https://github.com/mikeskaug/glacier-detect-ML) -\u003e a simple logistic regression model to identify a glacier in Landsat satellite imagery\n\n- [GlacierSemanticSegmentation](https://github.com/n9Mtq4/GlacierSemanticSegmentation)\n\n- [Antarctic-fracture-detection](https://github.com/chingyaolai/Antarctic-fracture-detection) -\u003e uses UNet with the MODIS Mosaic of Antarctica to detect surface fractures\n\n- [sentinel_lakeice](https://github.com/prs-eth/sentinel_lakeice) -\u003e Lake Ice Detection from Sentinel-1 SAR with Deep Learning\n\n### Segmentation - Other environmental\n\n- [Detection of Open Landfills](https://github.com/dymaxionlabs/basurales) -\u003e uses Sentinel-2 to detect large changes in the Normalized Burn Ratio (NBR)\n\n- [sea_ice_remote_sensing](https://github.com/sum1lim/sea_ice_remote_sensing) -\u003e Sea Ice Concentration classification\n\n- [Methane-detection-from-hyperspectral-imagery](https://github.com/satish1901/Methane-detection-from-hyperspectral-imagery) -\u003e Deep Remote Sensing Methods for Methane Detection in Overhead Hyperspectral Imagery\n\n- [methane-emission-project](https://github.com/stlbnmaria/methane-emission-project) -\u003e Classification CNNs was combined in an ensemble approach with traditional methods on tabular data\n\n- [CH4Net](https://github.com/annavaughan/CH4Net) -\u003e A fast, simple model for detection of methane plumes using sentinel-2\n\n- [EddyNet](https://github.com/redouanelg/EddyNet) -\u003e A Deep Neural Network For Pixel-Wise Classification of Oceanic Eddies\n\n- [schisto-vegetation](https://github.com/deleo-lab/schisto-vegetation) -\u003e Deep Learning Segmentation of Satellite Imagery Identifies Aquatic Vegetation Associated with Snail Intermediate Hosts of Schistosomiasis in Senegal, Africa\n\n- [Earthformer](https://github.com/amazon-science/earth-forecasting-transformer) -\u003e Exploring space-time transformers for earth system forecasting\n\n- [weather4cast-2022](https://github.com/iarai/weather4cast-2022) -\u003e Unet-3D baseline model for Weather4cast Rain Movie Prediction competition\n\n- [WeatherFusionNet](https://github.com/Datalab-FIT-CTU/weather4cast-2022) -\u003e Predicting Precipitation from Satellite Data. weather4cast-2022 1st place solution\n\n- [marinedebrisdetector](https://github.com/MarcCoru/marinedebrisdetector) -\u003e Large-scale Detection of Marine Debris in Coastal Areas with Sentinel-2\n\n- [kaggle-identify-contrails-4th](https://github.com/selimsef/kaggle-identify-contrails-4th) -\u003e 4th place Solution, Google Research - Identify Contrails to Reduce Global Warming\n\n- [MineSegSAT](https://github.com/macdonaldezra/MineSegSAT) -\u003e An automated system to evaluate mining disturbed area extents from Sentinel-2 imagery\n\n- [STARCOP: Semantic Segmentation of Methane Plumes with Hyperspectral Machine Learning models](https://github.com/spaceml-org/STARCOP)\n\n- [asos](https://gitlab.jsc.fz-juelich.de/kiste/asos) -\u003e Recognizing protected and anthropogenic patterns in landscapes using interpretable machine learning and satellite imagery\n\n### Segmentation - Roads \u0026 sidewalks\nExtracting roads is challenging due to the occlusions caused by other objects and the complex traffic environment\n\n- [ChesapeakeRSC](https://github.com/isaaccorley/ChesapeakeRSC) -\u003e segmentation to extract roads from the background but are additionally evaluated by how they perform on the \"Tree Canopy Over Road\" class\n\n- [ML_EPFL_Project_2](https://github.com/LucasBrazCappelo/ML_EPFL_Project_2) -\u003e U-Net in Pytorch to perform semantic segmentation of roads on satellite images\n\n- [Semantic Segmentation of roads](https://vihan-tyagi.medium.com/semantic-segmentation-of-satellite-images-based-on-deep-learning-algorithms-ea5ec408ac53) using  U-net Keras, OSM data, project summary article by student, no code\n\n- [Winning Solutions from SpaceNet Road Detection and Routing Challenge](https://github.com/SpaceNetChallenge/RoadDetector)\n\n- [RoadVecNet](https://github.com/gismodelling/RoadVecNet) -\u003e Road-Network-Segmentation-and-Vectorization in keras with dataset\n\n- [Detecting road and road types jupyter notebook](https://github.com/taspinar/sidl/blob/master/notebooks/2_Detecting_road_and_roadtypes_in_sattelite_images.ipynb)\n\n- [awesome-deep-map](https://github.com/antran89/awesome-deep-map) -\u003e A curated list of resources dedicated to deep learning / computer vision algorithms for mapping. The mapping problems include road network inference, building footprint extraction, etc.\n\n- [RoadTracer: Automatic Extraction of Road Networks from Aerial Images](https://github.com/mitroadmaps/roadtracer) -\u003e uses an iterative search process guided by a CNN-based decision function to derive the road network graph directly from the output of the CNN\n\n- [road_detection_mtl](https://github.com/ntelo007/road_detection_mtl) -\u003e Road Detection using a multi-task Learning technique to improve the performance of the road detection task by incorporating prior knowledge constraints, uses the SpaceNet Roads Dataset\n\n- [road_connectivity](https://github.com/anilbatra2185/road_connectivity) -\u003e Improved Road Connectivity by Joint Learning of Orientation and Segmentation (CVPR2019)\n\n- [Road-Network-Extraction using classical Image processing](https://github.com/abhaykes1/Road-Network-Extraction) -\u003e blur \u0026 canny edge detection\n\n- [SPIN_RoadMapper](https://github.com/wgcban/SPIN_RoadMapper) -\u003e Extracting Roads from Aerial Images via Spatial and Interaction Space Graph Reasoning for Autonomous Driving\n\n- [road_extraction_remote_sensing](https://github.com/jiankang1991/road_extraction_remote_sensing) -\u003e pytorch implementation, CVPR2018 DeepGlobe Road Extraction Challenge submission. See also [DeepGlobe-Road-Extraction-Challenge](https://github.com/zlckanata/DeepGlobe-Road-Extraction-Challenge)\n\n- [RoadDetections dataset by Microsoft](https://github.com/microsoft/RoadDetections)\n\n- [CoANet](https://github.com/mj129/CoANet) -\u003e Connectivity Attention Network for Road Extraction From Satellite Imagery. The CoA module incorporates graphical information to ensure the connectivity of roads are better preserved\n\n- [Satellite Imagery Road Segmentation](https://medium.com/@nithishmailme/satellite-imagery-road-segmentation-ad2964dc3812) -\u003e intro articule on Medium