Haoning724/obbstacking

Repo for the OBBStacking: An Ensemble Method for Remote Sensing Object Detection

27
/ 100
Experimental

This project helps remote sensing analysts combine the results from multiple object detection models to get more accurate and reliable detections of features in satellite or aerial images. You input the detection results (bounding boxes) from different models on the same images, and it outputs a single, refined set of object detections. This is useful for scientists, urban planners, or defense analysts who rely on precise object identification from high-resolution imagery.

No commits in the last 6 months.

Use this if you are using multiple object detection models on remote sensing imagery and want to improve the accuracy of their combined outputs, especially for oriented objects.

Not ideal if you only have one object detection model, or if your objects are not oriented (axis-aligned bounding boxes).

remote-sensing aerial-imagery-analysis object-detection geospatial-intelligence image-interpretation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

19

Forks

1

Language

Python

License

MIT

Last pushed

May 16, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Haoning724/obbstacking"

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