#18 · Primary category： Computer Vision
openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Project last updated：08/03/24
GitHub Stars
34.4K
Forks
8.0K
Contributors
109
License
Other
Why we included this project
OpenPose was the first real-time system to pull body, hand, face, and foot keypoints out of a single image, 135 in total, and it still holds up as the reference for that job. Its runtime stays roughly flat no matter how many people are in the frame, which is what makes it usable for live webcam and CCTV feeds. You get a command-line demo plus C++ and Python APIs, with CUDA, OpenCL, and CPU-only builds, so it works both as a quick test and as a component inside a larger pipeline. The calibration toolbox and 3D triangulation module are worth a look if you want to move past flat 2D landmarks, and the documentation is thorough enough to double as a tutorial for people learning pose estimation.
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)