using the kaggle [Massachusetts Roads Dataset](https://www.kaggle.com/datasets/balraj98/massachusetts-roads-dataset)\n\n- [Label-Pixels](https://github.com/venkanna37/Label-Pixels) -\u003e for semantic segmentation of roads and other features\n\n- [Satellite-image-road-extraction](https://github.com/amanhari-projects/Satellite-image-road-extraction) -\u003e Road Extraction by Deep Residual U-Net\n\n- [road_building_extraction](https://github.com/jeffwen/road_building_extraction) -\u003e Pytorch implementation of U-Net architecture for road and building extraction\n\n- [RCFSNet](https://github.com/CVer-Yang/RCFSNet) -\u003e Road Extraction From Satellite Imagery by Road Context and Full-Stage Feature\n\n- [SGCN](https://github.com/tist0bsc/SGCN) -\u003e Split Depth-Wise Separable Graph-Convolution Network for Road Extraction in Complex Environments From High-Resolution Remote-Sensing Images\n\n- [ASPN](https://github.com/pshams55/ASPN) -\u003e Road Segmentation for Remote Sensing Images using Adversarial Spatial Pyramid Networks\n\n - [FCNs-for-road-extraction-keras](https://github.com/zetrun-liu/FCNs-for-road-extraction-keras) -\u003e Road extraction of high-resolution remote sensing images based on various semantic segmentation networks\n\n- [cresi](https://github.com/avanetten/cresi) -\u003e Road network extraction from satellite imagery, with speed and travel time estimates\n\n- [D-LinkNet](https://github.com/NekoApocalypse/road-extraction-d-linknet) -\u003e LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction\n\n- [Sat2Graph](https://github.com/songtaohe/Sat2Graph) -\u003e Road Graph Extraction through Graph-Tensor Encoding\n\n- [Image-Segmentation)](https://github.com/mschulz/Image-Segmentation) -\u003e using Massachusetts Road dataset and fast.ai\n\n- [RoadTracer-M](https://github.com/astro-ck/RoadTracer-M) -\u003e Road Network Extraction from Satellite Images Using CNN Based Segmentation and Tracing\n\n- [ScRoadExtractor](https://github.com/weiyao1996/ScRoadExtractor) -\u003e Scribble-based Weakly Supervised Deep Learning for Road Surface Extraction from Remote Sensing Images\n\n- [RoadDA](https://github.com/LANMNG/RoadDA) -\u003e Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images\n\n- [DeepSegmentor](https://github.com/yhlleo/DeepSegmentor) -\u003e A Pytorch implementation of DeepCrack and RoadNet projects\n\n- [Cascaded Residual Attention Enhanced Road Extraction from Remote Sensing Images](https://github.com/liaochengcsu/Cascade_Residual_Attention_Enhanced_for_Refinement_Road_Extraction)\n\n- [NL-LinkNet](https://github.com/SIAnalytics/nia-road-baseline) -\u003e Toward Lighter but More Accurate Road Extraction with Non-Local Operations\n\n- [IRSR-net](https://github.com/yangzhen1252/IRSR-net) -\u003e Lightweight Remote Sensing Road Detection Network\n\n- [hironex](https://github.com/johannesuhl/hironex) -\u003e A python tool for automatic, fully unsupervised extraction of historical road networks from historical maps\n\n- [Road_detection_model](https://github.com/JonasImazon/Road_detection_model) -\u003e Mapping Roads in the Brazilian Amazon with Artificial Intelligence and Sentinel-2\n\n- [DTnet](https://github.com/huzican695/DTnet) -\u003e Road detection via a dual-task network based on cross-layer graph fusion modules\n\n- [Automatic-Road-Extraction-from-Historical-Maps-using-Deep-Learning-Techniques](https://github.com/UrbanOccupationsOETR/Automatic-Road-Extraction-from-Historical-Maps-using-Deep-Learning-Techniques) -\u003e Automatic Road Extraction from Historical Maps using Deep Learning Techniques\n\n- [Istanbul_Dataset](https://github.com/TolgaBkm/Istanbul_Dataset) -\u003e segmentation on the Istanbul, Inria and Massachusetts datasets\n\n- [Road-Segmentation](https://github.com/ralph-elhaddad/Road-Segmentation) -\u003e Road segmentation on Satellite Images using CNN (U-Nets and FCN8) and Logistic Regression\n\n- [D-LinkNet](https://github.com/ShenweiXie/D-LinkNet) -\u003e 1st place solution in DeepGlobe Road Extraction Challenge\n\n- [PaRK-Detect](https://github.com/ShenweiXie/PaRK-Detect) -\u003e PaRK-Detect: Towards Efficient Multi-Task Satellite Imagery Road Extraction via Patch-Wise Keypoints Detection\n\n- [tile2net](https://github.com/VIDA-NYU/tile2net) -\u003e Mapping the walk: A scalable computer vision approach for generating sidewalk network datasets from aerial imagery\n\n- [AerialLaneNet](https://github.com/Jiawei-Yao0812/AerialLaneNet) -\u003e Building Lane-Level Maps from Aerial Images, introduces the AErial Lane (AEL) Dataset: a first large-scale aerial image dataset built for lane detection\n\n- [sam_road](https://github.com/htcr/sam_road) -\u003e Segment Anything Model (SAM) for large-scale, vectorized road network extraction from aerial imagery.\n\n- [LRDNet](https://github.com/dyl96/LRDNet) -\u003e A Lightweight Road Detection Algorithm Based on Multiscale Convolutional Attention Network and Coupled Decoder Head\n\n- [Fine–Grained Extraction of Road Networks via Joint Learning of Connectivity and Segmentation](https://github.com/YXu556/RoadExtraction) -\u003e uses SpaceNet 3 dataset\n\n- [Satellite-Image-Road-Segmentation](https://github.com/aavek/Satellite-Image-Road-Segmentation) -\u003e Graph Reasoned Multi-Scale Road Segmentation in Remote Sensing Imagery [paper](https://ieeexplore.ieee.org/document/10281660)\n\n### Segmentation - Buildings \u0026 rooftops\n\n- [Road and Building Semantic Segmentation in Satellite Imagery](https://github.com/Paulymorphous/Road-Segmentation) uses U-Net on the Massachusetts Roads Dataset \u0026 keras\n\n- [find unauthorized constructions using aerial photography](https://medium.com/towards-artificial-intelligence/find-unauthorized-constructions-using-aerial-photography-and-deep-learning-with-code-part-2-b56ca80c8c99) -\u003e [Dataset creation](https://pub.towardsai.net/find-unauthorized-constructions-using-aerial-photography-and-deep-learning-with-code-part-1-6d3ca7ff6fa0)\n\n- [SRBuildSeg](https://github.com/xian1234/SRBuildSeg) -\u003e Making low-resolution satellite images reborn: a deep learning approach for super-resolution building extraction\n\n- [Building footprint detection with fastai on the challenging SpaceNet7 dataset](https://deeplearning.berlin/satellite%20imagery/computer%20vision/fastai/2021/02/17/Building-Detection-SpaceNet7.html) uses U-Net \u0026 fastai\n\n- [Pix2Pix-for-Semantic-Segmentation-of-Satellite-Images](https://github.com/A2Amir/Pix2Pix-for-Semantic-Segmentation-of-Satellite-Images) -\u003e using Pix2Pix GAN network to segment the building footprint from Satellite Images, uses tensorflow\n\n- [SpaceNetUnet](https://github.com/boggis30/SpaceNetUnet) -\u003e Baseline model is U-net like, applied to SpaceNet Vegas data, using Keras\n\n- [automated-building-detection](https://github.com/rodekruis/automated-building-detection) -\u003e Input: very-high-resolution (\u003c= 0.5 m/pixel) RGB satellite images. Output: buildings in vector format (geojson), to be used in digital map products. Built on top of robosat and robosat.pink.