basilevh/tcow

Tracking through Containers and Occluders in the Wild (CVPR 2023) - Official Implementation

33
/ 100
Emerging

This project helps video analysts and computer vision researchers accurately track specific objects in video footage, even when they are temporarily hidden or move behind other objects like containers. You provide video clips and an initial mask highlighting the object to track, and it outputs precise segmentations of that object across all frames. This is ideal for those studying object motion, analyzing crowded scenes, or evaluating the effectiveness of object tracking systems.

No commits in the last 6 months.

Use this if you need to reliably follow objects through complex video scenes where occlusions (like objects moving behind a box or another person) are common.

Not ideal if you primarily need to detect objects or classify actions, rather than tracking specific instances of objects across frames.

object tracking video analysis computer vision research motion analysis scene understanding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

40

Forks

4

Language

Python

License

MIT

Last pushed

Jun 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/basilevh/tcow"

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