Rectification-Free Multibaseline Stereo for Non-ideal Configurations

SSSD-based linear multibaseline stereo is an efficient implementation of multi-camera stereo vision system. This efficiency, however, vitally relies on the ideal configuration of all cameras. For dealing with non-ideal configurations, conventional stereo rectification algorithms can be used, but the performances are often still not satisfactory. This paper proposes a new algorithm to process non-ideally configured multibaseline stereo system, which not only avoids the rectification procedure but also remains the efficiency of SSSD at the same time. This is fulfilled by using the idea of tensor transfer used in image-based-rendering area. In particular, the multibaseline stereo is reformulated as a novel-view-synthesis problem. We propose a new concept of tensor-transfer to generate novel views as well as compute the depth map.

[1]  Charles T. Loop,et al.  Computing rectifying homographies for stereo vision , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[2]  Takeo Kanade,et al.  Stereo Matching between Three Images by Iterative Refinement in PVS , 2003 .

[3]  Tim J. Dennis,et al.  Epipolar line estimation and rectification for stereo image pairs , 1996, IEEE Trans. Image Process..

[4]  Emanuele Trucco,et al.  Rectification with unconstrained stereo geometry , 1997, BMVC.

[5]  Naokazu Yokoya,et al.  Dense 3-D Reconstruction of an Outdoor Scene by Hundreds-Baseline Stereo Using a Hand-Held Video Camera , 2004, International Journal of Computer Vision.

[6]  Larry S. Davis,et al.  Uncalibrated stereo rectification for automatic 3D surveillance , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[7]  Kostas Daniilidis,et al.  Trinocular stereo for non-parallel configurations , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[8]  Reinhard Koch,et al.  A simple and efficient rectification method for general motion , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[9]  Stephen Lin,et al.  Multibaseline stereo in the presence of specular reflections , 2002, Object recognition supported by user interaction for service robots.

[10]  Steven M. Seitz,et al.  Photorealistic Scene Reconstruction by Voxel Coloring , 1997, International Journal of Computer Vision.

[11]  Mubarak Shah,et al.  From Images to Video: View Morphing of Three Images , 2003, VMV.

[12]  Luc Van Gool,et al.  Wide-baseline multiple-view correspondences , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

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

[14]  Takeo Kanade,et al.  A Multiple-Baseline Stereo , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Andrew Zisserman,et al.  Multiple View Geometry in Computer Vision (2nd ed) , 2003 .

[16]  Shree K. Nayar,et al.  Rectifying transformations that minimize resampling effects , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[17]  Charles E. Thorpe,et al.  A specialized multibaseline stereo technique for obstacle detection , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[18]  Philippos Mordohai,et al.  Dense multiple view stereo with general camera placement using tensor voting , 2004 .

[19]  Andrew W. Fitzgibbon,et al.  Image-Based Rendering Using Image-Based Priors , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[20]  Amnon Shashua,et al.  Novel View Synthesis by Cascading Trilinear Tensors , 1998, IEEE Trans. Vis. Comput. Graph..

[21]  Andrew Zisserman,et al.  Wide baseline stereo matching , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).