\n\n- [project_sunroof_india](https://github.com/AKASH2907/project_sunroof_india) -\u003e Analyzed Google Satellite images to generate a report on individual house rooftop's solar power potential, uses a range of classical computer vision techniques (e.g Canny Edge Detection) to segment the roofs\n\n- [JointNet-A-Common-Neural-Network-for-Road-and-Building-Extraction](https://github.com/ThomasWangWeiHong/JointNet-A-Common-Neural-Network-for-Road-and-Building-Extraction)\n\n- [Mapping Africa’s Buildings with Satellite Imagery: Google AI blog post](https://ai.googleblog.com/2021/07/mapping-africas-buildings-with.html). See the [open-buildings](https://sites.research.google/open-buildings/) dataset\n\n- [nz_convnet](https://github.com/weiji14/nz_convnet) -\u003e A U-net based ConvNet for New Zealand imagery to classify building outlines\n\n- [polycnn](https://github.com/Lydorn/polycnn) -\u003e End-to-End Learning of Polygons for Remote Sensing Image Classification\n\n- [spacenet_building_detection](https://github.com/motokimura/spacenet_building_detection) solution by [motokimura](https://github.com/motokimura) using Unet\n\n- [Vec2Instance](https://github.com/lakmalnd/Vec2Instance) -\u003e applied to the SpaceNet challenge AOI 2 (Vegas) building footprint dataset, tensorflow v1.12\n\n- [EarthquakeDamageDetection](https://github.com/JaneKravchenko/EarthquakeDamageDetection) -\u003e Buildings segmentation from satellite imagery and damage classification for each build, using Keras\n\n- [Semantic-segmentation repo by fuweifu-vtoo](https://github.com/fuweifu-vtoo/Semantic-segmentation) -\u003e uses pytorch and the [Massachusetts Buildings \u0026 Roads Datasets](https://www.cs.toronto.edu/~vmnih/data/)\n\n- [Extracting buildings and roads from AWS Open Data using Amazon SageMaker](https://aws.amazon.com/blogs/machine-learning/extracting-buildings-and-roads-from-aws-open-data-using-amazon-sagemaker/) -\u003e With [repo](https://github.com/aws-samples/aws-open-data-satellite-lidar-tutorial)\n\n- [TF-SegNet](https://github.com/mathildor/TF-SegNet) -\u003e AirNet is a segmentation network based on SegNet, but with some modifications\n\n- [rgb-footprint-extract](https://github.com/aatifjiwani/rgb-footprint-extract) -\u003e a Semantic Segmentation Network for Urban-Scale Building Footprint Extraction Using RGB Satellite Imagery, DeepLavV3+ module with a Dilated ResNet C42 backbone\n\n- [SpaceNetExploration](https://github.com/yangsiyu007/SpaceNetExploration) -\u003e A sample project demonstrating how to extract building footprints from satellite images using a semantic segmentation model. Data from the SpaceNet Challenge\n\n- [Rooftop-Instance-Segmentation](https://github.com/MasterSkepticista/Rooftop-Instance-Segmentation) -\u003e VGG-16, Instance Segmentation, uses the Airs dataset\n\n- [solar-farms-mapping](https://github.com/microsoft/solar-farms-mapping) -\u003e An Artificial Intelligence Dataset for Solar Energy Locations in India\n\n- [poultry-cafos](https://github.com/microsoft/poultry-cafos) -\u003e This repo contains code for detecting poultry barns from high-resolution aerial imagery and an accompanying dataset of predicted barns over the United States\n\n- [ssai-cnn](https://github.com/mitmul/ssai-cnn) -\u003e This is an implementation of Volodymyr Mnih's dissertation methods on his Massachusetts road \u0026 building dataset\n\n- [Remote-sensing-building-extraction-to-3D-model-using-Paddle-and-Grasshopper](https://github.com/Youssef-Harby/Remote-sensing-building-extraction-to-3D-model-using-Paddle-and-Grasshopper)\n\n- [segmentation-enhanced-resunet](https://github.com/tranleanh/segmentation-enhanced-resunet) -\u003e Urban building extraction in Daejeon region using Modified Residual U-Net (Modified ResUnet) and applying post-processing\n\n- [Mask RCNN for Spacenet Off Nadir Building Detection](https://github.com/ashnair1/Mask-RCNN-for-Off-Nadir-Building-Detection)\n\n- [GRSL_BFE_MA](https://github.com/jiankang1991/GRSL_BFE_MA) -\u003e Deep Learning-based Building Footprint Extraction with Missing Annotations using a novel loss function\n\n- [FER-CNN](https://github.com/runnergirl13/FER-CNN) -\u003e Detection, Classification and Boundary Regularization of Buildings in Satellite Imagery Using Faster Edge Region Convolutional Neural Networks\n\n- [UNET-Image-Segmentation-Satellite-Picture](https://github.com/rwie1and/UNET-Image-Segmentation-Satellite-Pictures) -\u003e Unet to predict roof tops on Crowed AI Mapping dataset, uses keras\n\n- [Vector-Map-Generation-from-Aerial-Imagery-using-Deep-Learning-GeoSpatial-UNET](https://github.com/ManishSahu53/Vector-Map-Generation-from-Aerial-Imagery-using-Deep-Learning-GeoSpatial-UNET) -\u003e applied to geo-referenced images which are very large size \u003e 10k x 10k pixels\n\n- [building-footprint-segmentation](https://github.com/fuzailpalnak/building-footprint-segmentation) -\u003e pip installable library to train building footprint segmentation on satellite and aerial imagery, applied to Massachusetts Buildings Dataset and Inria Aerial Image Labeling Dataset\n\n- [SemSegBuildings](https://github.com/SharpestProjects/SemSegBuildings) -\u003e Project using fast.ai framework for semantic segmentation on Inria building segmentation dataset\n\n- [FCNN-example](https://github.com/emredog/FCNN-example) -\u003e overfit to a given single image to detect houses\n\n- [SAT2LOD2](https://github.com/gdaosu/lod2buildingmodel) -\u003e an open-source, python-based GUI-enabled software that takes the satellite images as inputs and returns LoD2 building models as outputs\n\n- [SatFootprint](https://github.com/PriyanK7n/SatFootprint) -\u003e building segmentation on the Spacenet 7 