Auto-labeling as a Minimization Problem with Virtual Occlusions

Abstract

In this paper we propose a fast algorithm for the automatic labeling of a set of predefined markers in an optical motion capture system. This algorithm is facing the problem as a minimization problem, using a virtual representation of the real model to predict possible occlusions that happen in the captured images. Moreover, we take advan-tage of the knowledge of the cameras parameters to solve potential labeling conflicts between markers. Categories and Subject Descriptors (according to ACM CCS): I.3.7 [Computer Graphics]: Three-Dimensional Graphics and Realism - animation.