Retrieving contact points without environment knowledge

This paper paves the way for contact retrieving of human motions without environment knowledge. The goal is to find out the minimal set of contacting links of the human body, that is required to perform a recorded motion. First, we fit the captured motion to a unified representation of the human: the Master Motor Map. Looking at the Minimal Oriented Bounding Boxes of the velocity and acceleration for every link, we determine whether one part of the link is moving or not. This provides an initial guess of the contacting links. Then, based on the dynamic equations of the model, we find the minimal set of contacting links that ensure the balance. Eventually, we assess this method on several motions with actual and pretended contacts. We show that it is efficient for motions such as walking and that it deserves to be improved for more complex motions with a lot of contact points.