Stereo Matching and 3D Reconstruction via an Omnidirectional Stereo Sensor

A catadioptric vision system using diverse mirrors has been a popular means to get panoramic images(K.Nayar, 1997) which contains a full horizontal field of view (FOV). This wide view is ideal for three-dimensional vision tasks such as motion estimation, localization, obstacle detection and mobile robots navigation. Omnidirectional stereo is a suitable sensing method for such tasks because it can acquire images and ranges of surrounding areas simultaneously. For omnidiretional stereo vision, an obvious method is to use two (or more) cameras instead of each conventional camera (K.Tan et al., 2004; J.Gluckman et al., 1998; H.Koyasu et al. 2002; A.Jagmohan et al. 2004). Such two-camera (or more-camera) stereo systems are relatively costly and complicated compared to single camera stereo systems. Omnidirectional stereo based on a double-lobed mirror and a single camera was developed (M.F.D. Southwell et al. 1996; T.L. Conroy & J.B. Moore, 1999; E. L. L. Cabral, et al. 2004; Sooyeong Yi & Narendra Ahuja, 1996) . A double lobed mirror is a coaxial mirror pair, where the centers of both mirrors are collinear with the camera axis, and the mirrors have a profile radially symmetric around this axis. This arrangement has the advantage to produce two panoramic views of the scene in a single image. But the disadvantage of this method is the relatively small baseline it provides. Since the two mirrors are so close together, the effective baseline for stereo calculation is quite small. We have developed a novel omnidirectional stereo vision optical device (OSVOD) based on a common perspective camera coupled with two hyperbolic mirrors, which are separately fixed inside a glass cylinder. As the separation between the two mirrors provides much enlarged baseline, in our system, the baseline length is about 200mm, the precision has improved correspondingly (Fig. 1).

[1]  Vladimir Kolmogorov,et al.  What energy functions can be minimized via graph cuts? , 2002, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Anup Basu,et al.  Panoramic stereo , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[3]  Eduardo L. L. Cabral,et al.  Omnidirectional stereo vision with a hyperbolic double lobed mirror , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[4]  Kostas Daniilidis,et al.  Catadioptric camera calibration , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[5]  W. Freeman,et al.  Generalized Belief Propagation , 2000, NIPS.

[6]  Radim Sára,et al.  Finding the Largest Unambiguous Component of Stereo Matching , 2002, ECCV.

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

[8]  Olivier D. Faugeras,et al.  The fundamental matrix: Theory, algorithms, and stability analysis , 2004, International Journal of Computer Vision.

[9]  Shree K. Nayar,et al.  Real-Time Omnidirectional and Panoramic Stereo , 1998 .

[10]  Narendra Ahuja,et al.  Multiview panoramic cameras using mirror pyramids , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Tomás Pajdla,et al.  Omnidirectional Camera Model and Epipolar Geometry Estimation by RANSAC with Bucketing , 2003, SCIA.

[12]  Olivier D. Faugeras,et al.  Computing differential properties of 3-D shapes from stereoscopic images without 3-D models , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Hiroshi Ishikawa,et al.  Exact Optimization for Markov Random Fields with Convex Priors , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Feng Zhu,et al.  Design of a novel stereo vision navigation system for mobile robots , 2005, 2005 IEEE International Conference on Robotics and Biomimetics - ROBIO.

[15]  Sing Bing Kang,et al.  Catadioptric self-calibration , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[16]  Olga Veksler,et al.  Fast approximate energy minimization via graph cuts , 2001, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[17]  Ryad Benosman,et al.  Calibration of panoramic catadioptric sensors made easier , 2002, Proceedings of the IEEE Workshop on Omnidirectional Vision 2002. Held in conjunction with ECCV'02.

[18]  Xianghua Ying,et al.  Catadioptric camera calibration using geometric invariants , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Kostas Daniilidis,et al.  Conformal Rectification of Omnidirectional Stereo Pairs , 2003, 2003 Conference on Computer Vision and Pattern Recognition Workshop.

[20]  Yoshiaki Shirai,et al.  Recognizing Moving Obstacles for Robot Navigation using Real-time Omnidirectional Stereo Vision , 2002, J. Robotics Mechatronics.

[21]  Wolfgang Straßer,et al.  Omnidirectional 3D Modeling on a Mobile Robot using Graph Cuts , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[22]  In So Kweon,et al.  Single Camera Catadioptric Stereo System , 2005, ICCV 2005.

[23]  Tomás Pajdla,et al.  Estimation of omnidirectional camera model from epipolar geometry , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

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

[25]  Ben J. A. Kröse,et al.  Robust scene reconstruction from an omnidirectional vision system , 2003, IEEE Trans. Robotics Autom..

[26]  Shree K. Nayar,et al.  Catadioptric omnidirectional camera , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[27]  John B. Moore,et al.  Resolution invariant surfaces for panoramic vision systems , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.