dataset\n\n- [Building-Detection](https://github.com/EL-BID/Building-Detection) -\u003e Raster Vision experiment to train a model to detect buildings from satellite imagery in three cities in Latin America\n\n- [Multi-building-tracker](https://github.com/sebasmos/Multi-building-tracker) -\u003e Multi-target building tracker for satellite images using deep learning\n\n- [Boundary Enhancement Semantic Segmentation for Building Extraction](https://github.com/hin1115/BEmodule-Satellite-Building-Segmentation)\n\n- [keras code for binary semantic segmentation](https://github.com/loveswine/UNet_keras_for_RSimage)\n\n- [Spacenet-Building-Detection](https://github.com/IdanC1s2/Spacenet-Building-Detection)\n\n- [LGPNet-BCD](https://github.com/TongfeiLiu/LGPNet-BCD) -\u003e Building Change Detection for VHR Remote Sensing Images via Local-Global Pyramid Network and Cross-Task Transfer Learning Strategy\n\n- [MTL_homoscedastic_SRB](https://github.com/burakekim/MTL_homoscedastic_SRB) -\u003e A Multi-Task Deep Learning Framework for Building Footprint Segmentation\n\n- [UNet_CNN](https://github.com/Inamdarpushkar/UNet_CNN) -\u003e UNet model to segment building coverage in Boston using Remote sensing data, uses keras\n\n- [FDANet](https://github.com/daifeng2016/FDANet) -\u003e Full-Level Domain Adaptation for Building Extraction in Very-High-Resolution Optical Remote-Sensing Images\n\n- [CBRNet](https://github.com/HaonanGuo/CBRNet) -\u003e A Coarse-to-fine Boundary Refinement Network for Building Extraction from Remote Sensing Imagery\n\n- [ASLNet](https://github.com/ggsDing/ASLNet) -\u003e Adversarial Shape Learning for Building Extraction in VHR Remote Sensing Images\n\n- [BRRNet](https://github.com/wangyi111/Building-Extraction) -\u003e A Fully Convolutional Neural Network for Automatic Building Extraction From High-Resolution Remote Sensing Images\n\n- [Multi-Scale-Filtering-Building-Index](https://github.com/ThomasWangWeiHong/Multi-Scale-Filtering-Building-Index) -\u003e A Multi - Scale Filtering Building Index for Building Extraction in Very High - Resolution Satellite Imagery\n\n- [Models for Remote Sensing](https://github.com/bohaohuang/mrs) -\u003e long list of unets etc applied to building detection\n\n- [boundary_loss_for_remote_sensing](https://github.com/yiskw713/boundary_loss_for_remote_sensing) -\u003e Boundary Loss for Remote Sensing Imagery Semantic Segmentation\n\n- [Open Cities AI Challenge](https://www.drivendata.org/competitions/60/building-segmentation-disaster-resilience/) -\u003e Segmenting Buildings for Disaster Resilience. Winning solutions [on Github](https://github.com/drivendataorg/open-cities-ai-challenge/)\n\n- [MAPNet](https://github.com/lehaifeng/MAPNet) -\u003e Multi Attending Path Neural Network for Building Footprint Extraction from Remote Sensed Imagery\n\n- [dual-hrnet](https://github.com/SIAnalytics/dual-hrnet) -\u003e localizing buildings and classifying their damage level\n\n- [ESFNet](https://github.com/mrluin/ESFNet-Pytorch) -\u003e Efficient Network for Building Extraction from High-Resolution Aerial Images\n\n- [rooftop-detection-python](https://github.com/sayonpalit/rooftop-detection-python) -\u003e Detect Rooftops from low resolution satellite images and calculate area for cultivation and solar panel installment using classical computer vision techniques\n\n- [keras_segmentation_models](https://github.com/sajmonogy/keras_segmentation_models) -\u003e Using Open Vector-Based Spatial Data to Create Semantic Datasets for Building Segmentation for Raster Data\n\n- [CVCMFFNet](https://github.com/Jiankun-chen/CVCMFFNet-master) -\u003e Complex-Valued Convolutional and Multifeature Fusion Network for Building Semantic Segmentation of InSAR Images\n\n- [STEB-UNet](https://github.com/BrightGuo048/STEB-UNet) -\u003e A Swin Transformer-Based Encoding Booster Integrated in U-Shaped Network for Building Extraction\n\n- [dfc2020_baseline](https://github.com/lukasliebel/dfc2020_baseline) -\u003e Baseline solution for the IEEE GRSS Data Fusion Contest 2020. Predict land cover labels from Sentinel-1 and Sentinel-2 imagery\n\n- [Fusing multiple segmentation models based on different datasets into a single edge-deployable model](https://github.com/markusmeingast/Satellite-Classifier) -\u003e roof, car \u0026 road segmentation\n\n- [ground-truth-gan-segmentation](https://github.com/zakariamejdoul/ground-truth-gan-segmentation) -\u003e use Pix2Pix to segment the footprint of a building. The dataset used is AIRS\n\n- [UNICEF-Giga_Sudan](https://github.com/Kamal-Eldin/UNICEF-Giga_Sudan) -\u003e Detecting school lots from satellite imagery in Southern Sudan using a UNET segmentation model\n\n- [building_footprint_extraction](https://github.com/shubhamgoel27/building_footprint_extraction) -\u003e The project retrieves satellite imagery from Google and performs building footprint extraction using a U-Net.\n\n- [projectRegularization](https://github.com/zorzi-s/projectRegularization) -\u003e Regularization of building boundaries in satellite images using adversarial and regularized losses\n\n- [PolyWorldPretrainedNetwork](https://github.com/zorzi-s/PolyWorldPretrainedNetwork) -\u003e Polygonal Building Extraction with Graph Neural Networks in Satellite Images\n\n- [dl_image_segmentation](https://github.com/harry-gibson/dl_image_segmentation) -\u003e Uncertainty-Aware Interpretable Deep Learning for Slum Mapping and Monitoring. Uses SHAP\n\n- [UBC-dataset](https://github.com/AICyberTeam/UBC-dataset) -\u003e a dataset for building detection and classification from very high-resolution satellite imagery with the focus on object-level interpretation of individual buildings\n\n- [UNetFormer](https://github.com/WangLibo1995/GeoSeg) -\u003e A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery\n\n- [BES-Net](https://github.com/FlyC235/BESNet) -\u003e Boundary Enhancing Semantic Context Network for High-Resolution Image Semantic Segmentation. Applied to Vaihingen and Potsdam datasets\n\n- [CVNet](https://github.com/xzq-njust/CVNet) -\u003e Contour Vibration Network for Building Extraction\n\n- [CFENet](https://github.com/djzgroup/CFENet) -\u003e A Context Feature Enhancement Network for Building Extraction from High-Resolution Remote Sensing Imagery\n\n- [HiSup](https://github.com/SarahwXU/HiSup) -\u003e Accurate Polygonal Mapping of Buildings in Satellite Imagery\n\n- [BuildingExtraction](https://github.com/KyanChen/BuildingExtraction) -\u003e