{"id":13507091,"url":"https://github.com/MinZHANG-WHU/Change-Detection-Review","last_synced_at":"2025-03-30T07:32:08.433Z","repository":{"id":38774614,"uuid":"266947676","full_name":"MinZHANG-WHU/Change-Detection-Review","owner":"MinZHANG-WHU","description":"A review of change detection methods, including codes and open data sets for deep learning.  From paper: change detection based on artificial intelligence: state-of-the-art and challenges.","archived":false,"fork":false,"pushed_at":"2021-07-30T13:43:15.000Z","size":1244,"stargazers_count":831,"open_issues_count":2,"forks_count":183,"subscribers_count":29,"default_branch":"master","last_synced_at":"2024-10-25T04:24:31.277Z","etag":null,"topics":["artificial-intelligence","caffe","change-detection","code","deep-learning","keras","machine-learning","matlab","open-datasets","python","pytorch","remote-sensing","review","sar","streetview","tensorflow","unsupervised-learning"],"latest_commit_sha":null,"homepage":"https://github.com/MinZHANG-WHU/Change-Detection-Review","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MinZHANG-WHU.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-05-26T04:54:37.000Z","updated_at":"2024-10-23T02:18:03.000Z","dependencies_parsed_at":"2022-09-09T09:10:47.344Z","dependency_job_id":null,"html_url":"https://github.com/MinZHANG-WHU/Change-Detection-Review","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MinZHANG-WHU%2FChange-Detection-Review","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MinZHANG-WHU%2FChange-Detection-Review/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MinZHANG-WHU%2FChange-Detection-Review/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MinZHANG-WHU%2FChange-Detection-Review/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MinZHANG-WHU","download_url":"https://codeload.github.com/MinZHANG-WHU/Change-Detection-Review/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":222397356,"owners_count":16977672,"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":["artificial-intelligence","caffe","change-detection","code","deep-learning","keras","machine-learning","matlab","open-datasets","python","pytorch","remote-sensing","review","sar","streetview","tensorflow","unsupervised-learning"],"created_at":"2024-08-01T02:00:22.476Z","updated_at":"2024-11-01T06:31:23.827Z","avatar_url":"https://github.com/MinZHANG-WHU.png","language":null,"funding_links":[],"categories":["Reference","Hyperspectral","Others"],"sub_categories":["2.2 SAR","Deep Learning"],"readme":"# Change Detection Based on Artificial Intelligence: State-of-the-Art and Challenges\n\n## 1. Introduction\n Change detection based on remote sensing (RS) data is an important method of detecting changes on the Earth’s surface and has a wide range of applications in urban planning, environmental monitoring, agriculture investigation, disaster assessment, and map revision. In recent years, integrated artificial intelligence (AI) technology has become a research focus in developing new change detection methods. Although some researchers claim that AI-based change detection approaches outperform traditional change detection approaches, it is not immediately obvious how and to what extent AI can improve the performance of change detection. This review focuses on the state-of-the-art methods, applications, and challenges of AI for change detection. Specifically, the implementation process of AI-based change detection is first introduced. Then, the data from different sensors used for change detection, including optical RS data, synthetic aperture radar (SAR) data, street view images, and combined heterogeneous data, are presented, and the available open datasets are also listed. The general frameworks of AI-based change detection methods are reviewed and analyzed systematically, and the unsupervised schemes used in AI-based change detection are further analyzed. Subsequently, the commonly used networks in AI for change detection are described. From a practical point of view, the application domains of AI-based change detection methods are classified based on their applicability. Finally, the major challenges and prospects of AI for change detection are discussed and delineated, including (a) heterogeneous big data processing, (b) unsupervised AI, and (c) the reliability of AI. This review will be beneficial for researchers in understanding this field.\n\n![](/Figure%201.png)\n\u003ccenter\u003eFigure 1. General schematic diagram of change detection.\u003c/center\u003e\n\n## 2. Implementation process\n\nFigure 2 provide a general implementation process of AI-based change detection, but the structure of the AI model is diverse and needs to be well designed according to different application situations and the training data. It is worth mentioning that existing mature frameworks such as \u003ca href=\"https://www.tensorflow.org/\" target=\"_blank\"\u003eTensorFlow\u003c/a\u003e, \u003ca href=\"https://keras.io/\" target=\"_blank\"\u003eKeras\u003c/a\u003e, \u003ca href=\"https://pytorch.org/\" target=\"_blank\"\u003ePytorch\u003c/a\u003e, and \u003ca href=\"https://caffe.berkeleyvision.org/\" target=\"_blank\"\u003eCaffe\u003c/a\u003e, help researchers more easily realize the design, training, and deployment of AI models, and their development documents provide detailed introductions.\n\n![](/Figure%202.png)\n\u003ccenter\u003eFigure 2. Implementation process of AI-based change detection (black arrows indicate workflow and red arrow indicates an example).\u003c/center\u003e\n\n### 2.1 Available codes for AI-based methods\n\n\u003ctable\u003e\n\u003ccaption\u003eTable 1. A list of available codes for AI-based change detection methods.\u003c/caption\u003e\n\t\u003ctr\u003e\n\t    \u003cth\u003eMethods\u003c/th\u003e\n\t    \u003cth\u003eKeywords\u003c/th\u003e\n\t    \u003cth\u003ePublication\u003c/th\u003e  \n        \u003cth\u003e(Re-)Implementation\u003c/th\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eSRCDNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN; Siamese; Attention; Super-resolution; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eSuper-resolution-based change detection network with stacked attention module for images with different resolutions, TGRS, 2021.  [\u003ca href=\"https://doi.org/10.1109/TGRS.2021.3091758\" target=\"_blank\"\u003epaper\u003c/a\u003e], [\u003ca href=\"https://github.com/liumency/SRCDNet\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch 1.2\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eESCNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN; Siamese; Superpixel; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eAn End-to-End superpixel-enhanced change detection network for Very-High-Resolution remote sensing images. TNNLS, 2021. [\u003ca href=\"https://doi.org/10.1109/TNNLS.2021.3089332\" target=\"_blank\"\u003epaper\u003c/a\u003e], [\u003ca href=\"https://github.com/Bobholamovic/ESCNet\" target=\"_blank\"\u003ecode\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch 1.3\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eKPCAMNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN; Siamese; KPCA; Unsupervised; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eUnsupervised change detection in multitemporal VHR images based on deep kernel PCA convolutional mapping network,TCYB, 2021. [\u003ca href=\"https://doi.org/10.1109/TCYB.2021.3086884\" target=\"_blank\"\u003epaper\u003c/a\u003e], [\u003ca href=\"https://github.com/I-Hope-Peace/KPCAMNet\" target=\"_blank\"\u003ecode\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePython\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eSeCo\u003c/td\u003e\n\t    \u003ctd\u003eCNN (ResNet); Transfer Learning; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eSeasonal contrast: unsupervised pre-training from uncurated remote sensing data, arXiv, 2021.  [\u003ca href=\"https://arxiv.org/abs/2103.16607\" target=\"_blank\"\u003epaper\u003c/a\u003e], [\u003ca href=\"https://github.com/ElementAI/seasonal-contrast\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch 1.7\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eCapsNet\u003c/td\u003e\n\t    \u003ctd\u003eCapsule Network(SegCaps); CVA; Siamese; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003ePseudo-siamese capsule network for aerial remote sensing images change detection, GRSL, 2020.  [\u003ca href=\"https://doi.org/10.1109/LGRS.2020.3022512\" target=\"_blank\"\u003epaper 1\u003c/a\u003e], Change Capsule Network for Optical Remote Sensing ImageChange Detection, RS, 2021. [\u003ca href=\"https://doi.org/10.1109/LGRS.2020.3022512\" target=\"_blank\"\u003epaper 2\u003c/a\u003e], [\u003ca href=\"https://github.com/xuquanfu/capsule_change_detection\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eKeras\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eBIT_CD\u003c/td\u003e\n\t    \u003ctd\u003eCNN (ResNet18); Siamese; Attention; Transformer; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eRemote sensing image change detection with transformers, TGRS, 2021.  [\u003ca href=\"https://doi.org/10.1109/TGRS.2021.3095166\" target=\"_blank\"\u003epaper\u003c/a\u003e], [\u003ca href=\"https://github.com/justchenhao/BIT_CD\" target=\"_blank\"\u003ecode, dataset, pre-trained model\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch 1.6\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eIAug_CDNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN (GauGAN+UNet); Siamese; GAN; Supervised; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eAdversarial instance augmentation for building change detection in remote sensing images, TGRS, 2021.  [\u003ca href=\"https://doi.org/10.1109/TGRS.2021.3066802\" target=\"_blank\"\u003epaper\u003c/a\u003e], [\u003ca href=\"https://github.com/justchenhao/IAug_CDNet\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eDDNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN; DI+FCM; Unsupervised; SAR\u003c/td\u003e\n\t    \u003ctd\u003eChange detection in synthetic aperture radar images using a dual-domain network, GRSL, 2021.  [\u003ca href=\"https://doi.org/10.1109/LGRS.2021.3073900\" target=\"_blank\"\u003epaper\u003c/a\u003e], [\u003ca href=\"https://github.com/summitgao/SAR_CD_DDNet\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eSNUNet-CD\u003c/td\u003e\n\t    \u003ctd\u003eCNN (NestedUNet); Siamese; Attention; Supervised; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eSNUNet-CD: A densely connected siamese network for change detection of VHR images,  GRSL, 2021.  [\u003ca href=\"https://doi.org/10.1109/LGRS.2021.3056416\" target=\"_blank\"\u003epaper\u003c/a\u003e], [\u003ca href=\"https://github.com/likyoo/Siam-NestedUNet\" target=\"_blank\"\u003ecode, dataset, pre-trained model\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch 1.4\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eDSMSCN\u003c/td\u003e\n\t    \u003ctd\u003eCNN; Siamese; Multi-scale; Unsupervised/Supervised; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003e A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sening images, arXiv, 2020.  [\u003ca href=\"https://arxiv.org/abs/1906.11479\" target=\"_blank\"\u003epaper\u003c/a\u003e], [\u003ca href=\"https://github.com/I-Hope-Peace/DSMSCN\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eTensorflow 1.9\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eSiamCRNN\u003c/td\u003e\n\t    \u003ctd\u003eCNN+RNN; Siamese; Multi-source; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003e Change Detection in Multisource VHR Images via Deep Siamese Convolutional Multiple-Layers Recurrent Neural Network, TGRS, 2020.  [\u003ca href=\"https://doi.org/10.1109/TGRS.2019.2956756\" target=\"_blank\"\u003epaper\u003c/a\u003e], [\u003ca href=\"https://github.com/I-Hope-Peace/SiamCRNN\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eTensorflow 1.9\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eDSIFN\u003c/td\u003e\n\t    \u003ctd\u003eCNN; Attention Mechanism; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003e A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sening images, ISPRS, 2020.  [\u003ca href=\"https://doi.org/10.1016/j.isprsjprs.2020.06.003\" target=\"_blank\"\u003epaper\u003c/a\u003e], [\u003ca href=\"https://github.com/GeoZcx/A-deeply-supervised-image-fusion-network-for-change-detection-in-remote-sensing-images\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch \u0026 Keras\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eCEECNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN; Attention Mechanism; Similarity Measure; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003e Looking for change? Roll the Dice and demand Attention, arXiv, 2020.  [\u003ca href=\"https://arxiv.org/abs/2009.02062\" target=\"_blank\"\u003epaper\u003c/a\u003e], [\u003ca href=\"https://github.com/feevos/ceecnet\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eMXNet + Python\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eLamboiseNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN (Light UNet++); Optical RS\u003c/td\u003e\n\t    \u003ctd\u003e Change detection in satellite imagery using deep learning, Master Thesis.  [\u003ca href=\"https://github.com/hbaudhuin/LamboiseNet\" target=\"_blank\"\u003ecode, dataset, pre-trained model\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eDTCDSCN\u003c/td\u003e\n\t    \u003ctd\u003eCNN; Siamese\u003c/td\u003e\n\t    \u003ctd\u003e Building change detection for remote sensing images using a dual task constrained deep siamese convolutional network model, undergoing review.  [\u003ca href=\"https://github.com/fitzpchao/DTCDSCN\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eLand-Cover-Analysis\u003c/td\u003e\n\t    \u003ctd\u003eCNN (UNet); Post-Classification;  Optical RS\u003c/td\u003e\n\t    \u003ctd\u003e Land Use/Land cover change detection in cyclone affected areas using convolutional neural networks.  [\u003ca href=\"https://github.com/Kalit31/Land-Cover-Analysis/blob/master/Report.pdf\" target=\"_blank\"\u003ereport\u003c/a\u003e], [\u003ca href=\"https://github.com/Kalit31/Land-Cover-Analysis\" target=\"_blank\"\u003ecode, dataset, pre-trained model\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eTensorFlow+Keras\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eCorrFusionNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN; Scene-level; Siamese;  Optical RS\u003c/td\u003e\n\t    \u003ctd\u003e Correlation based fusion network towards multi-temporal scene classification and change detection, undergoing review.  [\u003ca href=\"https://github.com/rulixiang/CorrFusionNet\" target=\"_blank\"\u003ecode, pre-trained model\u003c/a\u003e], [\u003ca href=\"https://github.com/rulixiang/MtS-WH-Dataset\" target=\"_blank\"\u003edataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eTensorFlow 1.8\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eSSCDNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN (ResNet18); Siamese; Transfer Learning; Semantic; Streetview\u003c/td\u003e\n\t    \u003ctd\u003eWeakly supervised silhouette-based semantic scene change detection, ICRA, 2020.  [\u003ca href=\"https://arxiv.org/abs/1811.11985\" target=\"_blank\"\u003epaper\u003c/a\u003e] [\u003ca href=\"https://github.com/xdspacelab/sscdnet\" target=\"_blank\"\u003ecode, dataset, pre-trained model\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch+Python3.6\u003c/td\u003e\n\t\u003c/tr\u003e\n     \u003ctr\u003e\n\t    \u003ctd\u003eHeterogeneous_CD\u003c/td\u003e\n\t    \u003ctd\u003eAE (Code-Aligned AE); Unsupervised; Transformation; Heterogeneous; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eCode-aligned autoencoders for unsupervised change detection in multimodal remote sensing images, arXiv, 2020. [\u003ca href=\"https://arxiv.org/abs/2004.07011\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/llu025/Heterogeneous_CD/tree/master/Code-Aligned_Autoencoders\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eTensorFlow 2.0\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eFDCNN\u003c/td\u003e\n\t    \u003ctd\u003eCNN (VGG16); Transfer Learning; Pure-Siamese; Multi-scale; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eA feature difference convolutional neural network-based change detection method, TGRS, 2020. [\u003ca href=\"https://dx.doi.org/10.1109/tgrs.2020.2981051\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/MinZHANG-WHU/FDCNN\" target=\"_blank\"\u003ecode, dataset, pre-trained model\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eCaffe+Python2.7\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eSTANet\u003c/td\u003e\n\t    \u003ctd\u003eCNN (ResNet-18); Attention Mechanism; Pure-Siamese; Spatial–Temporal Dependency; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eA spatial-temporal attention-based method and a new dataset for remote sensing image change detection, RS, 2020. [\u003ca href=\"https://dx.doi.org/10.3390/rs12101662\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/justchenhao/STANet\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch+Python3.6\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctr\u003e\n\t    \u003ctd\u003eX-Net\u003c/td\u003e\n\t    \u003ctd\u003eCNN; Unsupervised; Transformation; Heterogeneous; Optical RS; SAR\u003c/td\u003e\n\t    \u003ctd\u003eDeep image translation with an affinity-based change prior for unsupervised multimodal change detection, 2020. [\u003ca href=\"https://arxiv.org/abs/2001.04271\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/llu025/Heterogeneous_CD/tree/master/legacy/Deep_Image_Translation\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eTensorflow 1.4\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctr\u003e\n\t    \u003ctd\u003eACE-Net\u003c/td\u003e\n\t    \u003ctd\u003eAE (Adversarial Cyclic Encoders); Unsupervised; Transformation; Heterogeneous; Optical RS; SAR\u003c/td\u003e\n\t    \u003ctd\u003eDeep image translation with an affinity-based change prior for unsupervised multimodal change detection, 2020. [\u003ca href=\"https://arxiv.org/abs/2001.04271\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/llu025/Heterogeneous_CD/tree/master/legacy/Deep_Image_Translation\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eTensorflow 1.4\u003c/td\u003e\n\t\u003c/tr\u003e\n     \u003ctr\u003e\n\t    \u003ctd\u003eVGG_LR\u003c/td\u003e\n\t    \u003ctd\u003eCNN (VGG16); Transfer Learning; Pure-Siamese; SLIC; Low Ranks; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eChange detection based on deep features and low rank, GRSL, 2017. [\u003ca href=\"https://dx.doi.org/10.1109/LGRS.2017.2766840\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/MinZHANG-WHU/FDCNN/tree/master/vgg_lr\" target=\"_blank\"\u003ere-implementation code, dataset, pre-trained model\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eCaffe+Matlab\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eCDNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN; Siamese; Multimodal Data; Point Cloud Data\u003c/td\u003e\n\t    \u003ctd\u003e Detecting building changes between airborne laser scanning and photogrammetric data, RS, 2019. [\u003ca href=\"https://doi.org/10.3390/rs11202417\" target=\"_blank\"\u003epaper\u003c/a\u003e], [\u003ca href=\"https://github.com/Zhenchaolibrary/PointCloud2PointCloud-Change-Detection\" target=\"_blank\"\u003ecode\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch\u003c/td\u003e\n\t\u003c/tr\u003e\n     \u003ctr\u003e\n\t    \u003ctd\u003eSCCN\u003c/td\u003e\n\t    \u003ctd\u003eAE (DAE); Unsupervised; Heterogeneous; Optical RS; SAR\u003c/td\u003e\n\t    \u003ctd\u003eA deep convolutional coupling network for change detection based on heterogeneous optical and radar images, TNNLS, 2018. [\u003ca href=\"https://dx.doi.org/10.1109/TNNLS.2016.2636227\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/llu025/Heterogeneous_CD/tree/master/Code-Aligned_Autoencoders\" target=\"_blank\"\u003ere-implementation code\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eTensorFlow 2.0\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003ecGAN\u003c/td\u003e\n\t    \u003ctd\u003eGAN (conditional GAN); Heterogeneous; Optical RS; SAR\u003c/td\u003e\n\t    \u003ctd\u003e A conditional adversarial network for change detection in heterogeneous images, GRSL, 2019. [\u003ca href=\"https://dx.doi.org/10.1109/LGRS.2018.2868704\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/llu025/Heterogeneous_CD/tree/master/Code-Aligned_Autoencoders\" target=\"_blank\"\u003ere-implementation code\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eTensorFlow 2.0\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eDASNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN (VGG16); Siamese; Attention Mechanism  ; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eDASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images, arXiv, 2020. [\u003ca href=\"\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/lehaifeng/DASNet\" target=\"_blank\"\u003ecode, dataset, pre-trained model\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch+Python3.6\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eUNetLSTM\u003c/td\u003e\n\t    \u003ctd\u003eCNN (UNet); RNN (LSTM); Integrated Model; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eDetecting Urban Changes With Recurrent Neural Networks From Multitemporal Sentinel-2 Data, IGARSS, 2019. [\u003ca href=\"https://arxiv.org/abs/1910.07778\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/granularai/chip_segmentation_fabric\" target=\"_blank\"\u003ecode, dataset, pre-trained model\u003c/a\u003e] and  [\u003ca href=\"https://github.com/SebastianHafner/urban_change_detection\" target=\"_blank\"\u003ecode\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch+Python3.6\u003c/td\u003e\n\t\u003c/tr\u003e\u003ctr\u003e\n\t    \u003ctd\u003eCDMI-Net\u003c/td\u003e\n\t    \u003ctd\u003eCNN (Unet); Pure-Siamese; Multiple Instance Learning; Landslide Mapping; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eDeep multiple instance learning for landslide mapping, GRSL, 2020. [\u003ca href=\"https://dx.doi.org/10.1109/LGRS.2020.3007183\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/MinZHANG-WHU/CDMI-Net\" target=\"_blank\"\u003ecode, pre-trained model\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch+Python3.6\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eDSFANet\u003c/td\u003e\n\t    \u003ctd\u003eDNN; Unsupervised; Pre-classification; Slow Feature Analysis; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eUnsupervised deep slow feature analysis for change detection in multi-temporal remote sensing images, TGRS, 2019. [\u003ca href=\"https://dx.doi.org/10.1109/TGRS.2019.2930682\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/rulixiang/DSFANet\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eTensorFlow 1.7\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eCD-UNet++\u003c/td\u003e\n\t    \u003ctd\u003eCNN (improved UNet++); Direct Classification; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eEnd-to-end change detection for high resolution satellite images using improved UNet++, RS, 2019. [\u003ca href=\"https://doi.org/10.3390/rs11111382\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/daifeng2016/End-to-end-CD-for-VHR-satellite-image\" target=\"_blank\"\u003ecode\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eTensorFlow+Keras\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eSiameseNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN (VGG16); Pure-Siamese; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eSiamese network with multi-level features for patch-based change detection in satellite