PyMO is a python library for machine learning research on motion capture data. It is designed on top of scikit-learn, pandas, and numpy.

I'm developing this library as a part of my Ph.D. research in an effort to streamline and fascilitate the prepration and feature extraction methods often used with motion capture data in the literature. Currently, the library is highly experimental and everything is subject to change :)

Project Roadmap

  • Mocap Data Parsers and Writers
  • Common mocap pre-processing algorithms
  • Feature extraction library
  • Visualization tools

[Current] Features

  • Read BVH Files
  • Write BVH Files
  • Pre-processing pipelines
    • Supporting scikit-learn API
    • Convert data representations
      • Euler angles to positions
      • Euler angles to exponential maps
      • Exponential maps to euler angles
    • Body-oriented global translation and rotation calculation with inverse tranform
    • Root-centric position normalizer with inverse tranform
    • Standard scaler
    • Joint selectors
  • Visualization tools
    • Skeleton hierarchy
    • 2D frame visualization
    • 3D webgl-based animation
  • Annotations
    • Foot/ground contact detector

For more information, please checkout the project's page on Github.