Building Extraction from Remote Sensing Images with Sparse Token Transformers\n\n- [CrossGeoNet](https://github.com/lqycrystal/coseg_building) -\u003e A Framework for Building Footprint Generation of Label-Scarce Geographical Regions\n\n- [AFM_building](https://github.com/lqycrystal/AFM_building) -\u003e Building Footprint Generation Through Convolutional Neural Networks With Attraction Field Representation\n\n- [RAMP (Replicable AI for MicroPlanning)](https://github.com/devglobalpartners/ramp-code) -\u003e building detection in low and middle income countries\n\n- [Building-instance-segmentation](https://github.com/yuanqinglie/Building-instance-segmentation-combining-anchor-free-detectors-and-multi-modal-feature-fusion) -\u003e Multi-Modal Feature Fusion Network with Adaptive Center Point Detector for Building Instance Extraction\n\n- [CGSANet](https://github.com/MrChen18/CGSANet) -\u003e A Contour-Guided and Local Structure-Aware Encoder–Decoder Network for Accurate Building Extraction From Very High-Resolution Remote Sensing Imagery\n\n- [building-footprints-update](https://github.com/wangzehui20/building-footprints-update) -\u003e Learning Color Distributions from Bitemporal Remote Sensing Images to Update Existing Building Footprints\n\n- [RAMP](https://rampml.global/) -\u003e model and buildings dataset to support a wide variety of humanitarian use cases\n\n- [Thesis_Semantic_Image_Segmentation_on_Satellite_Imagery_using_UNets](https://github.com/rinkwitz/Thesis_Semantic_Image_Segmentation_on_Satellite_Imagery_using_UNets) -\u003e This master thesis aims to perform semantic segmentation of buildings on satellite images from the SpaceNet challenge 1 dataset using the U-Net architecture\n\n- [HD-Net](https://github.com/danfenghong/ISPRS_HD-Net) -\u003e High-resolution decoupled network for building footprint extraction via deeply supervised body and boundary decomposition\n\n- [RoofSense](https://github.com/DimitrisMantas/RoofSense/tree/master) -\u003e A novel deep learning solution for the automatic roofing material classification of the Dutch building stock using aerial imagery and laser scanning data fusion\n\n- [IBS-AQSNet](https://github.com/zhilyzhang/IBS-AQSNet) -\u003e Enhanced Automated Quality Assessment Network for Interactive Building Segmentation in High-Resolution Remote Sensing Imagery\n\n- [DeepMAO](https://github.com/Sumanth181099/DeepMAO) -\u003e Deep Multi-scale Aware Overcomplete Network for Building Segmentation in Satellite Imagery\n\n- [CMGFNet-Building_Extraction](https://github.com/hamidreza2015/CMGFNet-Building_Extraction) -\u003e Deep Learning Code for Building Extraction from very high resolution (VHR) remote sensing images\n\n### Segmentation - Solar panels\n\n- [Deep-Learning-for-Solar-Panel-Recognition](https://github.com/saizk/Deep-Learning-for-Solar-Panel-Recognition) -\u003e using both object detection with Yolov5 and Unet segmentation\n\n- [DeepSolar](https://github.com/wangzhecheng/DeepSolar) -\u003e A Machine Learning Framework to Efficiently Construct a Solar Deployment Database in the United States. [Dataset on kaggle](https://www.kaggle.com/datasets/tunguz/deep-solar-dataset), actually used a CNN for classification and segmentation is obtained by applying a threshold to the activation map. Original code is tf1 but [tf2/kers](https://github.com/aidan-fitz/deepsolar-v2) and a [pytorch implementation](https://github.com/wangzhecheng/deepsolar_pytorch) are available. Also checkout [Visualizations and in-depth analysis .. of the factors that can explain the adoption of solar energy in ..  Virginia]\n  \n- [hyperion_solar_net](https://github.com/fvergaracontesse/hyperion_solar_net) -\u003e trained classificaton \u0026 segmentation models on RGB imagery from Google Maps\n\n- [3D-PV-Locator](https://github.com/kdmayer/3D-PV-Locator) -\u003e Large-scale detection of rooftop-mounted photovoltaic systems in 3D\n\n- [PV_Pipeline](https://github.com/kdmayer/PV_Pipeline) -\u003e DeepSolar for Germany\n\n- [solar-panels-detection](https://github.com/dbaofd/solar-panels-detection) -\u003e using SegNet, Fast SCNN \u0026 ResNet\n\n- [predict_pv_yield](https://github.com/openclimatefix/predict_pv_yield) -\u003e Using optical flow \u0026 machine learning to predict PV yield\n\n- [Large-scale-solar-plant-monitoring](https://github.com/osmarluiz/Large-scale-solar-plant-monitoring) -\u003e Remote Sensing for Monitoring of Photovoltaic Power Plants in Brazil Using Deep Semantic Segmentation\n\n- [Panel-Segmentation](https://github.com/NREL/Panel-Segmentation) -\u003e Determine the presence of a solar array in the satellite image (boolean True/False), using a VGG16 classification model\n\n- [Roofpedia](https://github.com/ualsg/Roofpedia) -\u003e an open registry of green roofs and solar roofs across the globe identified by Roofpedia through deep learning\n\n- [Predicting the Solar Potential of Rooftops using Image Segmentation and Structured Data](https://medium.com/nam-r/predicting-the-solar-potential-of-rooftops-using-image-segmentation-and-structured-data-61198c39d57c) Medium article, using 20cm imagery \u0026 Unet\n\n- [solar-pv-global-inventory](https://github.com/Lkruitwagen/solar-pv-global-inventory)\n\n- [remote-sensing-solar-pv](https://github.com/Lkruitwagen/remote-sensing-solar-pv) -\u003e A repository for sharing progress on the automated detection of solar PV arrays in sentinel-2 remote sensing imagery\n\n- [solar-panel-segmentation)](https://github.com/gabrieltseng/solar-panel-segmentation) -\u003e Finding solar panels using USGS satellite imagery\n\n- [solar_seg](https://github.com/tcapelle/solar_seg) -\u003e Solar segmentation of PV modules (sub elements of panels) using drone images and fast.ai\n\n- [solar_plant_detection](https://github.com/Amirmoradi94/solar_plant_detection) -\u003e boundary extraction of Photovoltaic (PV) plants using Mask RCNN and Amir dataset\n\n- [SolarDetection](https://github.com/A-Stangeland/SolarDetection) -\u003e unet on satellite image from the USA and France\n\n- [adopptrs](https://github.com/francois-rozet/adopptrs) -\u003e Automatic Detection Of Photovoltaic Panels Through Remote Sensing using unet \u0026 pytorch\n\n- [solar-panel-locator](https://github.com/TorrBorr/solar-panel-locator) -\u003e the number of solar panel pixels was only ~0.2% of the total pixels in the dataset, so