A Deep Learning-powered tool that maps rooftop solar potential by extracting building footprints from satellite imagery using a ResNet50-U-Net model
-
Updated
Aug 14, 2024 - Jupyter Notebook
A Deep Learning-powered tool that maps rooftop solar potential by extracting building footprints from satellite imagery using a ResNet50-U-Net model
This project was built as a part of the ISRO Bharatiya Antariksh Hackathon - 2024. This project proposes a novel windowing method to detect minor craters and boulders in ISRO's PSD4 formats which are nearly of 1Mx1M resolution in an efficient manner
This is repository where we are testing our custom loss function on imbalanced earth satellite data
Generate grayscale and color DEMs from lunar images using shape-from-shading.
Spatiotemporal Generative Modelling Using Latent Disffusion Models on Insat Dataset. Team ~ noisynebula
Add a description, image, and links to the isro-hackathon topic page so that developers can more easily learn about it.
To associate your repository with the isro-hackathon topic, visit your repo's landing page and select "manage topics."