braun-steven/DAFNe

Code for our paper "DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Object Detection".

42
/ 100
Emerging

This project helps computer vision engineers and researchers accurately identify and locate objects in aerial or satellite images, even when they are oriented at various angles. You input an image containing objects like ships, vehicles, or buildings, and it outputs bounding boxes that precisely outline each object, noting its orientation. This is ideal for those developing advanced object recognition systems for geospatial analysis or surveillance.

No commits in the last 6 months.

Use this if you need to detect objects in images that are not always upright and require precise bounding boxes that account for rotation.

Not ideal if your application only requires standard axis-aligned bounding box detection for upright objects.

aerial-imagery-analysis geospatial-intelligence object-recognition remote-sensing maritime-surveillance
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

61

Forks

12

Language

Python

License

MIT

Last pushed

Apr 01, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/braun-steven/DAFNe"

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