Guanghan/lighttrack
LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking
This project helps you automatically track human movement and body postures in live camera feeds or pre-recorded videos. It takes raw video footage as input and outputs the location and posture (keypoints) of each person, maintaining their identity over time. Security professionals, sports analysts, or content creators can use this to understand motion.
731 stars. No commits in the last 6 months.
Use this if you need to continuously monitor and identify individual people's poses and movements within a video stream.
Not ideal if your primary need is to detect objects other than humans, or if you only need a single snapshot of a person's pose without tracking their identity over time.
Stars
731
Forks
140
Language
Python
License
MIT
Category
Last pushed
May 07, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Guanghan/lighttrack"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
roboflow/rf-detr
[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture...
stereolabs/zed-sdk
⚡️The spatial perception framework for rapidly building smart robots and spaces
mikel-brostrom/boxmot
BoxMOT: Pluggable SOTA multi-object tracking modules with support for axis-aligned and oriented...
RizwanMunawar/yolov7-object-tracking
YOLOv7 Object Tracking Using PyTorch, OpenCV and Sort Tracking
google-deepmind/tapnet
Tracking Any Point (TAP)