A Fast and Robust Facial Points Localization and Pose Estimation System

We have developed a fast facial feature point detection and pose estimation system. This system can detect facial points and estimate 3D pose angles in various conditions including facial expression changes and partial occlusion, etc. Only one facial image is needed as input and we don’t need special devices such as a blinking LED or a dual/stereo camera, etc. Moreover, no calibration process is needed. It shows 90% of estimation accuracy (when the error margin is 15 degrees), and the processing time is about 10ms/frame (Pentium4 3.2GHz). Acceptable range of facial pose is within ±60 degrees in yaw (left-right) and within ±30 degrees in pitch (up-down).

[1]  Takayoshi Yamashita,et al.  A Fast 360-Degree Rotation Invariant Face Detection System , 2003, ICCV 2003.

[2]  Qiang Ji,et al.  Real-Time Eye, Gaze, and Face Pose Tracking for Monitoring Driver Vigilance , 2002, Real Time Imaging.

[3]  Rainer Stiefelhagen,et al.  Head pose estimation using stereo vision for human-robot interaction , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[4]  David Beymer,et al.  Eye gaze tracking using an active stereo head , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[5]  Yi Zhou,et al.  Bayesian tangent shape model: estimating shape and pose parameters via Bayesian inference , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[6]  Ruigang Yang,et al.  Model-based head pose tracking with stereovision , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[7]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Takeo Kanade,et al.  Real-time combined 2D+3D active appearance models , 2004, CVPR 2004.

[9]  Bo Wu,et al.  Omni-directional face detection based on real AdaBoost , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..