# LeonLok/Multi-Camera-Live-Object-Tracking

Multi-camera live traffic and object counting with YOLO v4, Deep SORT, and Flask.

Repository: https://github.com/LeonLok/Multi-Camera-Live-Object-Tracking
Canonical: https://ross.abutalabs.com/products/multi-camera-live-object-tracking
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: yolo, tracking, object-detection, object-tracking, people-counter, flask, deep-sort, opencv, livestream, real-time-analytics, yolov4, traffic, traffic-monitoring, traffic-counter, traffic-counting, yolov4-cloud, yolov4-deepsort, yolo-v4, imagezmq, camera-stream
Last push: 2021-12-19T15:52:32+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2319, "days_push": 1718, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1110, forks 293 (observed 2026-08-28T04:03:37.531308+00:00)

## What it is
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
- artifact type: application
- maturity: maintenance
- function: computer-vision, machine-learning, video-processing, web-framework, streaming
- domain: computer-vision, machine-learning, analytics
- platform: python, cloud
- tags: yolov4, deep-sort, object-tracking, object-counting, traffic-monitoring, flask, opencv, imagezmq, ip-camera, people-counter, video, linux

## Member repositories
- LeonLok/Multi-Camera-Live-Object-Tracking (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:37.531308+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:43:25.584886+00:00, confidence not recorded.
  - readme: https://github.com/LeonLok/Multi-Camera-Live-Object-Tracking (fetched 2026-08-28T04:03:37.531308+00:00, sha 68f6ac25f0d3)
- Data as of 2026-08-30T08:39:29.467469+00:00.