LeonLok/Multi-Camera-Live-Object-Tracking

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1110 stars · 293 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python application that performs live multi-camera object detection, tracking, and counting using YOLO v4 and Deep SORT, with a Flask web interface for streaming results. It supports IP cameras via ImageZMQ and includes a specialized traffic counting mode trained on the DETRAC dataset.

Use cases

• count vehicles crossing a line in live traffic video
• count people entering a store from multiple cameras
• stream live object detection from smartphone cameras to a server
• track and count objects across multiple IP cameras in real time
• record directional traffic counts per hour interval
• host a live object counting dashboard on a cloud server

When to choose

• you need real-time multi-camera object counting with YOLO v4 and Deep SORT
• you want to count vehicles or people crossing a configurable line with directional logic
• you want to stream frames from smartphones or IP cameras to a central server via ImageZMQ
• you need a self-hosted Flask dashboard showing live tracking and counts

When to avoid

• you need state-of-the-art detection accuracy on modern vehicle types or non-Chinese traffic scenes
• you want a maintained production system - the last release was in 2021
• you need GPU-free real-time performance
• you prefer newer YOLO versions or transformer-based trackers

Facets

application · maturity maintenance

computer-vision machine-learning video-processing web-framework streaming computer-vision machine-learning analytics python cloud yolov4 deep-sort object-tracking object-counting traffic-monitoring flask opencv imagezmq ip-camera people-counter video linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="LeonLok/Multi-Camera-Live-Object-Tracking")