Sumanth181099/DeepMAO

This is the official implementation of "DeepMAO: Deep Multi-scale Aware Overcomplete Network for Building Segmentation in Satellite Imagery" CVPR 2023 Workshop paper.

25
/ 100
Experimental

This project helps mapmakers, urban planners, and disaster response teams accurately identify and outline buildings in satellite images, even those that are small or have complex shapes. You input electro-optical (EO) or SAR satellite imagery, and it outputs precise, pixel-level outlines of buildings. This is for professionals who need highly detailed and accurate building footprint data from overhead imagery.

No commits in the last 6 months.

Use this if you need to precisely segment and map buildings from satellite imagery, especially when dealing with challenging scenarios like small or irregularly shaped structures.

Not ideal if you're working with aerial photos instead of satellite imagery, or if your primary focus is on detecting other types of ground features besides buildings.

satellite-mapping urban-planning remote-sensing geographic-information-systems disaster-response
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

11

Forks

2

Language

Python

License

Last pushed

Jan 13, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Sumanth181099/DeepMAO"

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