An Automatic Method for Semantic Focal Feature Point Tracking of 3D Human Model in Motion Sequence

In this paper, a method, for automatically identifying and tracking garment related semantic focal feature points on 3D human model in motion sequence, is proposed. We consider the problem of automatic focal feature point identification and tracking when non-rigid shape deformation is occurred. The main contribution is that a novel method of tracking focal feature points when the human avatar move in front of depth camera. Firstly, we learn a regression analysis model that derives the relationship between sampled and focal feature points. Secondly, we build a model of correspondence maps to calculate the tracking results. The method can track garment-related feature points for different people in different motion and shape. We demonstrate on a wide variety of experiments that our approach leads to a significant identification and tracking result with input depth sequences.