jiaweihe1996/GMTracker

Official PyTorch implementation of "Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking" (CVPR 2021).

44
/ 100
Emerging

This project helps computer vision practitioners analyze video footage to identify and follow multiple moving objects over time. It takes raw video sequences and initial object detections as input, then outputs text files specifying the unique identity and location of each object in every frame. It's designed for researchers and engineers working on advanced object tracking applications.

117 stars. No commits in the last 6 months.

Use this if you need to accurately track the movement of multiple distinct objects across video frames, especially in complex scenarios with occlusions or crowded scenes.

Not ideal if you only need to detect objects at a single point in time, or if you require a simple, out-of-the-box solution without deep learning model configuration.

video-analytics object-tracking computer-vision surveillance motion-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

117

Forks

22

Language

Python

License

GPL-3.0

Last pushed

Dec 31, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jiaweihe1996/GMTracker"

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