Identify satellite training data (we hope to find pre-labelled images) perhaps from Kaggle?
phil8192 opened this issue · 3 comments
phil8192 commented
Identify satellite training data (we hope to find pre-labelled images) perhaps from Kaggle?
phil8192 commented
Actual image source likely to be Sentinel 2 and/or images from Google static maps API.
Leaving this open, since model pre-trained on another dataset (e.g., Kaggle DSTL) may be useful for processing actual data (transfer learning, bagging, ensembles etc)
phil8192 commented
- DSTL - Kaggle
- Draper Satellite Image Chronology - Kaggle
- Understanding the Amazon from Space - Kaggle
- Ships in Satellite Imagery - Kaggle - From Open California dataset.
- 2D Semantic Labelling - Vaihingen data - This is from a true orthophotographic survey (from a plane). The data is 9cm resolution!
- SAT-4 and SAT-6 airborne datasets - very high res (1m) whole of US. 65 Terabytes. (DeepSat) 1m/px. (2015). SAT-4: barren land, trees, grassland, other. SAT-6: barren land, trees, grassland, roads, buildings, water bodies. (RGB + NIR)