Reliable and Fast Tracking of Faces under Varying Pose

Authors:
Tao Yang;Stan Z. Li;Quan Pan;Jing Li;Chunhui Zhao
Affiliations:
Northwestern Polytechnical University, China;Chinese Academy of Sciences, China;Northwestern Polytechnical University, China;Northwestern Polytechnical University, China;Northwestern Polytechnical University, China
Venue:
FGR '06 Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
Year:
2006

Citing 0
Cited 3

The AIT 2D Face Detection and Tracking System for CLEAR 2007

Multimodal Technologies for Perception of Humans
Efficient object tracking by condentional and cascaded image sensing

Computer Standards & Interfaces
Tracking and recognition of multiple faces at distances

ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper presents a system that is able to track multiple faces under varying pose (tilted and rotated) reliably in real-time. The system consists of two interactive modules. The first module performs detection of face subject to rotations. The second does online learning based face tracking. A mechanism of switching between the two modules is embedded into the system to automatically decide the best strategy for reliable tracking. The mechanism enables smooth transit between the detection and tracking module when one of them gives no results or unreliable results. Results demonstrate that the system can make reliable real-time tracking of multiple faces in complex background under out-of-plane rotation, up to 90 degree tilting, fast nonlinear motion, partial occlusion, large scale changes, and camera motion.