# eduardolundgren/tracking.js

A modern approach for Computer Vision on the web

Repository: https://github.com/eduardolundgren/tracking.js
Canonical: https://ross.abutalabs.com/products/trackingjs
Homepage: http://trackingjs.com
Language: JavaScript
License: NOASSERTION
License Family: other
Last push: 2026-08-11T15:45:33+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 8, longevity 100
- inputs: {"age_days": 5189, "days_push": 22, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9465, forks 1427 (observed 2026-08-28T04:10:31.267245+00:00)

## What it is
tracking.js is a lightweight (~7 KB core) JavaScript library that brings computer vision algorithms like color tracking, object tracking, and face detection into the browser using HTML5 APIs. It includes utilities such as feature detection (FAST), feature descriptors (BRIEF), convolution, grayscale, blur, integral images, and Sobel filters, plus Web Components wrappers.

## Use cases
- detect faces in images or webcam video in the browser
- track colored objects in real time from a camera feed
- build webcam-controlled games or head-tracking interactions
- tag friends' faces in photos on a web page
- run feature detection and image filters client-side
- create interactive three.js scenes controlled by color or motion

## When to choose
- you need lightweight, dependency-free client-side face or color tracking in the browser
- you want simple CV demos or interactive webcam experiences without server processing
- you're targeting older browsers and need a small, self-contained script

## When to avoid
- you need maintained software - the project is inactive with open issues and stale tooling (Bower, Travis CI)
- you need production-grade accuracy or modern ML-based detection (consider MediaPipe, TensorFlow.js, or face-api.js)
- you need server-side or Node.js computer vision

## Facets
- artifact type: library
- maturity: abandoned
- function: computer-vision, image-processing
- domain: computer-vision, image-processing, web-development
- platform: browser
- tags: face-detection, color-tracking, html5, web-components, viola-jones, real-time, javascript

## Member repositories
- eduardolundgren/tracking.js (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:31.267245+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 2026-08-29T17:22:05.310308+00:00, confidence not recorded.
  - readme: https://github.com/eduardolundgren/tracking.js (fetched 2026-08-28T04:10:31.267245+00:00, sha 4b0ff327033a)
  - homepage: http://trackingjs.com (fetched 2026-08-29T08:22:16.422623+00:00, sha c00db4de2379)
  - site_page: https://trackingjs.com/docs.html (fetched 2026-08-29T08:22:16.425075+00:00, sha 18ecf05fc8aa)
- Data as of 2026-08-30T08:39:29.467469+00:00.