satellite/aerial imagery deep learning
A curated overview of deep learning techniques, architectures, and resources for satellite and aerial imagery.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose when you need an end-to-end Python framework for training deep learning models on satellite/aerial imagery instead of a techniques survey.
An open source library and framework for deep learning on satellite and aerial imagery.
Choose when you want an actively maintained PyTorch library with geospatial datasets, samplers, and pretrained models.
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
Choose when you need a modern, actively developed GeoAI library integrating deep learning with geospatial data.
GeoAI: Artificial Intelligence for Geospatial Data
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Choose when you need a specialized, ready-to-run semantic segmentation tool for aerial imagery (buildings, roads, etc.) rather than a broad techniques list.
Semantic segmentation on aerial and satellite imagery. Extracts features such as: buildings, parking lots, roads, water, clouds
Choose only as a historical/educational demo of OpenStreetMap plus satellite deep learning; it is unmaintained and outdated.
Train a deep learning net with OpenStreetMap features and satellite imagery.
These projects were analysed and named techniques among their alternatives. The relationship is not symmetric — how techniques rates them is a separate judgement, made when techniques is analysed in its own right.
calls techniques “narrower: focuses on satellite/aerial imagery CV techniques.”
Best Practices, code samples, and documentation for Computer Vision.