ambakick/Person-Detection-and-Tracking

A tensorflow implementation with SSD model for person detection and Kalman Filtering combined for tracking

49
/ 100
Emerging

This project helps security personnel and business owners monitor foot traffic by taking live video feeds and identifying each person with a unique ID. It outputs a video stream where every individual is highlighted with a bounding box and a persistent identification number, even if they are briefly out of view. This system is designed for anyone needing to track individuals through an area, like in retail stores or public spaces.

252 stars. No commits in the last 6 months.

Use this if you need to count, track, or analyze the movement of people in video surveillance footage, especially in real-time or near real-time scenarios.

Not ideal if your primary goal is to identify individuals by name or require accurate tracking through significant, prolonged obstructions.

video-surveillance foot-traffic-analysis security-monitoring crowd-management retail-analytics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

252

Forks

82

Language

Python

License

MIT

Last pushed

Dec 07, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ambakick/Person-Detection-and-Tracking"

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