Enhancement for face video from omni-directional video camera

In this paper we propose a novel algorithm to enhance the face video from omni-directional video camera. A two-stage strategy is used. First stage is the noise elimination, realized by iterative MAP update. Naive Bayesian criterion is used to model the posterior. The predominant salt and pepper noise introduced by the omni-to-perspective transformation can be removed effectively, while the image details are well preserved. The high frequency component compensation (HFCC) super-resolution algorithm is applied thereafter to remove the blocky effect. Experimental results show that the video quality has a marked improvement.

[1]  Robert L. Stevenson,et al.  Simultaneous multi-frame MAP super-resolution video enhancement using spatio-temporal priors , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[2]  Mohan M. Trivedi,et al.  Networked omnivision arrays for intelligent environment , 2001, SPIE Optics + Photonics.

[3]  Naokazu Yokoya,et al.  Visual surveillance and monitoring system using an omnidirectional video camera , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[4]  Toshio Ito,et al.  The omnidirectional vision sensor for in-vehicle image processing applications , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[5]  Mohan M. Trivedi,et al.  High Frequency Component Compensation based Super-Resolution Algorithm for Face Video Enhancement , 2004, ICPR.

[6]  Shmuel Peleg,et al.  Robust super-resolution , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[7]  Mohan M. Trivedi,et al.  Video arrays for real-time tracking of person, head, and face in an intelligent room , 2003, Machine Vision and Applications.

[8]  Qian Chen,et al.  Face Detection From Color Images Using a Fuzzy Pattern Matching Method , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Ruzena Bajcsy,et al.  High resolution catadioptric omni-directional stereo sensor for robot vision , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).