OpenPose  1.7.0
The first real-time multi-person system to jointly detect human body, hand, facial, and foot keypoints
OpenPose Very Advanced Doc - Library Structure

As a user, you do not need to know anything about this section! This section is intended for OpenPose internal developers. It is exposed publicly, but you can skip this whole folder if you are just trying to use OpenPose or create new code/demos using OpenPose.

Even if you want to e.g., change internal functions and/or extend the OpenPose functionality, the easiest solution as a user is to follow the ../../doc/04_cpp_api.md "OpenPose C++ API". If the new functionality is cool, make a pull request so we can add it to OpenPose!

In order to learn the basics about how OpenPose works internally:

  1. See the Doxygen documentation on http://cmu-perceptual-computing-lab.github.io/openpose or build that Doxygen doc from the source code.
  2. Take a look at the library Quick Start section from the main README (or its Doxygen analog).
  3. OpenPose Overview: Learn the basics about the library source code in doc/very_advanced/library_structure/1_library_deep_overview.md.
  4. Extending Functionality: Learn how to extend the library in doc/very_advanced/library_structure/2_library_extend_functionality.md.
  5. Adding An Extra Module: Learn how to add an extra module in doc/very_advanced/library_structure/3_library_add_new_module.md.