imagery, GlobalSIP, 2018. [\u003ca href=\"https://sigport.org/documents/siamese-network-multi-level-features-patch-based-change-detection-satellite-imagery\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/vbhavank/Siamese-neural-network-for-change-detection\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eTensorFlow+Keras\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eRe3FCN\u003c/td\u003e\n\t    \u003ctd\u003eCNN (ConvLSTM); PCA; 3D convolution; Multi-class changes; Optical RS; Hyperspectral\u003c/td\u003e\n\t    \u003ctd\u003eChange detection in hyperspectral images using recurrent 3D fully convolutional networks, RS, 2018. [\u003ca href=\"https://doi.org/10.3390/rs10111827\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/mkbensalah/Change-Detection-in-Hyperspectral-Images target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eTensorFlow+Keras\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eFC-EF, FC-Siam-conc, FC-Siam-diff\u003c/td\u003e\n\t    \u003ctd\u003eCNN (UNet); Pure-Siamese; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eFully convolutional siamese networks for change detection, ICIP, 2018. [\u003ca href=\"https://arxiv.org/abs/1810.08462\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/rcdaudt/fully_convolutional_change_detection\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eCosimNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN (Deeplab v2); Pure-Siamese; Streetview\u003c/td\u003e\n\t    \u003ctd\u003eLearning to measure changes: fully convolutional siamese metric networks for scene change detection, arXiv, 2018. [\u003ca href=\"https://arxiv.org/abs/1810.09111\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/gmayday1997/SceneChangeDet\" target=\"_blank\"\u003ecode, dataset, pre-trained model\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch+Python2.7\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eMask R-CNN\u003c/td\u003e\n\t    \u003ctd\u003eMask R-CNN (ResNet-101); Transfer Learning; Post-Classification; Optical RS \u003c/td\u003e\n\t    \u003ctd\u003eSlum segmentation and change detection: a deep learning approach, NIPS, 2018. [\u003ca href=\"https://arxiv.org/abs/1811.07896\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/cbsudux/Mumbai-slum-segmentation\" target=\"_blank\"\u003ecode, dataset, pre-trained model\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eTensorFlow+Keras\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eCaffeNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN (CaffeNet); Unsupervised; Transfer Learning; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eConvolutional neural network features based change detection in satellite images, IWPR, 2016. [\u003ca href=\"https://doi.org/10.1117/12.2243798\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/vbhavank/Unstructured-change-detection-using-CNN\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eTensorFlow+Keras\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eCWNN\u003c/td\u003e\n\t    \u003ctd\u003eCNN (CWNN); Unsupervised; Pre-Classification; SAR\u003c/td\u003e\n\t    \u003ctd\u003eSea ice change detection in SAR images based on convolutional-wavelet neural networks, GRSL, 2019. [\u003ca href=\"https://dx.doi.org/10.1109/LGRS.2019.2895656\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/summitgao/SAR_Change_Detection_CWNN\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eMatlab\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eMLFN\u003c/td\u003e\n\t    \u003ctd\u003eCNN (DenseNet); Transfer learning; SAR\u003c/td\u003e\n\t    \u003ctd\u003eTransferred deep learning for sea ice change detection from synthetic aperture radar images, GRSL, 2019. [\u003ca href=\"https://dx.doi.org/10.1109/LGRS.2019.2906279\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/summitgao/SAR-Change-Detection-MLFN\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eCaffe+Matlab\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eGarborPCANet\u003c/td\u003e\n\t    \u003ctd\u003eCNN (PCANet); Unsupervised; Pre-Classification; Gabor Wavelets; SAR\u003c/td\u003e\n\t    \u003ctd\u003eAutomatic change detection in synthetic aperture radar images based on PCANet, GRSL, 2016. [\u003ca href=\"https://dx.doi.org/10.1109/LGRS.2016.2611001\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/summitgao/SAR_Change_Detection_GarborPCANet\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eMatlab\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eMs-CapsNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN (Ms-CapsNet); Capsule; Attention Mechanism; Adaptive Fusion Convolution; SAR\u003c/td\u003e\n\t    \u003ctd\u003eChange detection in SAR images based on multiscale capsule network, GRSL, 2020. [\u003ca href=\"https://dx.doi.org/10.1109/LGRS.2020.2977838\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/summitgao/SAR_CD_MS_CapsNet\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eMatlab+Keras2.16\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eDCNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN; Unsupervised; Pre-Classification; SAR\u003c/td\u003e\n\t    \u003ctd\u003eChange detection from synthetic aperture radar images based on channel weighting-based deep cascade network, JSTARS, 2019. [\u003ca href=\"https://dx.doi.org/10.1109/JSTARS.2019.2953128\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/summitgao/SAR_CD_DCNet\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eCaffe\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eChangeNet\u003c/td\u003e\n\t    \u003ctd\u003eCNN; Siamese; StreetView\u003c/td\u003e\n\t    \u003ctd\u003eChangeNet: a deep learning architecture for visual change detection, ECCV, 2018. [\u003ca href=\"http://openaccess.thecvf.com/content_eccv_2018_workshops/w7/html/Varghese_ChangeNet_A_Deep_Learning_Architecture_for_Visual_Change_Detection_ECCVW_2018_paper.html\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/leonardoaraujosantos/ChangeNet\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePytorch\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd colspan=\"4\"\u003eOthers will be added soon!\u003c/td\u003e\n    \u003c/tr\u003e\n\u003c/table\u003e\n\n### 2.2 Available codes for traditional methods\n\n\u003ctable\u003e\n\u003ccaption\u003eTable 2. A list of available codes for traditional change detection methods.\u003c/caption\u003e\n\t\u003ctr\u003e\n\t    \u003cth\u003eMethods\u003c/th\u003e\n\t    \u003cth\u003eKeywords\u003c/th\u003e\n\t    \u003cth\u003ePublication\u003c/th\u003e  \n        \u003cth\u003eImplementation\u003c/th\u003e  \n\t\u003c/tr\u003e\n     \u003ctr\u003e\n\t    \u003ctd\u003eSeveral Classical Methods\u003c/td\u003e\n\t    \u003ctd\u003eCVA; DPCA; Image Differencing; Image Ratioing; Image Regression; IR-MAD; MAD; PCAkMeans; PCDA; KMeans; OTSU; Fixed Threshold\u003c/td\u003e\n\t    \u003ctd\u003eA toolbox for remote sensing change detection. [\u003ca href=\"https://github.com/Bobholamovic/ChangeDetectionToolbox\" target=\"_blank\"\u003ecode\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eMatlab\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eMatlab Toolbox Change Detection\u003c/td\u003e\n\t    \u003ctd\u003eIR-MAD; IT-PCA; ERM; ICM\u003c/td\u003e\n\t    \u003ctd\u003eA toolbox for unsupervised change detection analysis, IJRS, 2016.[\u003ca href=\"https://doi.org/10.1080/01431161.2016.1154226\" target=\"_blank\"\u003epaper\u003c/a\u003e] [\u003ca href=\"https://github.com/NicolaFalco/Matlab-toolbox-change-detection\" target=\"_blank\"\u003ecode\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eMatlab\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eRFR,SVR,GPR\u003c/td\u003e\n\t    \u003ctd\u003eUnsupervised; Image Regression; Heterogeneous; Optical RS; SAR\u003c/td\u003e\n\t    \u003ctd\u003eUnsupervised image regression for heterogeneous change detection, TGRS, 2019. [\u003ca href=\"https://dx.doi.org/10.1109/TGRS.2019.2930348\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/llu025/Heterogeneous_CD/tree/master/legacy/Image_Regression\" target=\"_blank\"\u003ecode\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eMatlab\u003c/td\u003e\n\t\u003c/tr\u003e\n     \u003ctr\u003e\n\t    \u003ctd\u003eHPT\u003c/td\u003e\n\t    \u003ctd\u003eUnsupervised; Transformation; Heterogeneous; Optical RS; SAR\u003c/td\u003e\n\t    \u003ctd\u003eChange detection in heterogenous remote sensing images via homogeneous pixel transformation, TIP, 2018. [\u003ca href=\"https://dx.doi.org/10.1109/TIP.2017.2784560\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/llu025/Heterogeneous_CD/tree/master/legacy/Image_Regression\" target=\"_blank\"\u003ere-implementation code\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eMatlab\u003c/td\u003e\n\t\u003c/tr\u003e\n     \u003ctr\u003e\n\t    \u003ctd\u003ekCCA\u003c/td\u003e\n\t    \u003ctd\u003eCanonical Correlation Analysis; Cross-Sensor; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eSpectral alignment of multi-temporal cross-sensor images with automated kernel correlation analysis, IJPRS, 2015. [\u003ca href=\"https://doi.org/10.1016/j.isprsjprs.2015.02.005\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://sites.google.com/site/michelevolpiresearch/codes/cross-sensor\" target=\"_blank\"\u003ecode\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eMatlab\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eKer. Diff. RBF\u003c/td\u003e\n\t    \u003ctd\u003eUnsupervised; K-means; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eUnsupervised change detection with kernels, GRSL, 2012. [\u003ca href=\"https://dx.doi.org/10.1016/j.jag.2011.10.013\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://drive.google.com/file/d/0B9xP9Y5JKJz0Q1ctbDJERWpTd2s/edit?usp=sharing\" target=\"_blank\"\u003ecode\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eMatlab\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eFDA-RM\u003c/td\u003e\n\t    \u003ctd\u003eDI-based; Frequency-Domain Analysis; Random Multigraphs; SAR\u003c/td\u003e\n\t    \u003ctd\u003eSynthetic aperture radar image change detection based on frequency domain analysis and random multigraphs, JARS, 2018. [\u003ca href=\"https://doi.org/10.1117/1.JRS.12.016010\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/summitgao/SAR_Change_Detection_FDA_RMG\" target=\"_blank\"\u003ecode\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eMatlab \u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eCD-NR-ELM\u003c/td\u003e\n\t    \u003ctd\u003eDI-based; Pre-Classification; Extreme Learning Machine; SAR\u003c/td\u003e\n\t    \u003ctd\u003eChange detection from synthetic aperture radar images based on neighborhood-based ratio and extreme learning machine, JARS, 2016. [\u003ca href=\"https://doi.org/10.1117/1.JRS.10.046019\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/summitgao/SAR_Change_Detection_NR_ELM\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eMatlab\u003c/td\u003e\n\t\u003c/tr\u003e\n     \u003ctr\u003e\n\t    \u003ctd\u003eNone\u003c/td\u003e\n\t    \u003ctd\u003eLikelihood Ratio; Test Statistic; SAR\u003c/td\u003e\n\t    \u003ctd\u003eChange detection in polarimetric SAR\nimages, 2015. [\u003ca href=\"https://github.com/fouronnes/SAR-change-detection/blob/master/SAR_Change_Detection_Victor_Poughon.pdf\" target=\"_blank\"\u003ereport\u003c/a\u003e]  [\u003ca href=\"https://github.com/fouronnes/SAR-change-detection\" target=\"_blank\"\u003ecode\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003ePython\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003ePCA K-Means\u003c/td\u003e\n\t    \u003ctd\u003eUnsupervised; DI-based; PCA; K Means; Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eUnsupervised Change Detection in Satellite Images Using Principal Component Analysis and k-Means Clustering, GRSL, 2009. [\u003ca href=\"https://dx.doi.org/10.1109/LGRS.2009.2025059\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/rulixiang/ChangeDetectionPCAKmeans\" target=\"_blank\"\u003ere-implementation code, dataset\u003c/a\u003e] or [\u003ca href=\"https://github.com/leduckhai/Change-Detection-PCA-KMeans\" target=\"_blank\"\u003ere-implementation code\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eMatlab\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003ePTCD\u003c/td\u003e\n\t    \u003ctd\u003eTensor; Hyperspectral Optical RS\u003c/td\u003e\n\t    \u003ctd\u003eThree-Order Tucker Decomposition and Reconstruction Detector for Unsupervised Hyperspectral Change Detection. JSTARS, 2021. [\u003ca href=\"https://dx.doi.org/10.1109/JSTARS.2021.3088438\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/zephyrhours/Hyperspectral-Change-Detection-PTCD\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eMatlab\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\t\u003ctr\u003e\n\t    \u003ctd\u003eGBF-CD\u003c/td\u003e\n\t    \u003ctd\u003eData Fusion; Graph; EM; KI;\u003c/td\u003e\n\t    \u003ctd\u003eGraph-Based Data Fusion Applied to: Change Detection and Biomass Estimation in Rice Crops. Remote Sensing, 2020 [\u003ca href=\"https://doi.org/10.3390/rs12172683\" target=\"_blank\"\u003epaper\u003c/a\u003e]  [\u003ca href=\"https://github.com/DavidJimenezS/GBF-CD\" target=\"_blank\"\u003ecode, dataset\u003c/a\u003e]\u003c/td\u003e\n        \u003ctd\u003eMatlab\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd colspan=\"4\"\u003eOthers will be added soon!