https://github.com/sumanth44a/satellite_image_segmentation_using_deep_learning_model

Satellite Image segmentation using Unet
https://github.com/sumanth44a/satellite_image_segmentation_using_deep_learning_model

deep-learning image-processing python u-net

Last synced: about 2 months ago
JSON representation

Satellite Image segmentation using Unet

• Host: GitHub
• URL: https://github.com/sumanth44a/satellite_image_segmentation_using_deep_learning_model
• Owner: sumanth44a
• Created: 2024-06-28T11:15:08.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-06-28T11:31:47.000Z (almost 2 years ago)
• Last Synced: 2025-09-03T01:45:41.232Z (10 months ago)
• Topics: deep-learning, image-processing, python, u-net
• Language: Jupyter Notebook
• Homepage:
• Size: 3.72 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Satellite image segmentation using Deep Learning Model

## Introduction:

  Deep learning has revolutionized the analysis and interpretation of satellite and aerial imagery, addressing unique challenges such as vast image sizes and a wide array of object classes. This repository provides an exhaustive overview of deep learning techniques specifically tailored for satellite and aerial image processing using the U-Net model.

## Model:

![image](https://github.com/sumanth44a/Satellite_Image_segmentation_Using_Unet/assets/114097800/8a830e13-20d3-4398-8d59-f27c4bde9a22)

The U-Net model is employed in this project for semantic segmentation of satellite images. U-Net is known for its efficiency and accuracy in handling image segmentation tasks, making it a suitable choice for this application.

## Dataset

  - DatasetLink: https://www.kaggle.com/datasets/humansintheloop/semantic-segmentation-of-aerial-imagery?resource=download

### Context

Humans in the Loop is publishing an open-access dataset annotated for a joint project with the Mohammed Bin Rashid Space Center in Dubai, UAE.

### Content

The dataset consists of aerial imagery of Dubai obtained by MBRSC satellites and annotated with pixel-wise semantic segmentation in 6 classes. The total volume of the dataset is 72 images grouped into 6 larger tiles. The classes are:

  - Building: #3C1098

  - Land (unpaved area): #8429F6

  - Road: #6EC1E4

  - Vegetation: #FEDD3A

  - Water: #E2A929

  - Unlabeled: #9B9B9B

## Results:

![Output](https://github.com/sumanth44a/Satellite_Image_segmentation_Using_Unet/assets/114097800/80d3ce0a-9342-4ba1-8359-478beb002db2)