solar panel data was upsampled to account for the class imbalance\n\n- [projects-solar-panel-detection](https://github.com/top-on/projects-solar-panel-detection) -\u003e List of project to detect solar panels from aerial/satellite images\n\n- [Satellite_ComputerVision](https://github.com/mjevans26/Satellite_ComputerVision) -\u003e UNET to detect solar arrays from Sentinel-2 data, using Google Earth Engine and Tensorflow. Also covers parking lot detection\n\n- [photovoltaic-detection](https://github.com/riccardocadei/photovoltaic-detection) -\u003e Detecting available rooftop area from satellite images to install photovoltaic panels\n\n- [Solar_UNet](https://github.com/mjevans26/Solar_UNet) -\u003e U-Net models delineating solar arrays in Sentinel-2 imagery\n\n- [SolarDetection-solafune](https://github.com/bit-guber/SolarDetection-solafune) -\u003e Solar Panel Detection Using Sentinel-2 for the Solafune Competition\n\n- [A Comparative Evaluation of Deep Learning Techniques for Photovoltaic Panel Detection from Aerial Images](https://github.com/links-ads/access-solar-panels)\n\n### Segmentation - Ships \u0026 vessels\n\n- [Universal-segmentation-baseline-Kaggle-Airbus-Ship-Detection](https://github.com/OniroAI/Universal-segmentation-baseline-Kaggle-Airbus-Ship-Detection) -\u003e Kaggle Airbus Ship Detection Challenge - bronze medal solution\n\n- [Airbus-Ship-Segmentation](https://github.com/TheXirex/Airbus-Ship-Segmentation) -\u003e unet\n\n- [contrastive_SSL_ship_detection](https://github.com/alina2204/contrastive_SSL_ship_detection) -\u003e Contrastive self supervised learning for ship detection in Sentinel 2 images\n\n- [airbus-ship-detection](https://github.com/odessitua/airbus-ship-detection) -\u003e using DeepLabV3+\n\n- [Unet with web-application applied to Airbus ships](https://github.com/glibesyck/ImageSegmentation)\n\n### Segmentation - Other manmade\n\n- [Aarsh2001/ML_Challenge_NRSC](https://github.com/Aarsh2001/ML_Challenge_NRSC) -\u003e Electrical Substation detection\n\n- [electrical_substation_detection](https://github.com/thisishardik/electrical_substation_detection)\n\n- [MCAN-OilSpillDetection](https://github.com/liyongqingupc/MCAN-OilSpillDetection) -\u003e Oil Spill Detection with A Multiscale Conditional Adversarial Network under Small Data Training\n\n- [mining-detector](https://github.com/earthrise-media/mining-detector) -\u003e detection of artisanal gold mines in Sentinel-2 satellite imagery for [Amazon Mining Watch](https://amazonminingwatch.org/). Also covers clandestine airstrips\n\n- [EG-UNet](https://github.com/tist0bsc/EG-UNet) Deep Feature Enhancement Method for Land Cover With Irregular and Sparse Spatial Distribution Features: A Case Study on Open-Pit Mining\n\n- [plastics](https://github.com/earthrise-media/plastics) -\u003e Detecting and Monitoring Plastic Waste Aggregations in Sentinel-2 Imagery\n\n- [MADOS](https://github.com/gkakogeorgiou/mados) -\u003e Detecting Marine Pollutants and Sea Surface Features with Deep Learning in Sentinel-2 Imagery on the MADOS dataset\n\n- [SADMA](https://github.com/sheikhazhanmohammed/SADMA) -\u003e Residual Attention UNet on MARIDA: Marine Debris Archive is a marine debris-oriented dataset on Sentinel-2 satellite images\n\n- [MAP-Mapper](https://github.com/CoDIS-Lab/MAP-Mapper) -\u003e Marine Plastic Mapper is a tool for assessing marine macro-plastic density to identify plastic hotspots, underpinned by the MARIDA dataset.\n\n- [substation-seg](https://github.com/Lindsay-Lab/substation-seg) -\u003e segmenting substations in Sentinel 2 satellite imagery\n\n### Panoptic segmentation\n\n- [Things and stuff or how remote sensing could benefit from panoptic segmentation](https://softwaremill.com/things-and-stuff-or-how-remote-sensing-could-benefit-from-panoptic-segmentation/)\n\n- [utae-paps](https://github.com/VSainteuf/utae-paps) -\u003e PyTorch implementation of U-TAE and PaPs for satellite image time series panoptic segmentation\n\n- [pastis-benchmark](https://github.com/VSainteuf/pastis-benchmark)\n\n- [Panoptic-Generator](https://github.com/abilius-app/Panoptic-Generator) -\u003e This module converts GIS data into panoptic segmentation tiles\n\n- [BSB-Aerial-Dataset](https://github.com/osmarluiz/BSB-Aerial-Dataset) -\u003e an example on how to use Detectron2's Panoptic-FPN in the BSB Aerial Dataset\n\n### Segmentation - Miscellaneous\n\n- [seg-eval](https://github.com/itracasa/seg-eval) -\u003e SegEval is a Python library that provides tools for evaluating semantic segmentation models. Generate evaluation regions and to analyze segmentation results within them.\n\n- [awesome-satellite-images-segmentation](https://github.com/mrgloom/awesome-semantic-segmentation#satellite-images-segmentation)\n\n- [Satellite Image Segmentation: a Workflow with U-Net](https://medium.com/vooban-ai/satellite-image-segmentation-a-workflow-with-u-net-7ff992b2a56e) is a decent intro article\n\n- [mmsegmentation](https://github.com/open-mmlab/mmsegmentation) -\u003e Semantic Segmentation Toolbox with support for many remote sensing datasets including LoveDA, Potsdam, Vaihingen \u0026 iSAID\n\n- [segmentation_gym](https://github.com/Doodleverse/segmentation_gym) -\u003e A neural gym for training deep learning models to carry out geoscientific image segmentation\n\n- [Using a U-Net for image segmentation, blending predicted patches smoothly is a must to please the human eye](https://github.com/Vooban/Smoothly-Blend-Image-Patches) -\u003e python code to blend predicted patches smoothly. See [Satellite-Image-Segmentation-with-Smooth-Blending](https://github.com/MaitrySinha21/Satellite-Image-Segmentation-with-Smooth-Blending)\n\n- [DCA](https://github.com/Luffy03/DCA) -\u003e Deep Covariance Alignment for Domain Adaptive Remote Sensing Image Segmentation\n\n- [SCAttNet](https://github.com/lehaifeng/SCAttNet) -\u003e Semantic Segmentation Network with Spatial and Channel Attention Mechanism\n\n- [unetseg](https://github.com/dymaxionlabs/unetseg) -\u003e A set of classes and CLI tools for training a semantic segmentation model based on the U-Net architecture, using Tensorflow and Keras. This implementation is tuned specifically for satellite imagery and other geospatial raster data\n\n- [Semantic Segmentation of Satellite Imagery using U-Net \u0026 fast.ai](https://medium.com/dataseries/image-semantic-segmentation-of-satellite-imagery-using-u-net-e99ae13cf464) -\u003e with [repo](https://github.com/raoofnaushad/Image-Semantic-Segmentation-of-Satellite-Imagery-using-U-Net.)