levan92/deep_sort_realtime
A really more real-time adaptation of deep sort
This tool helps security analysts, crowd managers, or anyone monitoring live video feeds to reliably track objects or people in real-time. It takes a stream of object detections (like bounding boxes or polygons around people or cars) from each video frame and outputs consistent, unique IDs for each tracked object as they move across frames. This ensures that you know if it's the "same" person or object you're seeing again.
241 stars. Available on PyPI.
Use this if you need to assign unique, persistent IDs to objects or individuals as they appear and move across consecutive frames in a live video stream.
Not ideal if your primary goal is simply detecting objects in individual frames without needing to track their identities over time or across different views.
Stars
241
Forks
63
Language
Python
License
MIT
Category
Last pushed
Mar 25, 2026
Commits (30d)
0
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/levan92/deep_sort_realtime"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
lucidrains/vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with...
roflcoopter/viseron
Self-hosted, local only NVR and AI Computer Vision software. With features such as object...
blakeblackshear/frigate
NVR with realtime local object detection for IP cameras
notAI-tech/NudeNet
Lightweight nudity detection
blakeblackshear/frigate-hass-integration
Frigate integration for Home Assistant