\u003c/td\u003e\n    \u003c/tr\u003e\n\u003c/table\u003e\n\n\n## 3. Open datasets\n\nCurrently, there are some freely available data sets for change detection, which can be used as benchmark datasets for AI training and accuracy evaluation in future research. Detailed information is presented in Table 3.\n\u003ctable\u003e\n\u003ccaption\u003eTable 3. A list of open datasets for change detection.\u003c/caption\u003e\n\t\u003ctr\u003e\n\t    \u003cth\u003eType\u003c/th\u003e\n\t    \u003cth width=\"180px\"\u003eData set\u003c/th\u003e\n\t    \u003cth\u003eDescription\u003c/th\u003e  \n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd rowspan=\"21\"\u003eOptical RS\u003c/td\u003e\n\t    \u003ctd\u003eDSIFN Dataset [\u003ca href=\"#Ref-25\"\u003e25\u003c/a\u003e] \u003c/td\u003e\n\t    \u003ctd\u003e6 bi-temporal high resolution images from Google Earth. There are 3600 image pairs with size of 512 × 512 for training, 340 for validation, and 48 for test. [\u003ca href=\"https://github.com/GeoZcx/A-deeply-supervised-image-fusion-network-for-change-detection-in-remote-sensing-images/tree/master/dataset\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eS2MTCP [\u003ca href=\"#Ref-26\"\u003e26\u003c/a\u003e] \u003c/td\u003e\n\t    \u003ctd\u003e1520 Sentinel-2 level 1C image pairs focused on urban areas around the world,  with 10m spatial resolution and the size of 600x600 pixels. Geometric or radiometric corrections are not performed. [\u003ca href=\"https://zenodo.org/record/4280482#.YQPtXI5LhjV\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eSYSU-CD [\u003ca href=\"#Ref-27\"\u003e27\u003c/a\u003e] \u003c/td\u003e\n\t    \u003ctd\u003e20000 pairs of 0.5-m aerial images of size 256×256 taken between the years 2007 and 2014 in Hong Kong, including 6 change types: (a) newly built urban buildings; (b) suburban dilation; (c) groundwork before construction; (d) change of vegetation; (e) road expansion; (f) sea construction. [\u003ca href=\"https://github.com/liumency/SYSU-CD\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eS2Looking [\u003ca href=\"#Ref-28\"\u003e28\u003c/a\u003e] \u003c/td\u003e\n\t    \u003ctd\u003eBuilding change detection dataset consists of 5000 registered bitemporal image pairs (size of 1024*1024, 0.5 ~ 0.8 m/pixel) of rural areas throughout the world and more than 65,920 annotated change instances, separately indicating the newly built and demolished building [\u003ca href=\"https://github.com/AnonymousForACMMM/Dataset\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eSynthetic and real images Dataset [\u003ca href=\"#Ref-29\"\u003e29\u003c/a\u003e] \u003c/td\u003e\n\t    \u003ctd\u003eThe database contains 12,000 triples of synthetic images without object shift, 12,000 triples of model images  with object shift and 16,000 triples of fragments of real remote  sensing  images.  Performed  tests  have  shown  that  the proposed  CNN  is  promising  and  efficient  enough  in  change detection on synthetic and real images [\u003ca href=\"https://drive.google.com/file/d/1GX656JqqOyBi_Ef0w65kDGVto-nHrNs9\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eSEmantic Change detectiON Dataset (SECOND) [\u003ca href=\"#Ref-24\"\u003e24\u003c/a\u003e] \u003c/td\u003e\n\t    \u003ctd\u003ea pixel-level annotated semantic change detection dataset, including 4662 pairs of aerial images with 512 x 512 pixels from several platforms and sensors, covering Hangzhou, Chengdu, and Shanghai.  It focus on 6 main land-cover classes, i.e. , non-vegetated ground surface, tree, low vegetation, water, buildings and playgrounds , that are frequently involved in natural and man-made geographical changes. [\u003ca href=\"http://www.captain-whu.com/PROJECT/SCD/\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eHyperspectral change detection dataset [\u003ca href=\"#Ref-1\"\u003e1\u003c/a\u003e] \u003c/td\u003e\n\t    \u003ctd\u003e3 different hyperspectral scenes acquired by AVIRIS or HYPERION sensor, with 224 or 242 spectral bands, labeled 5 types of changes related with crop transitions at pixel level. [\u003ca href=\"https://citius.usc.es/investigacion/datasets/hyperspectral-change-detection-dataset\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eRiver HSIs dataset  [\u003ca href=\"#Ref-2\"\u003e2\u003c/a\u003e] \u003c/td\u003e\n\t    \u003ctd\u003e2 HSIs in Jiangsu province, China, with 198 bands, labeled as changed and unchanged at pixel level. [\u003ca href=\"https://drive.google.com/file/d/1cWy6KqE0rymSk5-ytqr7wM1yLMKLukfP/view\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eHRSCD  [\u003ca href=\"#Ref-3\"\u003e3\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003e291 co-registered pairs of RGB aerial images, with pixel-level change and land cover annotations, providing hierarchical level change labels, for example, level 1 labels include five classes: no information, artificial surfaces, agricultural areas, forests, wetlands, and water. [\u003ca href=\"https://ieee-dataport.org/open-access/hrscd-high-resolution-semantic-change-detection-dataset\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eWHU building dataset  [\u003ca href=\"#Ref-4\"\u003e4\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003e2-period aerial images containing 12,796 buildings, provided along with building vector and raster maps. [\u003ca href=\"http://study.rsgis.whu.edu.cn/pages/download/\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\u003ctd\u003eSZTAKI Air change benchmark  [\u003ca href=\"#Ref-5\"\u003e5\u003c/a\u003e, \u003ca href=\"#Ref-6\"\u003e6\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003e13 aerial image pairs with 1.5 m spatial resolution, labeled as changed and unchanged at pixel level. [\u003ca href=\"http://web.eee.sztaki.hu/remotesensing/airchange_benchmark.html\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eOSCD  [\u003ca href=\"#Ref-7\"\u003e7\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003e24 pairs of multispectral images acquired by Sentinel-2, labeled as changed and unchanged at pixel level. [\u003ca href=\"https://rcdaudt.github.io/oscd/\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eChange detection dataset  [\u003ca href=\"#Ref-8\"\u003e8\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003e4 pairs of multispectral images with different spatial resolutions, labeled as changed and unchanged at pixel level. [\u003ca href=\"https://github.com/MinZHANG-WHU/FDCNN\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eMtS-WH [\u003ca href=\"#Ref-9\"\u003e9\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003e2 large-size VHR images acquired by IKONOS sensors, with 4 bands and 1 m spatial resolution, labeled 5 types of changes (i.e., parking, sparse houses, residential region, and vegetation region) at scene level. [\u003ca href=\"http://sigma.whu.edu.cn/newspage.php?q=2019_03_26\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eABCD  [\u003ca href=\"#Ref-10\"\u003e10\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003e16,950 pairs of RGB aerial images for detecting washed buildings by tsunami, labeled damaged buildings at scene level. [\u003ca href=\"https://github.com/gistairc/ABCDdataset\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003exBD  [\u003ca href=\"#Ref-11\"\u003e11\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003ePre- and post-disaster satellite imageries for building damage assessment, with over 850,000 building polygons from 6 disaster types, labeled at pixel level with 4 damage scales. [\u003ca href=\"https://xview2.org/dataset\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eAICD  [\u003ca href=\"#Ref-12\"\u003e12\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003e1000 pairs of synthetic aerial images with artificial changes generated with a rendering engine, labeled as changed and unchanged at pixel level. [\u003ca href=\"https://computervisiononline.com/dataset/1105138664\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eDatabase of synthetic and real images  [\u003ca href=\"#Ref-13\"\u003e13\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003e24,000 synthetic images and 16,000 fragments of real season-varying RS images obtained by Google Earth, labeled as changed and unchanged at pixel level. [\u003ca href=\"https://drive.google.com/file/d/1GX656JqqOyBi_Ef0w65kDGVto-nHrNs9/edit\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eLEVIR-CD  [\u003ca href=\"#Ref-14\"\u003e14\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003e637 very high-resolution (VHR, 0.5m/pixel) Google Earth (GE) image patch pairs with a size of 1024 × 1024 pixels and contains a total of 31,333 individual change building instances, labeled as changed and unchanged at pixel level. [\u003ca href=\"https://justchenhao.github.io/LEVIR/\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eBastrop fire dataset [\u003ca href=\"#Ref-21\"\u003e21\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003e4 images acquired by different sensors over the Bastrop County, Texas (USA). It is composed by a Landsat 5 TM as the pre-event image and a Landsat 5 TM, a EO-1 ALI and a Landsat 8 as post-event images, labeled as changed and unchanged at pixel level, mainly caused by wildfire. [\u003ca href=\"https://sites.google.com/site/michelevolpiresearch/codes/cross-sensor\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n\t \u003ctr\u003e\n\t    \u003ctd\u003eGoogle data set [\u003ca href=\"#Ref-23\"\u003e23\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003e19 season-varying VHR images pairswith 3 bands of red, green, and blue, a spatial resolution of 0.55 m, and the size ranging from 1006×1168 pixels to 4936×5224 pixels. The image changes include waters, roads, farmland, bare land, forests, buildings, ships, etc. Buildings make up the main changes. acquired during the periods between 2006 and 2019, covering the suburb areas of Guangzhou City, China. [\u003ca href=\"https://github.com/daifeng2016/Change-Detection-Dataset-for-High-Resolution-Satellite-Imagery\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd rowspan=\"2\" \u003eOptical RS \u0026 SAR\u003c/td\u003e\n\t    \u003ctd\u003eCalifornia dataset [\u003ca href=\"#Ref-22\"\u003e22\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003e 3 images, including a RS image captured by Landsat 8 with 9 channels on 2017, a SAR image captured by Sentinel-1A (recorded in polarisations VV and VH) after the occurrence of a flood, and a ground truth map. [\u003ca href=\"https://sites.google.com/view/luppino/data\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t \u003ctr\u003e\n\t    \u003ctd\u003eHomogeneous CD Dataset [\u003ca href=\"#Ref-30\"\u003e30\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003e6 scenarios:  Scenario  1  with  two  single-polarizationSAR  data  sets;  Scenario  2  with  two  PolSAR  data  sets;  Scenario  3  with  two  optical  image  data  sets.  