Binocular Structured Light Stereo Matching Approach for Dense Facial Disparity Map

Binocular stereo vision technology shows a particular interesting for face recognition, in which the accurate stereo matching is the key issue for obtaining dense disparity map used for exploiting 3D shape information of object. This paper proposed a binocular structured light stereo matching approach to deal with the challenge of stereo matching to objects having large disparity and low texture, such as facial image. By introducing global system to coordinate the binocular camera and projector, a projector cast structured light pattern which added texture to the face scene. Binocular epipolar constraint and semi-global stereo matching algorithm were applied. The experiments showed that the accuracy had improved compared to that of purely binocular vision for getting dense facial disparity map.

[1]  Andrew Blake,et al.  Trinocular Active Range-Sensing , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  H. Hirschmüller.  Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual Information , 2005, CVPR.

[3]  Vladimir Kolmogorov,et al.  Computing visual correspondence with occlusions using graph cuts , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[4]  Georg Umlauf,et al.  Accurate real-time multi-camera stereo-matching on the GPU for 3D reconstruction , 2011, WSCG 2011.

[5]  Georgy L. Gimel'farb,et al.  A Comparison of Three 3-D Facial Reconstruction Approaches , 2006, 2006 IEEE International Conference on Multimedia and Expo.

[6]  Steven W. Zucker,et al.  Surface Geometric Constraints for Stereo in Belief Propagation , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[7]  Leszek Wojnar,et al.  Image Analysis , 1998 .

[8]  Luc Van Gool,et al.  Real-time range acquisition by adaptive structured light , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Emanuele Trucco,et al.  Efficient stereo with multiple windowing , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  Yazhu Chen,et al.  Flexible and accurate implementation of a binocular structured light system , 2008 .

[11]  Hans-Peter Seidel,et al.  Using Active Illumination for Accurate Variational Space-Time Stereo , 2011, SCIA.

[12]  Vladimir Kolmogorov,et al.  Visual correspondence using energy minimization and mutual information , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[13]  Ingemar J. Cox,et al.  A Maximum Likelihood Stereo Algorithm , 1996, Comput. Vis. Image Underst..

[14]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[15]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[16]  Daniel P. Huttenlocher,et al.  Efficient Belief Propagation for Early Vision , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[17]  Olga Veksler,et al.  Fast variable window for stereo correspondence using integral images , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[18]  Yu Zhang,et al.  Hierarchical modeling of a personalized face for realistic expression animation , 2002, Proceedings. IEEE International Conference on Multimedia and Expo.