YonghaoXu/CRGNet
[IEEE TIP 2022] Consistency-Regularized Region-Growing Network for Semantic Segmentation of Urban Scenes with Point-Level Annotations
This project helps urban planners and environmental scientists automatically classify features like buildings, roads, and vegetation in satellite or aerial images. It takes high-resolution remote sensing images, along with minimal 'point-level' annotations (just a few pixels labeled per feature), and outputs a fully segmented image where every pixel is categorized. This is useful for professionals who need detailed land cover maps but lack the resources for extensive manual labeling.
No commits in the last 6 months.
Use this if you need to perform semantic segmentation on urban remote sensing imagery with very limited manual annotations, saving significant time and effort.
Not ideal if you already have fully labeled datasets or are working with different types of imagery (e.g., medical, microscopic) or non-urban scenes.
Stars
38
Forks
2
Language
Python
License
MIT
Category
Last pushed
Aug 12, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/YonghaoXu/CRGNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
WangLibo1995/GeoSeg
UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban...
cvjena/cn24
Convolutional (Patch) Networks for Semantic Segmentation
TUI-NICR/EMSANet
EMSANet: Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments
qizhuli/Weakly-Supervised-Panoptic-Segmentation
Weakly- and Semi-Supervised Panoptic Segmentation (ECCV18)
KieDani/SegformerPlusPlus
Official implementation of "Segformer++: Efficient Token-Merging Strategies for High-Resolution...