HeterogeneousCD:  Scenario  4  with  two  SAR/optical  (multispectral)  datasets;  Scenario  5  with  two  multispectral data  sets  of  differentbands  acquired  from  different  sensors;  Scenario  6  with  twoPolSAR/optical  (multispectral)  data  sets.  [\u003ca href=\"https://github.com/yulisun/INLPG\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd rowspan=\"3\" \u003eStreet view\u003c/td\u003e\n\t    \u003ctd\u003eVL-CMU-CD  [\u003ca href=\"#Ref-15\"\u003e15\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003e1362 co-registered pairs of RGB and depth images, labeled ground truth change (e.g., bin, sign, vehicle, refuse, construction, traffic cone, person/cycle, barrier) and sky masks at pixel level. [\u003ca href=\"http://ghsi.github.io/proj/RSS2016.html\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003ePCD 2015 [\u003ca href=\"#Ref-16\"\u003e16\u003c/a\u003e]\u003c/td\u003e\n\t    \u003ctd\u003e200 panoramic image pairs in \"TSUNAMI\" and \"GSV\" subset, with the size of 224 × 1024 pixels, label as changed and unchanged at pixel level. [\u003ca href=\"http://www.vision.is.tohoku.ac.jp/us/download/\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eChange detection dataset  [\u003ca href=\"#Ref-17\"\u003e17\u003c/a\u003e] \u003c/td\u003e\n\t    \u003ctd\u003eImage sequences of city streets captured by a vehicle-mounted camera at two different time points, with the size of 5000 × 2500 pixels, labeled 3D scene structure changes at pixel level. [\u003ca href=\"http://www.vision.is.tohoku.ac.jp/us/research/4d_city_modeling/chg_dataset/\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n    \t\u003ctr\u003e\n       \u003ctd rowspan=\"4\" \u003eCV\u003c/td\u003e\n\t    \u003ctd\u003eCDNet 2012 [\u003ca href=\"#Ref-18\"\u003e18\u003c/a\u003e] \u003c/td\u003e\n\t    \u003ctd\u003e 6 video categories with 4 to 6 videos sequences in each category, and the groundtruth images contain 5 labels namely: static, hard shadow, outside region of interest, unknown motion (usually around moving objects, due to semi-transparency and motion blur), and motion. [\u003ca href=\"http://jacarini.dinf.usherbrooke.ca/dataset2012/\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n    \t\u003ctr\u003e\n\t    \u003ctd\u003eCDNet 2014  [\u003ca href=\"#Ref-19\"\u003e19\u003c/a\u003e,\u003ca href=\"#Ref-20\"\u003e20\u003c/a\u003e] \u003c/td\u003e\n\t    \u003ctd\u003e 22 additional videos (∼70; 000 pixel-wise annotated frames) spanning 5 new categories that incorporate challenges encountered in many surveillance settings, and provides realistic, camera captured (without CGI), diverse set of indoor and outdoor videos like the CDnet 2012. [\u003ca href=\"http://www.changedetection.net/\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\n        \u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003eChangeSim  [\u003ca href=\"#Ref-31\"\u003e31\u003c/a\u003e] \u003c/td\u003e\n\t    \u003ctd\u003ea challenging dataset aimed at online scene change detection and more, collecting in photo-realistic simulation environments with the presence of environmental non-targeted variations, such as air turbidity and light condition changes, as well as targeted object changes in industrial indoor environments. [\u003ca href=\"https://github.com/SAMMiCA/ChangeSim\" target=\"_blank\"\u003eDownload\u003c/a\u003e]\n        \u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd colspan=\"2\"\u003e \u003ca href=\"https://github.com/MinZHANG-WHU/Change-Detection-Review/blob/master/Video%20datasets.png\" target=\"_blank\"\u003e More video datasets\u003c/a\u003e \u003c/td\u003e\n\t\u003c/tr\u003e\n\u003c/table\u003e\n\n\nIt can be seen that the amount of open datasets that can be used for change detection tasks is small, and some of them have small data sizes. At present, there is still a lack of large SAR datasets that can be used for AI training. Most AI-based change detection methods are based on several SAR data sets that contain limited types of changes, e.g., the Bern dataset, the Ottawa dataset, the Yellow River dataset, and the Mexico dataset, which cannot meet the needs of change detection in areas with complex land cover and various change types. Moreover, their labels are not freely available. Street-view datasets are generally used for research of AI-based change detection methods in computer vision (CV). In CV, change detection based on pictures or video is also a hot research field, and the basic idea is consistent with that based on RS data. Therefore, in addition to street view image datasets, several video datasets in CV can also be used for research on AI-based change detection methods, such as CDNet 2012 and CDNet 2014. \n\n## 4. Applications\nThe development of AI-based change detection techniques has greatly facilitated many applications and has improved their automation and intelligence. Most AI-based change detection generates binary maps, and these studies only focus on the algorithm itself, without a specific application field. Therefore, it can be considered that they are generally suitable for LULC change detection. In this section, we focus on the techniques that are associated with specific applications, and they can be broadly divided into four categories:\n* **Urban contexts**: urban expansion, public space management, and building change detection;\n* **Resources and environment**: human-driven environmental changes, hydro-environmental changes, sea ice, surface water, and forest monitoring;\n* **Natural disasters**: landslide mapping and damage assessment;\n* **Astronomy**: planetary surfaces.\n\nWe provide an overview of the various change detection techniques in the literature for the different application categories. The works and data types associated with these applications are listed in Table 4.\n\n\n\u003ctable\u003e\n\u003ccaption\u003eTable 4. Summary of main applications of AI-based change detection techniques.\u003c/caption\u003e\n\t\u003ctr\u003e\n\t    \u003cth colspan=\"2\"\u003eApplications\u003c/th\u003e\n\t    \u003cth\u003eData Types\u003c/th\u003e\n\t    \u003cth\u003ePapers\u003c/th\u003e  \n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd rowspan=\"10\"\u003eUrban contexts\u003c/td\u003e\n\t    \u003ctd rowspan=\"2\"\u003eUrban expansion\u003c/td\u003e\n\t    \u003ctd\u003eSatellite images  \u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://dx.doi.org/10.3390/rs10030471\" target=\"_blank\"\u003eLyu et.al (2018)\u003c/a\u003e, \u003ca href=\"https://dx.doi.org/10.1080/01431160903475290\" target=\"_blank\"\u003eTong et.al (2007)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eSAR images  \u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Generating+high-accuracy+urban+distribution+map+for+short-term+change+monitoring+based+on+convolutional+neural+network+by+utilizing+SAR+imagery\u0026author=Iino,+S.\u0026author=Ito,+R.\u0026author=Doi,+K.\u0026author=Imaizumi,+T.\u0026author=Hikosaka,+S.\u0026publication_year=2017\" target=\"_blank\"\u003eIino et.al (2017)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t    \u003ctd\u003ePublic space management\u003c/td\u003e\n\t    \u003ctd\u003eStreet view images\u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://scholar.google.com/scholar_lookup?title=ChangeNet:+A+deep+learning+architecture+for+visual+change+detection\u0026conference=Proceedings+of+the+European+Conference+on+Computer+Vision+(ECCV)\u0026author=Varghese,+A.\u0026author=Gubbi,+J.\u0026author=Ramaswamy,+A.\u0026author=Balamuralidhar,+P.\u0026publication_year=2018\u0026pages=129%E2%80%93145\" target=\"_blank\"\u003eVarghese et.al (2018)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eRoad surface\u003c/td\u003e\n\t    \u003ctd\u003eUAV images\u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://doi.org/10.3390/su12062482\" target=\"_blank\"\u003eTruong et.al (2020)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd rowspan=\"6\"\u003eBuilding change detection\u003c/td\u003e\n\t    \u003ctd\u003eAerial images\u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://dx.doi.org/10.3390/rs11111343\" target=\"_blank\"\u003eJi et.al (2019)\u003c/a\u003e, \u003ca href=\"https://scholar.google.com/scholar_lookup?title=A+deep+learning+approach+to+detecting+changes+in+buildings+from+aerial+images\u0026conference=Proceedings+of+the+International+Symposium+on+Neural+Networks\u0026author=Sun,+B.\u0026author=Li,+G.-Z.\u0026author=Han,+M.\u0026author=Lin,+Q.-H.\u0026publication_year=2019\u0026pages=414%E2%80%93421\" target=\"_blank\"\u003eSun et.al (2019)\u003c/a\u003e, \u003ca href=\"https://dx.doi.org/10.1117/12.2277912\" target=\"_blank\"\u003eNemoto et.al (2017)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eSatellite images\u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://dx.doi.org/10.1016/j.jvcir.2019.102585\" target=\"_blank\"\u003eHuang et.al (2019)\u003c/a\u003e, \u003ca href=\"https://scholar.google.com/scholar_lookup?title=Change+Detection+Based+on+the+Combination+of+Improved+SegNet+Neural+Network+and+Morphology\u0026conference=Proceedings+of+the+2018+IEEE+3rd+International+Conference+on+Image,+Vision+and+Computing+(ICIVC)\u0026author=Zhu,+B.\u0026author=Gao,+H.\u0026author=Wang,+X.\u0026author=Xu,+M.\u0026author=Zhu,+X.\u0026publication_year=2018\u0026pages=55%E2%80%9359\" target=\"_blank\"\u003eZhu et.al (2018)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eSatellite/Aerial images\u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://dx.doi.org/10.3390/rs12030484\" target=\"_blank\"\u003eJiang  et.al (2020)\u003c/a\u003e, \u003ca href=\"https://dx.doi.org/10.1109/TGRS.2018.2858817\" target=\"_blank\"\u003eJi et.al (2018)\u003c/a\u003e, \u003ca href=\"https://dx.doi.org/10.1109/TGRS.2020.3000296\" target=\"_blank\"\u003eSaha et.al (2020)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eAirborne laser scanning data and aerial images \u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://dx.doi.org/10.3390/rs11202417\" target=\"_blank\"\u003eZhang et.al (2019)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eSAR images \u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://dx.doi.org/10.3390/rs11121444\" target=\"_blank\"\u003eJaturapitpornchai et.al (2019)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eSatellite images and GIS map\u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://dx.doi.org/10.3390/rs11202427\" target=\"_blank\"\u003eGhaffarian et.al (2019)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd rowspan=\"5\"\u003eResources \u0026 environment \u003c/td\u003e\n\t    \u003ctd\u003eHuman-driven environmental changes\u003c/td\u003e\n\t    \u003ctd\u003eSatellite images  \u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://dx.doi.org/10.1117/1.JRS.10.016021\" target=\"_blank\"\u003eChen et.al (2016)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eHydro-environmental changes\u003c/td\u003e\n\t    \u003ctd\u003eSatellite images\u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://dx.doi.org/10.1016/j.jhydrol.2018.05.018\" target=\"_blank\"\u003eNourani et.al (2018)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n     \u003ctr\u003e\n\t    \u003ctd\u003eSea ice\u003c/td\u003e\n\t    \u003ctd\u003eSAR images\u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://dx.doi.org/10.1109/LGRS.2019.2906279\" target=\"_blank\"\u003eGao et.al (2019)\u003c/a\u003e, \u003ca href=\"https://dx.doi.org/10.1109/LGRS.2019.2895656\" target=\"_blank\"\u003eGao et.al (2019)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eSurface water\u003c/td\u003e\n\t    \u003ctd\u003eSatellite images\u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://dx.doi.org/10.2112/SI91-086.1\" target=\"_blank\"\u003eSong et.al (2019)\u003c/a\u003e, \u003ca href=\"https://dx.doi.org/10.1016/j.jag.2014.08.014\" target=\"_blank\"\u003eRokni et.al (2015)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eForest monitoring\u003c/td\u003e\n\t    \u003ctd\u003eSatellite images\u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://dx.doi.org/10.1109/TGRS.2017.2707528\" target=\"_blank\"\u003eKhan et.al (2017)\u003c/a\u003e, \u003ca href=\"https://dx.doi.org/10.3390/rs8080678\" target=\"_blank\"\u003eLindquist et.al (2016)\u003c/a\u003e, \u003ca href=\"https://scholar.google.com/scholar_lookup?title=Comparison+of+pixel+-based+and+artificial+neural+networks+classification+methods+for+detecting+forest+cover+changes+in+Malaysia\u0026conference=Proceedings+of+the+8th+International+Symposium+of+the+Digital+Earth,+Univ+Teknologi+Malaysia,+Inst+Geospatial+Sci+\u0026+Technol\u0026author=Deilmai,+B.R.