rogerxujiang/dstl_unet
Dstl Satellite Imagery Feature Detection
This project helps interpret satellite imagery by automatically identifying and outlining ten types of objects, like buildings, roads, trees, and vehicles. You input multi-spectral satellite images and receive precise outlines (masks) of these features. It's designed for geospatial analysts or researchers who need to extract detailed information from satellite data.
145 stars. No commits in the last 6 months.
Use this if you need to automatically detect and map specific features within satellite imagery for large-scale analysis or monitoring.
Not ideal if you lack access to high-performance computing resources like a powerful GPU and significant RAM, or if your primary interest is in developing new deep learning architectures from scratch.
Stars
145
Forks
57
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 18, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rogerxujiang/dstl_unet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
WHU-Sigma/HyperSIGMA
The official repo for [TPAMI'25] "HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model"
manideep2510/eye-in-the-sky
Satellite Image Classification using semantic segmentation methods in deep learning
motokimura/spacenet_building_detection
Project to train/test convolutional neural networks to extract buildings from SpaceNet satellite...
Paulymorphous/skeyenet
Road and Building Segmentation in Satellite Imagery
IGNF/FLAIR-1
Semantic segmentation from aerial imagery (baseline of the FLAIR #1 challenge)