3D environment measurement using binocular stereo and motion stereo by mobile robot with omnidirectional stereo camera

Map information is important for path planning and selflocalization when mobile robots accomplish autonomous tasks. In unknown environments, they should generate environment maps by themselves. An omnidirectional camera is effective for environment measurement, because it has a wide field of view. There are binocular stereo and motion stereo in traditional methods for measurement by omnidirectional camera. However, each method has advantages and disadvantages. In this paper, we aim to improve measurement accuracy by integrating binocular stereo and motion stereo using two omnidirectional cameras installed on a mobile robot. In addition, stereo matching accuracy is improved by considering omnidirectional image distortion. Experimental results show the effectiveness of our proposed method.

[1]  M. Hebert,et al.  Omni-directional structure from motion , 2000, Proceedings IEEE Workshop on Omnidirectional Vision (Cat. No.PR00704).

[2]  Hiroshi Ishiguro,et al.  Omni-Directional Stereo , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Shree K. Nayar,et al.  Ego-motion and omnidirectional cameras , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[4]  Andrew J. Davison,et al.  Real-time simultaneous localisation and mapping with a single camera , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[5]  Atsushi Yamashita,et al.  Three-Dimensional Environment Model Construction from an Omnidirectional Image Sequence , 2009, J. Robotics Mechatronics.

[6]  Kostas Daniilidis,et al.  Omnidirectional video , 2003, The Visual Computer.

[7]  H. Opower.  Multiple view geometry in computer vision , 2002 .

[8]  Minoru Yoshida,et al.  High precision range estimation from an omnidirectional stereo system , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

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

[10]  J.-Y. Bouguet,et al.  Pyramidal implementation of the lucas kanade feature tracker , 1999 .

[11]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.