\u0026author=Kanniah,+K.D.\u0026author=Rasib,+A.W.\u0026author=Ariffin,+A.\u0026publication_year=2014\" target=\"_blank\"\u003eDeilmai et.al (2014)\u003c/a\u003e, \u003ca href=\"https://dx.doi.org/10.1016/S0034-4257(01)00259-0\" target=\"_blank\"\u003eWoodcock et.al (2001)\u003c/a\u003e, \u003ca href=\"https://dx.doi.org/10.1109/36.485117\" target=\"_blank\"\u003eGopal et.al (1996)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd rowspan=\"7\"\u003eNatural disasters\u003c/td\u003e\n\t    \u003ctd rowspan=\"2\"\u003eLandslide mapping\u003c/td\u003e\n\t    \u003ctd\u003eAerial images\u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://dx.doi.org/10.1109/LGRS.2020.2979693\" target=\"_blank\"\u003eFang et.al (2020)\u003c/a\u003e, \u003ca href=\"https://dx.doi.org/10.1109/LGRS.2018.2889307\" target=\"_blank\"\u003eLei et.al (2019)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eSatellite images\u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://dx.doi.org/10.3390/s18030821\" target=\"_blank\"\u003eChen et.al (2018)\u003c/a\u003e, \u003ca href=\"https://scholar.google.com/scholar_lookup?title=Automatic+Recognition+of+Landslide+Based+on+CNN+and+Texture+Change+Detection\u0026conference=Proceedings+of+the+2016+31st+Youth+Academic+Annual+Conference+of+Chinese-Association-of-Automation+(YAC)\u0026author=Ding,+A.\u0026author=Zhang,+Q.\u0026author=Zhou,+X.\u0026author=Dai,+B.\u0026publication_year=2016\u0026pages=444%E2%80%93448\" target=\"_blank\"\u003eDing et.al (2016)\u003c/a\u003e, \u003ca href=\"https://dx.doi.org/10.1007/s11069-006-9041-x\" target=\"_blank\"\u003eTarantino et.al (2006)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd rowspan=\"5\"\u003eDamage assessment \u003c/td\u003e\n\t    \u003ctd\u003eSatellite images\u003c/td\u003e\n        \u003ctd\u003ecaused by tsunami [\u003ca href=\"https://dx.doi.org/10.3390/rs11091123\" target=\"_blank\"\u003eSublime et.al (2019)\u003c/a\u003e,\u003ca href=\"https://dx.doi.org/10.1007/s11069-015-1595-z\" target=\"_blank\"\u003eSingh et.al (2015)\u003c/a\u003e], particular incident [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Change+detection+from+unlabeled+remote+sensing+images+using+siamese+ANN\u0026conference=Proceedings+of+the+IGARSS+2019%E2%80%942019+IEEE+International+Geoscience+and+Remote+Sensing+Symposium\u0026author=Hedjam,+R.\u0026author=Abdesselam,+A.\u0026author=Melgani,+F.\u0026publication_year=2019\u0026pages=1530%E2%80%931533\" target=\"_blank\"\u003eHedjam et.al (2019)\u003c/a\u003e], flood [\u003ca href=\"https://dx.doi.org/10.3390/rs11212492\" target=\"_blank\"\u003ePeng et.al (2019)\u003c/a\u003e], or earthquake [\u003ca href=\"https://dx.doi.org/10.3390/rs11101202\" target=\"_blank\"\u003eJi et.al (2019)\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eAerial images\u003c/td\u003e\n        \u003ctd\u003ecaused by tsunami [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Damage+detection+from+aerial+images+via+convolutional+neural+networks\u0026conference=Proceedings+of+the+2017+Fifteenth+IAPR+International+Conference+on+Machine+Vision+Applications+(MVA),+Nagoya+Univ\u0026author=Fujita,+A.\u0026author=Sakurada,+K.\u0026author=Imaizumi,+T.\u0026author=Ito,+R.\u0026author=Hikosaka,+S.\u0026author=Nakamura,+R.\u0026publication_year=2017\u0026pages=5%E2%80%938\" target=\"_blank\"\u003eFujita et.al (2017)\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eSAR images\u003c/td\u003e\n        \u003ctd\u003ecaused by fires  [\u003ca href=\"https://dx.doi.org/10.1109/LGRS.2017.2786344\" target=\"_blank\"\u003ePlaninšič et.al (2018)\u003c/a\u003e], or earthquake [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Destroyed-buildings+detection+from+VHR+SAR+images+using+deep+features\u0026author=Saha,+S.\u0026author=Bovolo,+F.\u0026author=Bruzzone,+L.\u0026publication_year=2018\" target=\"_blank\"\u003eSaha et.al (2018)\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eStreet view images \u003c/td\u003e\n        \u003ctd\u003ecaused by tsunami [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Change+detection+from+a+street+image+pair+using+CNN+features+and+superpixel+segmentation\u0026conference=Proceedings+of+the+British+Machine+Vision+Conference+(BMVC)\u0026author=Sakurada,+K.\u0026author=Okatani,+T.\u0026publication_year=2015\u0026pages=61.1%E2%80%9361.12\" target=\"_blank\"\u003eSakurada et.al (2015)\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eStreet view images and GIS map \u003c/td\u003e\n        \u003ctd\u003ecaused by tsunami [\u003ca href=\"https://dx.doi.org/10.1016/j.cviu.2017.01.012\" target=\"_blank\"\u003eSakurada et.al (2017)\u003c/a\u003e]\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n\t    \u003ctd\u003eAstronomy\u003c/td\u003e\n\t    \u003ctd\u003ePlanetary surfaces\u003c/td\u003e\n\t    \u003ctd\u003eSatellite images\u003c/td\u003e\n        \u003ctd\u003e\u003ca href=\"https://dx.doi.org/10.1109/JSTARS.2019.2936771\" target=\"_blank\"\u003eKerner et.al (2019)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\u003c/table\u003e\n\n## 5. Software programs\nThere are currently a large number of software with change detection tools, and we have a brief summary of them, see table 5.\n\u003ctable\u003e\n\u003ccaption\u003eTable 5. A list of software for change detection.\u003c/caption\u003e\n\t\u003ctr\u003e\n\t    \u003cth\u003eType\u003c/th\u003e\n\t    \u003cth\u003eName\u003c/th\u003e\n        \u003cth\u003eDescription\u003c/th\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n    \u003ctd rowspan=\"6\"\u003eCommercial\u003c/td\u003e\n    \u003ctd\u003eERDAS IMAGINE\u003c/td\u003e\n    \u003ctd\u003eprovides true value, consolidating remote sensing, photogrammetry, LiDAR analysis, basic vector analysis, and radar processing into a single product, including a variety of \u003ca href=\"https://www.hexagongeospatial.com/products/power-portfolio/erdas-imagine/erdas-imagine-remote-sensing-software-package\" target=\"_blank\"\u003echange detection tools\u003c/a\u003e.\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n    \u003ctd\u003eArcGIS\u003c/td\u003e\n    \u003ctd\u003e change detection can be calculate between two raster datasets by using the \u003ca href=\"https://support.esri.com/en/technical-article/000001209\" target=\"_blank\"\u003eraster calculator tool\u003c/a\u003e or \u003ca href=\"https://pro.arcgis.com/en/pro-app/help/analysis/image-analyst/deep-learning-in-arcgis-pro.htm\" target=\"_blank\"\u003edeep learning workflow\u003c/a\u003e. \u003c/td\u003e\n    \u003c/tr\u003e\n     \u003ctr\u003e\n    \u003ctd\u003eENVI\u003c/td\u003e\n    \u003ctd\u003eprovides \u003ca href=\"https://www.harrisgeospatial.com/docs/ChangeDetectionAnalysis.html\" target=\"_blank\"\u003echange detection analysis tools\u003c/a\u003e and the \u003ca href=\"https://www.harrisgeospatial.com/Software-Technology/ENVI-Deep-Learning\" target=\"_blank\"\u003e ENVI deep learning module\u003c/a\u003e.\u003c/td\u003e\n    \u003c/tr\u003e\n     \u003ctr\u003e\n    \u003ctd\u003eeCognition\u003c/td\u003e\n    \u003ctd\u003ecan be used for \u003ca href=\"https://geospatial.trimble.com/products-and-solutions/ecog-essentials-support-cases\" target=\"_blank\"\u003ea variety of change mapping\u003c/a\u003e, and by leveraging deep learning technology from the Google TensorFlow™ library, eCognition empowers customers with highly sophisticated pattern recognition and correlation tools that automate the classification of objects of interest for faster and more accurate results,\u003ca href=\"https://geospatial.trimble.com/ecognition-whats-new\" target=\"_blank\"\u003e more\u003c/a\u003e.\u003c/td\u003e\n    \u003c/tr\u003e\n     \u003ctr\u003e\n    \u003ctd\u003ePCI Geomatica\u003c/td\u003e\n    \u003ctd\u003e provides \u003ca href=\"https://support.pcigeomatics.com/hc/en-us/articles/203483499-Change-Detection-Optical\" target=\"_blank\"\u003echange detection tools\u003c/a\u003e, and can be useful in numerous circumstances in which you may want to analyze change, such as: storm damage, forest-fire damage, flooding, urban sprawl, and \u003ca href=\"https://support.pcigeomatics.com/hc/en-us/articles/203483499-Change-Detection-Optical\" target=\"_blank\"\u003emore\u003c/a\u003e.\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n    \u003ctd\u003eSenseTime\u003c/td\u003e\n    \u003ctd\u003e \u003ca href=\"https://www.sensetime.com/en/Service/RemoteSensing.html#product\" target=\"_blank\"\u003eSenseRemote remote sensing intelligent solutions\u003c/a\u003e\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n    \u003ctd rowspan=\"3\"\u003eOpen source\u003c/td\u003e\n    \u003ctd\u003eQGIS\u003c/td\u003e\n    \u003ctd\u003eprovides many \u003ca href=\"https://plugins.qgis.org/plugins/tags/change-detection/\" target=\"_blank\"\u003echange detection tools\u003c/a\u003e.\u003c/td\u003e\n    \u003c/tr\u003e\n     \u003ctr\u003e\n    \u003ctd\u003eOrfeo ToolBox\u003c/td\u003e\n    \u003ctd\u003echange detection by \u003ca href=\"https://www.orfeo-toolbox.org/CookBook/Applications/Change_Detection.html\" target=\"_blank\"\u003emultivariate alteration detector (MAD) algorithm\u003c/a\u003e.\u003c/td\u003e\n    \u003c/tr\u003e\n   \u003ctr\u003e\n    \u003ctd\u003eChange Detection ToolBox\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"https://github.com/Bobholamovic/ChangeDetectionToolbox\" target=\"_blank\"\u003eMATLAB toolbox for remote sensing change detection\u003c/a\u003e.\u003c/td\u003e\n    \u003c/tr\u003e\n\u003ctable\u003e\n\n## 6. Review papers for change detection\nThe following papers are helpful for researchers to better understand this  field of remote sensing change detection, see table 6.\n\u003ctable\u003e\n\u003ccaption\u003eTable 6. A list of review papers on change detection.