Robust 3D Face Tracking on Multiple Users with Dynamical Active Models

Dianle Zhou, Patrick Horain

Publication reference:

D. Zhou, P. Horain, "Robust 3D Face Tracking on Multiple Users with Dynamical Active Models", Advances in Multimedia Modeling, Proceedings of the 15th International Multimedia Modeling Conference (MMM2009), 7-9 January 2009, EURECOM, Sophia Antipolis, France, p. 74-84 [doi:10.1007/978-3-540-92892-8_9].


The Active Appearance Models and the derived Active Models (AM) allow to robustly track the face of a single user that was previously learnt, but works poorly with multiple or unknown users. Our research aims at improving the tracking robustness by learning from video databases. In this paper, we study the relation between the face texture and the parameter gradient matrix, and propose a statistical approach to dynamically fit the AM to unknown users by estimating the gradient and update matrices from the face texture. We have implemented this algorithm for real time face tracking and experimentally demonstrate its robustness when tracking multiple or unknown users’ faces.

Full text:

Copyright 2009 Springer-Verlag. The copyright to this Contribution is transferred to Springer-Verlag GmbH Berlin Heidelberg. This article is published on Springer’s website.
PDF (3292 kbytes).