Motion Data and Machine Learning: Prototyping and Evaluation
Thierry Ravet, Joëlle Tilmanne, Nicolas d’Alessandro, Sohaïb Laraba · ORBi UMONS · 2016
In this work, we address the problem of graphical visualization to train and validate machine learning solutions with motion capture data. We describe our experiment to build an ecient system to explore and manipulate, spatially and temporally, motion data collection. We present a prototyping tool for motion representation and interaction design based on the MotionMachine framework. This framework provides a coherent process chain to annotate the data, apply training algorithm and validate graphically the obtained results.