\u003c/caption\u003e\n\t\u003ctr\u003e\n\t    \u003cth\u003ePublished year\u003c/th\u003e\n\t    \u003cth\u003eReview paper\u003c/th\u003e\n\t\u003c/tr\u003e\n    \u003ctr\u003e\n    \u003ctd\u003e1989\u003c/td\u003e\n    \u003ctd\u003eDigital change detection techniques using remotely sensed data, IJRS. [\u003ca href=\"https://dx.doi.org/10.1080/01431168908903939\" target=\"_blank\"\u003epaper\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n\t \u003ctr\u003e\n    \u003ctd\u003e2004\u003c/td\u003e\n    \u003ctd\u003eDigital change detection methods in ecosystem monitoring: a review, IJRS. [\u003ca href=\"https://dx.doi.org/10.1080/0143116031000101675\" target=\"_blank\"\u003epaper\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n\t \u003ctr\u003e\n\t \u003ctd\u003e2004\u003c/td\u003e\n    \u003ctd\u003eChange detection techniques, IJRS. [\u003ca href=\"https://dx.doi.org/10.1080/0143116031000139863\" target=\"_blank\"\u003epaper\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n\t \u003ctr\u003e\n\t\u003ctd\u003e2012\u003c/td\u003e\n    \u003ctd\u003eObject-based change detection, IJRS. [\u003ca href=\"https://dx.doi.org/10.1080/01431161.2011.648285\" target=\"_blank\"\u003epaper\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n\t \u003ctr\u003e\n\t \u003ctd\u003e2013\u003c/td\u003e\n    \u003ctd\u003eChange detection from remotely sensed images: From pixel-based to object-based approaches, ISPRS. [\u003ca href=\"https://doi.org/10.1016/j.isprsjprs.2013.03.006\" target=\"_blank\"\u003epaper\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n\t\u003ctr\u003e\n\t \u003ctd\u003e2016\u003c/td\u003e\n    \u003ctd\u003e3D change detection–approaches and applications, ISPRS. [\u003ca href=\"https://doi.org/10.1016/j.isprsjprs.2016.09.013\" target=\"_blank\"\u003epaper\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n\t\u003ctr\u003e\n\t \u003ctd\u003e2016\u003c/td\u003e\n    \u003ctd\u003eDeep learning for remote sensing data a technical tutorial on the state of the art, MGRS. [\u003ca href=\"https://dx.doi.org/10.1109/MGRS.2016.2540798\" target=\"_blank\"\u003epaper\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n\t\u003ctr\u003e\n\t \u003ctd\u003e2017\u003c/td\u003e\n    \u003ctd\u003eComprehensive survey of deep learning in remote sensing: theories, tools, and challenges for the community, JRS. [\u003ca href=\"https://doi.org/10.1117/1.JRS.11.042609\" target=\"_blank\"\u003epaper\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n\t\u003ctr\u003e\n\t \u003ctd\u003e2017\u003c/td\u003e\n    \u003ctd\u003eDeep Learning in Remote Sensing, MGRS. [\u003ca href=\"https://dx.doi.org/10.1109/MGRS.2017.2762307\" target=\"_blank\"\u003epaper\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n\t\u003ctr\u003e\n\t \u003ctd\u003e2018\u003c/td\u003e\n    \u003ctd\u003eComputational intelligence in optical remote sensing image processing, ASOC. [\u003ca href=\"https://doi.org/10.1016/j.asoc.2017.11.045\" target=\"_blank\"\u003epaper\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n\t\u003ctr\u003e\n\t \u003ctd\u003e2019\u003c/td\u003e\n    \u003ctd\u003eA review of change detection in multitemporal hyperspectral images: current techniques, applications, and challenges, MGRS. [\u003ca href=\"https://dx.doi.org/10.1109/MGRS.2019.2898520\" target=\"_blank\"\u003epaper\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n\t\u003ctr\u003e\n\t \u003ctd\u003e2019\u003c/td\u003e\n    \u003ctd\u003eDeep learning in remote sensing applications: A meta-analysis and review, ISPRS. [\u003ca href=\"https://doi.org/10.1016/j.isprsjprs.2019.04.015\" target=\"_blank\"\u003epaper\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n\t\u003ctr\u003e\n\t \u003ctd\u003e2020\u003c/td\u003e\n    \u003ctd\u003eDeep Learning for change detection in remote sensing images: comprehensive review and meta-analysis, arXiv. [\u003ca href=\"https://arxiv.org/abs/2006.05612\" target=\"_blank\"\u003epaper\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n\t\u003ctr\u003e\n\t \u003ctd\u003e2020\u003c/td\u003e\n    \u003ctd\u003eChange detection based on artificial intelligence: state-of-the-art and challenges, RS. [\u003ca href=\"https://doi.org/10.3390/rs12101688\" target=\"_blank\"\u003epaper\u003c/a\u003e]\u003c/td\u003e\n    \u003c/tr\u003e\n\u003ctable\u003e\n\n## 7. Reference\n\u003cspan id=\"Ref-1\"\u003e[1] Hyperspectral Change Detection Dataset. Available online: https://citius.usc.es/investigacion/datasets/hyperspectral-change-detection-dataset (accessed on 4 May 2020).\u003c/span\u003e\n\n\u003cspan id=\"Ref-2\"\u003e[2] Wang, Q.; Yuan, Z.; Du, Q.; Li, X. GETNET: A General End-to-End 2-D CNN Framework for Hyperspectral Image Change Detection. IEEE Trans. Geosci. Remote Sens. 2018, 57, 3–13. [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=GETNET:+A+General+End-to-End+2-D+CNN+Framework+for+Hyperspectral+Image+Change+Detection\u0026author=Wang,+Q.\u0026author=Yuan,+Z.\u0026author=Du,+Q.\u0026author=Li,+X.\u0026publication_year=2018\u0026journal=IEEE+Trans.+Geosci.+Remote+Sens.\u0026volume=57\u0026pages=3%E2%80%9313\u0026doi=10.1109/TGRS.2018.2849692\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e] [\u003ca href=\"https://ieeexplore.ieee.org/document/8418840/\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e]\u003c/span\u003e\n\n\u003cspan id=\"Ref-3\"\u003e[3] Daudt, R.C.; Le Saux, B.; Boulch, A.; Gousseau, Y. Multitask learning for large-scale semantic change detection. Comput. Vis. Image Underst. 2019, 187, 102783. [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Multitask+learning+for+large-scale+semantic+change+detection\u0026author=Daudt,+R.C.\u0026author=Le+Saux,+B.\u0026author=Boulch,+A.\u0026author=Gousseau,+Y.\u0026publication_year=2019\u0026journal=Comput.+Vis.+Image+Underst.\u0026volume=187\u0026pages=102783\u0026doi=10.1016/j.cviu.2019.07.003\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e] [\u003ca href=\"https://dx.doi.org/10.1016/j.cviu.2019.07.003\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e]\u003c/span\u003e\n\n\u003cspan id=\"Ref-4\"\u003e[4] Ji, S.; Wei, S.; Lu, M. Fully Convolutional Networks for Multisource Building Extraction from an Open Aerial and Satellite Imagery Data Set. IEEE Trans. Geosci. Remote Sens. 2018, 57, 574–586. [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Fully+Convolutional+Networks+for+Multisource+Building+Extraction+from+an+Open+Aerial+and+Satellite+Imagery+Data+Set\u0026author=Ji,+S.\u0026author=Wei,+S.\u0026author=Lu,+M.\u0026publication_year=2018\u0026journal=IEEE+Trans.+Geosci.+Remote+Sens.\u0026volume=57\u0026pages=574%E2%80%93586\u0026doi=10.1109/TGRS.2018.2858817\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e] [\u003ca href=\"https://dx.doi.org/10.1109/TGRS.2018.2858817\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e]\u003c/span\u003e\n\n\u003cspan id=\"Ref-5\"\u003e[5] Benedek, C.; Sziranyi, T. Change Detection in Optical Aerial Images by a Multilayer Conditional Mixed Markov Model. IEEE Trans. Geosci. Remote Sens. 2009, 47, 3416–3430. [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Change+Detection+in+Optical+Aerial+Images+by+a+Multilayer+Conditional+Mixed+Markov+Model\u0026author=Benedek,+C.\u0026author=Sziranyi,+T.\u0026publication_year=2009\u0026journal=IEEE+Trans.+Geosci.+Remote+Sens.\u0026volume=47\u0026pages=3416%E2%80%933430\u0026doi=10.1109/TGRS.2009.2022633\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e] [\u003ca href=\"https://dx.doi.org/10.1109/TGRS.2009.2022633\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e]\u003c/span\u003e\n\n\u003cspan id=\"Ref-6\"\u003e[6] Benedek, C.; Sziranyi, T. A Mixed Markov model for change detection in aerial photos with large time differences. In Proceedings of the 2008 19th International Conference on Pattern Recognition, Tampa, FL, USA, 8–11 December 2008; pp. 1–4. [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=A+Mixed+Markov+model+for+change+detection+in+aerial+photos+with+large+time+differences\u0026conference=Proceedings+of+the+2008+19th+International+Conference+on+Pattern+Recognition\u0026author=Benedek,+C.\u0026author=Sziranyi,+T.\u0026publication_year=2008\u0026pages=1%E2%80%934\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e] \u003c/span\u003e\n\n\u003cspan id=\"Ref-7\"\u003e[7] Daudt, R.C.; Le Saux, B.; Boulch, A.; Gousseau, Y. Urban change detection for multispectral earth observation using convolutional neural networks. In Proceedings of the IGARSS 2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain, 22–27 July 2018; pp. 2115–2118. [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Urban+change+detection+for+multispectral+earth+observation+using+convolutional+neural+networks\u0026conference=Proceedings+of+the+IGARSS+2018+IEEE+International+Geoscience+and+Remote+Sensing+Symposium\u0026author=Daudt,+R.C.\u0026author=Le+Saux,+B.\u0026author=Boulch,+A.\u0026author=Gousseau,+Y.\u0026publication_year=2018\u0026pages=2115%E2%80%932118\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e]\u003c/span\u003e\n\n\u003cspan id=\"Ref-8\"\u003e[8] Zhang, M.; Shi, W. A Feature Difference Convolutional Neural Network-Based Change Detection Method. IEEE Trans. Geosci. Remote Sens. 2020, 1–15.  [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=A+Feature+Difference+Convolutional+Neural+Network-Based+Change+Detection+Method\u0026author=Zhang,+M.\u0026author=Shi,+W.\u0026publication_year=2020\u0026journal=IEEE+Trans.+Geosci.+Remote+Sens.\u0026pages=1%E2%80%9315\u0026doi=10.1109/tgrs.2020.2981051\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e] [\u003ca href=\"https://dx.doi.org/10.1109/tgrs.2020.2981051\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e]\u003c/span\u003e\n\n\u003cspan id=\"Ref-9\"\u003e[9] Wu, C.; Zhang, L.; Zhang, L. A scene change detection framework for multi-temporal very high resolution remote sensing images. Signal Process. 2016, 124, 184–197. [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=A+scene+change+detection+framework+for+multi-temporal+very+high+resolution+remote+sensing+images\u0026author=Wu,+C.\u0026author=Zhang,+L.\u0026author=Zhang,+L.\u0026publication_year=2016\u0026journal=Signal+Process.\u0026volume=124\u0026pages=184%E2%80%93197\u0026doi=10.1016/j.sigpro.2015.09.020\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e] [\u003ca href=\"https://dx.doi.org/10.1016/j.sigpro.2015.09.020\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e]\u003c/span\u003e\n\n\u003cspan id=\"Ref-10\"\u003e[10] Fujita, A.; Sakurada, K.; Imaizumi, T.; Ito, R.; Hikosaka, S.; Nakamura, R. Damage detection from aerial images via convolutional neural networks. In Proceedings of the 2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA), Nagoya Univ, Nagoya, Japan, 08–12 May 2017; pp. 5–8 [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Damage+detection+from+aerial+images+via+convolutional+neural+networks\u0026conference=Proceedings+of+the+2017+Fifteenth+IAPR+International+Conference+on+Machine+Vision+Applications+(MVA),+Nagoya+Univ\u0026author=Fujita,+A.\u0026author=Sakurada,+K.\u0026author=Imaizumi,+T.\u0026author=Ito,+R.\u0026author=Hikosaka,+S.\u0026author=Nakamura,+R.\u0026publication_year=2017\u0026pages=5%E2%80%938\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e] \u003c/span\u003e\n\n\u003cspan id=\"Ref-11\"\u003e[11] Gupta, R.; Goodman, B.; Patel, N.; Hosfelt, R.; Sajeev, S.; Heim, E.; Doshi, J.; Lucas, K.; Choset, H.; Gaston, M. Creating xBD: A dataset for assessing building damage from satellite imagery. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA, 16–20 June 2019; pp. 10–17. [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Creating+xBD:+A+dataset+for+assessing+building+damage+from+satellite+imagery\u0026conference=Proceedings+of+the+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition+Workshops\u0026author=Gupta,+R.\u0026author=Goodman,+B.\u0026author=Patel,+N.\u0026author=Hosfelt,+R.\u0026author=Sajeev,+S.\u0026author=Heim,+E.\u0026author=Doshi,+J.\u0026author=Lucas,+K.\u0026author=Choset,+H.\u0026author=Gaston,+M.\u0026publication_year=2019\u0026pages=10%E2%80%9317\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e]\u003c/span\u003e\n\n\u003cspan id=\"Ref-12\"\u003e[12] Bourdis, N.; Marraud, D.; Sahbi, H. Constrained optical flow for aerial image change detection. In Proceedings of the 2011 IEEE International Geoscience and Remote Sensing Symposium, Vancouver, BC, Canada, 24–29 July 2011; pp. 4176–4179. [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Constrained+optical+flow+for+aerial+image+change+detection\u0026conference=Proceedings+of+the+2011+IEEE+International+Geoscience+and+Remote+Sensing+Symposium\u0026author=Bourdis,+N.