Motion machine: A new framework for motion capture signal feature prototyping

Motion capture (mocap) is rapidly evolving and embraced by a growing community in various research areas. However, a common problem is the high dimensionality of mocap data, and the difficulty to extract and understand meaningful features. In this paper, we propose a framework for the rapid prototyping of feature sets, MotionMachine, which helps to overcome the standard problem of mocap feature understanding by an interactive visualisation of both features and 3D scene. Our framework aims at being flexible to input data format, and to work both offline or in real-time. The design of the feature extraction modules in C++ is intended for modules to be used both for visualisation in the MotionMachine framework and for integration in end-user applications or communication with other existing softwares. We present two examples of use-cases in which the main features of this framework have successfully been tested.