Junjue-Wang/FactSeg

[TGRS 2021] FactSeg: Foreground Activation Driven Small Object Semantic Segmentation in Large-Scale Remote Sensing Imagery

29
/ 100
Experimental

FactSeg helps geospatial analysts and remote sensing professionals accurately identify and map very small objects like vehicles, buildings, or infrastructure elements in satellite or aerial images. It takes large-scale remote sensing imagery as input and outputs precise segmentation masks, clearly outlining these small objects. This is ideal for tasks requiring fine-grained mapping and object detection from overhead views.

No commits in the last 6 months.

Use this if you need to precisely detect and delineate small, critical objects within vast satellite or aerial photographs.

Not ideal if your primary goal is general land cover classification or detecting large, easily visible features in remote sensing data.

remote-sensing geospatial-analysis object-detection aerial-imagery urban-mapping
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

80

Forks

8

Language

Python

License

Last pushed

Nov 11, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Junjue-Wang/FactSeg"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.