manideep2510/eye-in-the-sky
Satellite Image Classification using semantic segmentation methods in deep learning
Implements U-Net and PSPNet architectures with one-hot encoded ground truth conversion, achieving 92% training and 85% validation accuracy on 9-class land-cover classification. Uses batch normalization and deconvolution layers in the encoder-decoder pipeline, processing 4-channel GeoTIFF satellite imagery. Provides pre-trained weights and comparison utilities to evaluate per-class segmentation performance against ground truth masks.
317 stars. No commits in the last 6 months.
Stars
317
Forks
86
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/manideep2510/eye-in-the-sky"
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"
motokimura/spacenet_building_detection
Project to train/test convolutional neural networks to extract buildings from SpaceNet satellite...
rogerxujiang/dstl_unet
Dstl Satellite Imagery Feature Detection
IGNF/FLAIR-1
Semantic segmentation from aerial imagery (baseline of the FLAIR #1 challenge)
Paulymorphous/skeyenet
Road and Building Segmentation in Satellite Imagery