\n\n- [clusternet_segmentation](https://github.com/zhygallo/clusternet_segmentation) -\u003e Unsupervised Segmentation by applying K-Means clustering to the features generated by Neural Network\n\n- [Efficient-Transformer](https://github.com/zyxu1996/Efficient-Transformer) -\u003e Efficient Transformer for Remote Sensing Image Segmentation\n\n- [weakly_supervised](https://github.com/LobellLab/weakly_supervised) -\u003e Weakly Supervised Deep Learning for Segmentation of Remote Sensing Imagery\n\n- [HRCNet-High-Resolution-Context-Extraction-Network](https://github.com/zyxu1996/HRCNet-High-Resolution-Context-Extraction-Network) -\u003e High-Resolution Context Extraction Network for Semantic Segmentation of Remote Sensing Images\n\n- [Semantic segmentation of SAR images using a self supervised technique](https://github.com/cattale93/pytorch_self_supervised_learning)\n\n- [satellite-segmentation-pytorch](https://github.com/obravo7/satellite-segmentation-pytorch) -\u003e explores a wide variety of image augmentations to increase training dataset size\n\n- [Spectralformer](https://github.com/danfenghong/IEEE_TGRS_SpectralFormer) -\u003e Rethinking hyperspectral image classification with transformers\n\n- [Unsupervised Segmentation of Hyperspectral Remote Sensing Images with Superpixels](https://github.com/mpBarbato/Unsupervised-Segmentation-of-Hyperspectral-Remote-Sensing-Images-with-Superpixels)\n\n- [Semantic-Segmentation-with-Sparse-Labels](https://github.com/Hua-YS/Semantic-Segmentation-with-Sparse-Labels)\n\n- [SNDF](https://github.com/mi18/SNDF) -\u003e Superpixel-enhanced deep neural forest for remote sensing image semantic segmentation\n\n- [Satellite-Image-Classification](https://github.com/yxian29/Satellite-Image-Classification) -\u003e using random forest or support vector machines (SVM) and sklearn\n\n- [dynamic-rs-segmentation](https://github.com/keillernogueira/dynamic-rs-segmentation) -\u003e Dynamic Multi-Context Segmentation of Remote Sensing Images based on Convolutional Networks\n\n- [segmentation_models.pytorch](https://github.com/qubvel/segmentation_models.pytorch) -\u003e Segmentation models with pretrained backbones, has been used in multiple winning solutions to remote sensing competitions\n\n- [SSRN](https://github.com/zilongzhong/SSRN) -\u003e Spectral-Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework\n\n- [SO-DNN](https://github.com/PanXinZebra/SO-DNN) -\u003e Simplified object-based deep neural network for very high resolution remote sensing image classification\n\n- [SANet](https://github.com/mrluin/SANet-PyTorch) -\u003e Scale-Aware Network for Semantic Segmentation of High-Resolution Aerial Images\n\n- [aerial-segmentation](https://github.com/alpemek/aerial-segmentation) -\u003e Learning Aerial Image Segmentation from Online Maps\n\n- [IterativeSegmentation](https://github.com/gaudetcj/IterativeSegmentation) -\u003e Recurrent Neural Networks to Correct Satellite Image Classification Maps\n\n- [Detectron2 FPN + PointRend Model for amazing Satellite Image Segmentation](https://affine.medium.com/detectron2-fpn-pointrend-model-for-amazing-satellite-image-segmentation-183456063e15) -\u003e 15% increase in accuracy when compared to the U-Net model\n\n- [HybridSN](https://github.com/purbayankar/HybridSN-pytorch) -\u003e Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image Classification\n\n- [TNNLS_2022_X-GPN](https://github.com/B-Xi/TNNLS_2022_X-GPN) -\u003e Semisupervised Cross-scale Graph Prototypical Network for Hyperspectral Image Classification\n\n- [singleSceneSemSegTgrs2022](https://github.com/sudipansaha/singleSceneSemSegTgrs2022) -\u003e Unsupervised Single-Scene Semantic Segmentation for Earth Observation\n\n- [A-Fast-and-Compact-3-D-CNN-for-HSIC](https://github.com/mahmad00/A-Fast-and-Compact-3-D-CNN-for-HSIC) -\u003e A Fast and Compact 3-D CNN for Hyperspectral Image Classification\n\n- [HSNRS](https://github.com/Walkerlikesfish/HSNRS) -\u003e  Hourglass-ShapeNetwork Based Semantic Segmentation for High Resolution Aerial Imagery\n\n- [GiGCN](https://github.com/ShuGuoJ/GiGCN) -\u003e Graph-in-Graph Convolutional Network for Hyperspectral Image Classification\n\n- [SSAN](https://github.com/EtPan/SSAN) -\u003e Spectral-Spatial Attention Networks for Hyperspectral Image Classification\n\n- [drone-images-semantic-segmentation](https://github.com/ayushdabra/drone-images-semantic-segmentation) -\u003e Multiclass Semantic Segmentation of Aerial Drone Images Using Deep Learning\n\n- [Satellite-Image-Segmentation-with-Smooth-Blending](https://github.com/MaitrySinha21/Satellite-Image-Segmentation-with-Smooth-Blending) -\u003e uses [Smoothly-Blend-Image-Patches](https://github.com/Vooban/Smoothly-Blend-Image-Patches)\n\n- [BayesianUNet](https://github.com/tha-santacruz/BayesianUNet) -\u003e Pytorch Bayesian UNet model for segmentation and uncertainty prediction, applied to the Potsdam Dataset\n\n- [RAANet](https://github.com/Lrr0213/RAANet) -\u003e A Residual ASPP with Attention Framework for Semantic Segmentation of High-Resolution Remote Sensing Images\n\n- [wheelRuts_semanticSegmentation](https://github.com/SmartForest-no/wheelRuts_semanticSegmentation) -\u003e Mapping wheel-ruts from timber harvesting operations using deep learning techniques in drone imagery\n\n- [LWN-for-UAVRSI](https://github.com/syliudf/LWN-for-UAVRSI) -\u003e Light-Weight Semantic Segmentation Network for UAV Remote Sensing Images, applied to Vaihingen, UAVid and UDD6 datasets\n\n- [hypernet](https://github.com/ESA-PhiLab/hypernet) -\u003e library which implements hyperspectral image (HSI) segmentation\n\n- [ST-UNet](https://github.com/XinnHe/ST-UNet) -\u003e Swin Transformer Embedding UNet for Remote Sensing Image Semantic Segmentation\n\n- [EDFT](https://github.com/h1063135843/EDFT) -\u003e Efficient Depth Fusion Transformer for Aerial Image Semantic Segmentation\n\n- [WiCoNet](https://github.com/ggsDing/WiCoNet) -\u003e Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images\n\n- [CRGNet](https://github.com/YonghaoXu/CRGNet) -\u003e Consistency-Regularized Region-Growing Network for Semantic Segmentation of Urban Scenes with Point-Level Annotations\n\n- [SA-UNet](https://github.com/Yancccccc/SA-UNet) -\u003e Improved U-Net Remote Sensing