satellite-image-semantic-segmentation

Semantic Segmentation of Large Satellite Images with blockedImage Datastores
105 Downloads
Updated 29 Sep 2023

Semantic Segmentation of Large Satellite Images

Open in MATLAB Online View satellite-image-semantic-segmentation on File Exchange

Semantic segmentation of large multi-resolution satellite imagery tiles is ideally suited to blockedImage workflows - where only part of the image is loaded for training at one time. This is a much faster workflow as the size of the tiles can be tuned to fit within GPU RAM.

This example walks through the process of:

  1. Importing a pre-labelled groundMATLAB Worksheet examples of Algo.7z truth object
  2. Modifying the paths of the ground truth to match this training machine
  3. Converting the large satellite images to blockedImageDatastores
  4. Building and training, with validation, a semantic segmentation network on blockedImages
  5. Testing on out of sample data that was not used in the training set.

Semantic segementation screenshot of raw and labelled data

Data Acknowledgement

The satellite data used in this example is based on SPOT 6/7 Imagery and is reused from the New South Wales Spatial Data Portal and is licensed under a Creative Commons Attribution 3.0 License with additional acknowledgement to Airbus (© CNES (2020) DISTRIBUTION AIRBUS DS) as the original provider of the data to the NSW Government.

Setup

To run open and execute buildAndTrainNet.mlx.

If you have moved the two data folders:

  1. dataRaw
  2. dataLabels

Outside the MATLAB Project folder you will have to change lines 7 and 11, respectively to point to the new data folder locations.

MathWorks Products (http://www.mathworks.com)

Requires MATLAB release R2021b or newer

License

The license is available in the LICENSE.TXT file in this GitHub repository.

Community Support

MATLAB Central

Copyright 2021-2023 The MathWorks, Inc.

Cite As

Peter Brady (2024). satellite-image-semantic-segmentation (https://github.com/matlab-deep-learning/satellite-image-semantic-segmentation/releases/tag/V1.1.1), GitHub. Retrieved .

MATLAB Release Compatibility
Created with R2022a
Compatible with any release
Platform Compatibility
Windows macOS Linux
Tags Add Tags

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
Version Published Release Notes
1.1.1.0

See release notes for this release on GitHub: https://github.com/matlab-deep-learning/satellite-image-semantic-segmentation/releases/tag/V1.1.1

1.0.2

See release notes for this release on GitHub: https://github.com/matlab-deep-learning/satellite-image-semantic-segmentation/releases/tag/1.0.2

1.0.1

To view or report issues in this GitHub add-on, visit the GitHub Repository.
To view or report issues in this GitHub add-on, visit the GitHub Repository.