Here is a huge list of resources for performing deep learning on satellite and aerial imagery. The resources are updated regularly and could benefit both the research and developer communities.
Remote-sensing
- Want to learn more about satellite imagery? Here you can find tutorials, user guides and examples of how you can use satellite imagery to analyze various phenomena and events around the globe.
- EOReader is a remote sensing open-source Python library reading optical and SAR constellations, loading and stacking bands, clouds, DEM and spectral indices in a sensor-agnostic way.
- LEVIR-Ship is the first public tiny ship detection dataset specific to medium-resolution remote sensing images. Check it out here.
- Here is a long list of available benchmark datasets which are acquired using airborne/spaceborne imaging/radar sensors.
- Check out this large collection of tutorials on Google Earth Engine, WhiteboxTools, and more. The blog is created by Dr. Qiusheng Wu, author and contributor of many open source geospatial projects.
- Check here for a long list of references, algorithms, applications, and other resources on remote sensing data fusions.
- The eemont package extends the Google Earth Engine Python API with pre-processing and processing tools for the most used satellite platforms by adding utility methods for Earth Engine Objects.
- Spectral indices are widely used in the Remote Sensing community. This repository includes a curated list of both classical and novel spectral indices for different remote sensing applications.
- The Canadian Space Agency, in collaboration with its partners, has made over 674 000 historical RADARSAT-1 synthetic aperture radar (SAR) images of Earth freely available.