Classification Algorithm Fusing Attention and Multiscale Features\n\n- [MANet](https://github.com/lironui/Multi-Attention-Network) -\u003e Multi-Attention-Network for Semantic Segmentation of Fine Resolution Remote Sensing Images\n\n- [BANet](https://github.com/lironui/BANet) -\u003e Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images\n\n- [MACU-Net](https://github.com/lironui/MACU-Net) -\u003e MACU-Net for Semantic Segmentation of Fine-Resolution Remotely Sensed Images\n\n- [DNAS](https://github.com/faye0078/DNAS) -\u003e Decoupling Neural Architecture Search for High-Resolution Remote Sensing Image Semantic Segmentation\n\n- [A2-FPN](https://github.com/lironui/A2-FPN) -\u003e A2-FPN for Semantic Segmentation of Fine-Resolution Remotely Sensed Images\n\n- [MAResU-Net](https://github.com/lironui/MAResU-Net) -\u003e Multi-stage Attention ResU-Net for Semantic Segmentation of Fine-Resolution Remote Sensing Images\n\n- [ml_segmentation](https://github.com/dgriffiths3/ml_segmentation) -\u003e semantic segmentation of buildings using Random Forest, Support Vector Machine (SVM) \u0026 Gradient Boosting Classifier (GBC)\n\n- [RSEN](https://github.com/YonghaoXu/RSEN) -\u003e Robust Self-Ensembling Network for Hyperspectral Image Classification\n\n- [MSNet](https://github.com/taochx/MSNet) -\u003e multispectral semantic segmentation network for remote sensing images\n\n- [k-textures](https://zenodo.org/record/6359859#.Yytt6OzMK3I) -\u003e K-textures, a self-supervised hard clustering deep learning algorithm for satellite image segmentation\n\n- [Swin-Transformer-Semantic-Segmentation](https://github.com/koechslin/Swin-Transformer-Semantic-Segmentation) -\u003e Satellite Image Semantic Segmentation\n\n- [UDA_for_RS](https://github.com/Levantespot/UDA_for_RS) -\u003e Unsupervised Domain Adaptation for Remote Sensing Semantic Segmentation with Transformer\n\n- [A-3D-CNN-AM-DSC-model-for-hyperspectral-image-classification](https://github.com/hahatongxue/A-3D-CNN-AM-DSC-model-for-hyperspectral-image-classification) -\u003e Attention Mechanism and Depthwise Separable Convolution Aided 3DCNN for Hyperspectral Remote Sensing Image Classification\n\n- [contrastive-distillation](https://github.com/edornd/contrastive-distillation) -\u003e  A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Images\n\n- [SegForestNet](https://github.com/gritzner/SegForestNet) -\u003e SegForestNet: Spatial-Partitioning-Based Aerial Image Segmentation\n\n- [MFVNet](https://github.com/weichenrs/MFVNet) -\u003e MFVNet: Deep Adaptive Fusion Network with Multiple Field-of-Views for Remote Sensing Image Semantic Segmentation\n\n- [Wildebeest-UNet](https://github.com/zijing-w/Wildebeest-UNet) -\u003e detecting wildebeest and zebras in Serengeti-Mara ecosystem from very-high-resolution satellite imagery\n\n- [segment-anything-eo](https://github.com/aliaksandr960/segment-anything-eo) -\u003e Earth observation tools for Meta AI Segment Anything (SAM - Segment Anything Model)\n\n- [HR-Image-classification_SDF2N](https://github.com/SicongLiuRS/HR-Image-classification_SDF2N) -\u003e A Shallow-to-Deep Feature Fusion Network for VHR Remote Sensing Image Classification\n\n- [sink-seg](https://github.com/mvrl/sink-seg) -\u003e Automatic Segmentation of Sinkholes Using a Convolutional Neural Network\n\n- [Tiling and Stitching Segmentation Output for Remote Sensing: Basic Challenges and Recommendations](https://arxiv.org/abs/1805.12219)\n\n- [EMRT](https://github.com/peach-xiao/EMRT) -\u003e Enhancing Multiscale Representations With Transformer for Remote Sensing Image Semantic Segmentation\n\n- [UDA_for_RS](https://github.com/Levantespot/UDA_for_RS) -\u003e Unsupervised Domain Adaptation for Remote Sensing Semantic Segmentation with Transformer\n\n- [CMTFNet](https://github.com/DrWuHonglin/CMTFNet) -\u003e CMTFNet: CNN and Multiscale Transformer Fusion Network for Remote Sensing Image Semantic Segmentation\n\n- [CM-UNet](https://github.com/XiaoBuL/CM-UNet) -\u003e Hybrid CNN-Mamba UNet for Remote Sensing Image Semantic Segmentation\n\n- [Using Stable Diffusion to Improve Image Segmentation Models](https://medium.com/edge-analytics/using-stable-diffusion-to-improve-image-segmentation-models-1e99c25acbf) -\u003e Augmenting Data with Stable Diffusion\n\n- [SSRS](https://github.com/sstary/SSRS) -\u003e Semantic Segmentation for Remote Sensing, multiple networks implemented\n\n- [BIOSCANN](https://github.com/BiodiversityLab/bioscann) -\u003e BIOdiversity Segmentation and Classification with Artificial Neural Networks\n\n- [ResUNet-a](https://github.com/feevos/resuneta) -\u003e a deep learning framework for semantic segmentation of remotely sensed data\n\n- [SSG2](https://github.com/feevos/ssg2) -\u003e A New Modelling Paradigm for Semantic Segmentation\n\n- [DBFNet](https://github.com/Luffy03/DBFNet) -\u003e Deep Bilateral Filtering Network for Point-Supervised Semantic Segmentation in Remote Sensing Images [IEEE](https://ieeexplore.ieee.org/document/9961229) paper\n\n- [PGNet](https://github.com/Fhujinwu/PGNet) -\u003e PGNet: Positioning Guidance Network for Semantic Segmentation of Very-High-Resolution Remote Sensing Images [paper](https://www.mdpi.com/2072-4292/14/17/4219)\n\n- [ASD](https://github.com/Jingtao-Li-CVer/ASD) -\u003e Anomaly Segmentation for High-Resolution Remote Sensing Images Based on Pixel Descriptors (AAAI2023) [download link](https://ojs.aaai.org/index.php/AAAI/article/view/25563/25335)\n\n- [u-nets-implementation](https://github.com/Aadit3003/u-nets-implementation) -\u003e Semantic-Segmentation-with-U-Nets\n\n- [SDM](https://github.com/caoql98/SDM) -\u003e Scale-aware Detailed Matching for Few-Shot Aerial Image Semantic Segmentation\n\n- [Transferability-Remote-Sensing](https://github.com/GDAOSU/Transferability-Remote-Sensing) -\u003e On the Transferability of Learning Models for Semantic Segmentation for Remote Sensing Data\n\n#\n## Instance segmentation\n\nIn instance segmentation, each individual 'instance' of a segmented area is given a unique lable. For detection of very small objects this may a good approa","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frobmarkcole%2Fsatellite-image-deep-learning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frobmarkcole%2Fsatellite-image-deep-learning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frobmarkcole%2Fsatellite-image-deep-learning/lists"}