\u0026author=Marraud,+D.\u0026author=Sahbi,+H.\u0026publication_year=2011\u0026pages=4176%E2%80%934179\u0026doi=10.1109/igarss.2011.6050150\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e] [\u003ca href=\"https://dx.doi.org/10.1109/igarss.2011.6050150\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e]\u003c/span\u003e\n\n\u003cspan id=\"Ref-13\"\u003e[13] Lebedev, M.A.; Vizilter, Y.V.; Vygolov, O.V.; Knyaz, V.A.; Rubis, A.Y. Change detection in remote sensing images using conditional adversarial networks. ISPRS Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2018, 565–571. [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Change+detection+in+remote+sensing+images+using+conditional+adversarial+networks\u0026author=Lebedev,+M.A.\u0026author=Vizilter,+Y.V.\u0026author=Vygolov,+O.V.\u0026author=Knyaz,+V.A.\u0026author=Rubis,+A.Y.\u0026publication_year=2018\u0026journal=ISPRS+Int.+Arch.+Photogramm.+Remote+Sens.+Spat.+Inf.+Sci.\u0026pages=565%E2%80%93571\u0026doi=10.5194/isprs-archives-XLII-2-565-2018\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e] [\u003ca href=\"https://dx.doi.org/10.5194/isprs-archives-XLII-2-565-2018\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e]\u003c/span\u003e\n\n\u003cspan id=\"Ref-14\"\u003e[14] Chen, H.; Shi, Z. A Spatial-Temporal Attention-Based Method and a New Dataset for Remote Sensing Image Change Detection. Remote Sensing, 12(10), 1662. [\u003ca href=\"https://scholar.google.co.jp/scholar?q=A+Spatial-Temporal+Attention-Based+Method+and+a+New+Dataset+for+Remote+Sensing+Image+Change+Detection\u0026hl=zh-TW\u0026as_sdt=0\u0026as_vis=1\u0026oi=scholart\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e] [\u003ca href=\"https://doi.org/10.3390/rs12101662\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e]\u003c/span\u003e\n\n\u003cspan id=\"Ref-15\"\u003e[15] Alcantarilla, P.F.; Stent, S.; Ros, G.; Arroyo, R.; Gherardi, R. Street-view change detection with deconvolutional networks. Auton. Robot. 2018, 42, 1301–1322. [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Street-view+change+detection+with+deconvolutional+networks\u0026author=Alcantarilla,+P.F.\u0026author=Stent,+S.\u0026author=Ros,+G.\u0026author=Arroyo,+R.\u0026author=Gherardi,+R.\u0026publication_year=2018\u0026journal=Auton.+Robot.\u0026volume=42\u0026pages=1301%E2%80%931322\u0026doi=10.1007/s10514-018-9734-5\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e] [\u003ca href=\"https://dx.doi.org/10.1007/s10514-018-9734-5\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e]\u003c/span\u003e\n\n\u003cspan id=\"Ref-16\"\u003e[16] Sakurada, K.; Okatani, T. Change detection from a street image pair using CNN features and superpixel segmentation. In Proceedings of the British Machine Vision Conference (BMVC), Swansea, UK, 7–10 September 2015; pp. 61.1–61.12. [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Change+detection+from+a+street+image+pair+using+CNN+features+and+superpixel+segmentation\u0026conference=Proceedings+of+the+British+Machine+Vision+Conference+(BMVC)\u0026author=Sakurada,+K.\u0026author=Okatani,+T.\u0026publication_year=2015\u0026pages=61.1%E2%80%9361.12\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e] \u003c/span\u003e\n\n\u003cspan id=\"Ref-17\"\u003e[17] Sakurada, K.; Okatani, T.; Deguchi, K. Detecting changes in 3D structure of a scene from multi-view images captured by a vehicle-mounted camera. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA, 23–28 June 2013; pp. 137–144. [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Detecting+changes+in+3D+structure+of+a+scene+from+multi-view+images+captured+by+a+vehicle-mounted+camera\u0026conference=Proceedings+of+the+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition\u0026author=Sakurada,+K.\u0026author=Okatani,+T.\u0026author=Deguchi,+K.\u0026publication_year=2013\u0026pages=137%E2%80%93144\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e]\u003c/span\u003e\n\n\u003cspan id=\"Ref-18\"\u003e[18] Goyette, N.; Jodoin, P.-M.; Porikli, F.; Konrad, J.; Ishwar, P. Changedetection. net: A new change detection benchmark dataset. In Proceedings of the 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Providence, RI, USA, 16–21 June 2012; pp. 1–8. [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=Changedetection.+net:+A+new+change+detection+benchmark+dataset\u0026conference=Proceedings+of+the+2012+IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition+Workshops\u0026author=Goyette,+N.\u0026author=Jodoin,+P.-M.\u0026author=Porikli,+F.\u0026author=Konrad,+J.\u0026author=Ishwar,+P.\u0026publication_year=2012\u0026pages=1%E2%80%938\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e] \u003c/span\u003e\n\n\u003cspan id=\"Ref-19\"\u003e[19] Wang, Y.; Jodoin, P.-M.; Porikli, F.; Konrad, J.; Benezeth, Y.; Ishwar, P. CDnet 2014: An Expanded Change Detection Benchmark Dataset. In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Columbus, OH, USA, 23–28 June 2014; pp. 393–400.  [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=CDnet+2014:+An+Expanded+Change+Detection+Benchmark+Dataset\u0026conference=Proceedings+of+the+2014+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition+Workshops\u0026author=Wang,+Y.\u0026author=Jodoin,+P.-M.\u0026author=Porikli,+F.\u0026author=Konrad,+J.\u0026author=Benezeth,+Y.\u0026author=Ishwar,+P.\u0026publication_year=2014\u0026pages=393%E2%80%93400\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e] \u003c/span\u003e\n\n\u003cspan id=\"Ref-20\"\u003e[20] Goyette, N.; Jodoin, P.-M.; Porikli, F.; Konrad, J.; Ishwar, P. A Novel Video Dataset for Change Detection Benchmarking. IEEE Trans. Image Process. 2014, 23, 4663–4679. [\u003ca href=\"https://scholar.google.com/scholar_lookup?title=A+Novel+Video+Dataset+for+Change+Detection+Benchmarking\u0026author=Goyette,+N.\u0026author=Jodoin,+P.-M.\u0026author=Porikli,+F.\u0026author=Konrad,+J.\u0026author=Ishwar,+P.\u0026publication_year=2014\u0026journal=IEEE+Trans.+Image+Process.\u0026volume=23\u0026pages=4663%E2%80%934679\u0026doi=10.1109/TIP.2014.2346013\" target=\"_blank\"\u003eGoogle Scholar\u003c/a\u003e] [\u003ca href=\"https://dx.doi.org/10.1109/TIP.2014.2346013\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e] \u003c/span\u003e\n\n\u003cspan id=\"Ref-21\"\u003e[21] Volpi, Michele; Camps-Valls, Gustau; Tuia, Devis (2015). Spectral alignment of multi-temporal cross-sensor images with automated kernel canonical correlation analysis; ISPRS Journal of Photogrammetry and Remote Sensing, vol. 107, pp. 50-63, 2015. [\u003ca href=\"https://dx.doi.org/10.1016/j.isprsjprs.2015.02.005\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e] \u003c/span\u003e\n\n\u003cspan id=\"Ref-22\"\u003e[22] L. T. Luppino, F. M. Bianchi, G. Moser and S. N. Anfinsen. Unsupervised Image Regression for Heterogeneous Change Detection. IEEE Transactions on Geoscience and Remote Sensing. 2019, vol. 57, no. 12, pp. 9960-9975. [\u003ca href=\"https://dx.doi.org/10.1109/TGRS.2019.2930348\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e] \u003c/span\u003e\n\n\u003cspan id=\"Ref-23\"\u003e[23] D. Peng, L. Bruzzone, Y. Zhang, H. Guan, H. Ding and X. Huang, SemiCDNet: A Semisupervised Convolutional Neural Network for Change Detection in High Resolution Remote-Sensing Images. IEEE Transactions on Geoscience and Remote Sensing. 2020. [\u003ca href=\"https://dx.doi.org/10.1109/TGRS.2020.3011913\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e] \u003c/span\u003e\n\n\u003cspan id=\"Ref-24\"\u003e[24] Yang, Kunping, et al. Asymmetric Siamese Networks for Semantic Change Detection. arXiv preprint arXiv:2010.05687 (2020). [\u003ca href=\"https://arxiv.org/abs/2010.05687\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e] \u003c/span\u003e\n\n\u003cspan id=\"Ref-25\"\u003e[25] Zhang, C., Yue, P., Tapete, D., Jiang, L., Shangguan, B., Huang, L., \u0026 Liu, G. A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing. 2020. [\u003ca href=\"https://doi.org/10.1016/j.isprsjprs.2020.06.003\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e] \u003c/span\u003e\n\n\u003cspan id=\"Ref-26\"\u003e[26] LEENSTRA, Marrit, et al. Self-supervised pre-training enhances change detection in Sentinel-2 imagery. arXiv. 2021. [\u003ca href=\"https://arxiv.org/abs/2101.08122\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e] \u003c/span\u003e\n\n\u003cspan id=\"Ref-27\"\u003e[27] SHI, Qian, et al. A Deeply Supervised Attention Metric-Based Network and an Open Aerial Image Dataset for Remote Sensing Change Detection. IEEE Transactions on Geoscience and Remote Sensing. 2021. [\u003ca href=\"https://doi.org/10.1109/TGRS.2021.3085870\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e] \u003c/span\u003e\n\n\u003cspan id=\"Ref-28\"\u003e[28] SHEN, Li, et al. S2Looking: A Satellite Side-Looking Dataset for Building Change Detection. arXiv. 2021. [\u003ca href=\"https://arxiv.org/abs/2107.09244\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e] \u003c/span\u003e\n\n\u003cspan id=\"Ref-29\"\u003e[29] LEBEDEV, M. A., et al. CHANGE DETECTION IN REMOTE SENSING IMAGES USING CONDITIONAL ADVERSARIAL NETWORKS. International Archives of the Photogrammetry, Remote Sensing \u0026 Spatial Information Sciences, 2018. [\u003ca href=\"https://doi.org/10.5194/isprs-archives-XLII-2-565-2018\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e] \u003c/span\u003e\n\n\u003cspan id=\"Ref-30\"\u003e[30] SUN, Yuli, et al. Structure Consistency-Based Graph for Unsupervised Change Detection With Homogeneous and Heterogeneous Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, 2021. [\u003ca href=\"https://doi.org/10.5194/10.1109/TGRS.2021.3053571\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e] \u003c/span\u003e\n\n\u003cspan id=\"Ref-31\"\u003e[31] PARK, Jin-Man, et al. ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments. arXiv. 2021. [\u003ca href=\"https://arxiv.org/abs/2103.05368\" target=\"_blank\"\u003eCrossRef\u003c/a\u003e] \u003c/span\u003e\n\n\n\n## Cite\nIf you find this review helpful to you, please consider citing our paper. [\u003ca href=\"https://doi.org/10.3390/rs12101688\" target=\"_blank\"\u003eOpen Access\u003c/a\u003e]\n\n```\n@Article{rs12101688,\nAUTHOR = {Shi, Wenzhong and Zhang, Min and Zhang, Rui and Chen, Shanxiong and Zhan, Zhao},\nTITLE = {Change Detection Based on Artificial Intelligence: State-of-the-Art and Challenges},\nJOURNAL = {Remote Sensing},\nVOLUME = {12},\nYEAR = {2020},\nNUMBER = {10},\nARTICLE-NUMBER = {1688},\nURL = {https://www.mdpi.com/2072-4292/12/10/1688},\nISSN = {2072-4292},\nDOI = {10.3390/rs12101688}\n}\n```\n\n## Note\nThis list will be updated in time, and volunteer contributions are welcome. For questions or sharing, please feel free to [contact us](mailto:007zhangmin@whu.edu.cn) or make issues.\n\n##### Reference materials:\n* [I-Hope-Peace/ChangeDetectionRepository](https://github.com/I-Hope-Peace/ChangeDetectionRepository)\n* [Michele Volpi personal research page](https://sites.google.com/site/michelevolpiresearch/codes)\n* [llu025/Heterogeneous_CD](https://github.com/llu025/Heterogeneous_CD)\n* [wenhwu/awesome-remote-sensing-change-detection](https://github.com/wenhwu/awesome-remote-sensing-change-detection)\n* [neverstoplearn/remote_sensing_change_detection](https://github.com/neverstoplearn/remote_sensing_change_detection)\n* [Change Detection in GIS](https://www.gislounge.com/change-detection-in-gis/)\n* [Gao Feng personal research page](http://feng-gao.cn/)\n* [Bobholamovic/ChangeDetectionToolbox](https://github.com/Bobholamovic/ChangeDetectionToolbox)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMinZHANG-WHU%2FChange-Detection-Review","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FMinZHANG-WHU%2FChange-Detection-Review","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMinZHANG-WHU%2FChange-Detection-Review/lists"}