Face Tracking in Video Sequences Using Particle Filter Based on Skin Color Model and Facial Contour

摘要

This paper proposed a robust and real-time face tracking method using particle filter based on skin color model and facial contour. Particle filter is an excellent tracking algorithm that can resolve no-linear and no-Gaussian problems. Skin color is used as an important cue since it is robust to various face poses and face rotations. A skin color model is constructed in YCbCr color space which is used to avoid the effect of illumination change in the skin color tracker. Facial contour is another important cue for face tracking which is insensitive to complex environment. The experiment results show that the approach can track face with various rotation in complex environment and can solve partial occlusion.