Extraction of buildings and road networks from Satellite Images
Machine Learning ·Keywords: Python, Tensorflow, Keras, Pytest
Repository: Building and Road Segmentation
Below we display an example of an input image and the corresponding ground truth and predicted road network and building footprints.
Input Image
![](https://raw.githubusercontent.com/Luke-Pratley/building_road_segmentation/getting_ready_for_submission/Vegas_input.png)
Predicted Labels
![](https://raw.githubusercontent.com/Luke-Pratley/building_road_segmentation/getting_ready_for_submission/Vegas_output.png)
Humanitarian and natural disasters can impact roads and buildings, and having a tool that can quickly survey them is useful. For this reason, I extract buildings and road networks from satellite images using Tensorflow and UNet archtectures.