#261 · Primary category: Computer Vision
sort
Simple, online, and realtime tracking of multiple objects in a video sequence.
Project last updated:11/28/23
GitHub Stars
4.4K
Forks
1.1K
Contributors
3
License
GPL-3.0
Why we included this project
SORT is a stripped-down multiple object tracker that gives you consistent IDs for moving objects using only past and current frames. It pairs a Kalman filter with Hungarian data association, which keeps latency low because it never waits for the whole video. That makes it a natural fit for real-time systems, but the README is upfront that it doesn't handle occlusion or objects that leave and re-enter. So it is less a finished product than a reference implementation, and its tiny codebase is exactly why researchers still use it as a baseline when testing new ideas.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)