Home -> Projects ->OpenPose: Multi-Person Pose Estimation Member Login  


OpenPose is a library for real-time multi-person keypoint detection and multi-threading written in C++ using OpenCV and Caffe, authored by Gines Hidalgo, Zhe Cao, Tomas Simon, Shih-En Wei Hanbyul Joo and Yaser Sheikh.

OpenPose represents the first real-time system to jointly detect human body and hand keypoints on single images. In addition, the system computational performance on body keypoint estimation is invariant to the number of detected people in the image.

In addition, OpenPose would not be possible without the [CMU Panoptic Studio](http://domedb.perception.cs.cmu.edu/).

Library main functionality:
  • Multi-person 15 or 18-keypoint body pose estimation and rendering. Running time invariant to number of people on the image.
  • Multi-person 2x21-keypoint hand estimation and rendering. Note: In this initial version, running time linearly depends on the number of people on the image.
  • Flexible and easy-to-configure multi-threading module.
  • Image, video, and webcam reader.
  • Able to save and load the results in various formats (JSON, XML, PNG, JPG, ...).
  • Small display and GUI for simple result visualization.
  • All the functionality is wrapped into a simple-to-use OpenPose Wrapper class.
  • Face will be included in a few months.

The pose estimation work is based on the C++ code from [the ECCV 2016 demo](https://github.com/CMU-Perceptual-Computing-Lab/caffe_rtpose), "Realtime Multiperson Pose Estimation", where we present a bottom-up approach for multi-person pose estimation, without using any person detector. For more details, refer to our Arxiv paper and presentation slides at ILSVRC and COCO workshop 2016:

Watch our video result in YouTube:

Find the installation steps on doc/installation.md; and the demo overview on doc/demo_overview.md. For a general overview of the library, please refer to the README.md.
The documentation (installation steps, README.md, etc.) is in Markdown format. In case you do not have already your own Markdown reader, you might simply copy the text of any of those documents into any free online Markdown editor in order to visualize it, e.g. https://stackedit.io/editor.

 Releases [ Members Only ]