apennisi/deep_sort

Deep Sort algorithm C++ version

44
/ 100
Emerging

This is a C++ implementation of the Deep Sort algorithm designed for robust object tracking in video streams. It takes a sequence of detected objects (their bounding boxes, classes, and confidences) from video frames, along with pre-trained models for appearance features, and outputs consistent tracking IDs for each object across frames. This tool is for computer vision engineers or researchers who need to track multiple objects accurately in real-time or from recorded footage.

No commits in the last 6 months.

Use this if you need to assign and maintain unique IDs for detected objects in a video, even when objects are occluded or temporarily leave the frame, and you are working in a C++ development environment.

Not ideal if you need a plug-and-play solution without C++ compilation or if your primary environment is Python or another high-level language.

object-tracking video-analytics computer-vision real-time-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

96

Forks

22

Language

C++

License

GPL-3.0

Last pushed

Dec 03, 2019

Commits (30d)

0

Get this data via API

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

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