Robust and Real-time Rotation Estimation of Compound Omnidirectional Sensor

Camera ego-motion consists of translation and rotation, in which rotation can be described simply by distant features. We present a robust rotation estimation using distant features given by our compound omnidirectional sensor. Features are detected by a conventional feature detector, and then distant features are identified by checking the infinity on the omnidirectional image of the compound sensor. The rotation matrix is estimated between consecutive video frames using RANSAC with only distant features. Experiments with various environments show that our approach is robust and also gives reasonable accuracy in real-time.

[1]  Hans-Hellmut Nagel,et al.  The coupling of rotation and translation in motion estimation of planar surfaces , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Michal Irani,et al.  Recovery of Ego-Motion Using Region Alignment , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Kostas Daniilidis,et al.  Fixation Simplifies 3D Motion Estimation , 1997, Comput. Vis. Image Underst..

[4]  Peter F. Sturm,et al.  Algorithms for plane-based pose estimation , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[5]  Jean Ponce,et al.  Computer Vision: A Modern Approach , 2002 .

[6]  Hans J. Schneebeli,et al.  A general approach for egomotion estimation with omnidirectional images , 2002, Proceedings of the IEEE Workshop on Omnidirectional Vision 2002. Held in conjunction with ECCV'02.

[7]  Yasushi Yagi,et al.  Rolling and swaying motion estimation for a mobile robot by using omnidirectional optical flows , 2003, Machine Vision and Applications.

[8]  S. Shankar Sastry,et al.  Omnidirectional Egomotion Estimation From Back-projection Flow , 2003, 2003 Conference on Computer Vision and Pattern Recognition Workshop.

[9]  Kostas Daniilidis,et al.  Linear Pose Estimation from Points or Lines , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  J. Aloimonos,et al.  Finding motion parameters from spherical motion fields (or the advantages of having eyes in the back of your head) , 1988, Biological Cybernetics.

[11]  Yasushi Yagi,et al.  Compound catadioptric stereo sensor for omnidirectional object detection , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[12]  Onay Urfalioglu,et al.  Robust estimation of camera rotation,translation and focal length at high outlier rates , 2004, First Canadian Conference on Computer and Robot Vision, 2004. Proceedings..

[13]  Han Wang,et al.  Robust Estimation of Rotation Angles from Image Sequences Using the Annealing M-Estimator , 2004, Journal of Mathematical Imaging and Vision.

[14]  Kostas Daniilidis,et al.  Rotation recovery from spherical images without correspondences , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.