Robust, Real-Time Motion analysis

An algorithm is presented for a robust real-time motion recovery. The algorithm uses point to line matches and L1 error metric to reduce outliers and aperture effects. The line-to-point match is implemented using weighted hough transform over a normalized correlation matrix. The motion parameters minimize theL1 norm and are computed using linear programming.

[1]  Shmuel Peleg,et al.  Motion Segmentation Using Convergence Properties , 1994 .

[2]  P. Anandan,et al.  Robust multi-sensor image alignment , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[3]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

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

[5]  Michael Werman,et al.  Efficient computation of the most probable motion from fuzzy correspondences , 1998, Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201).

[6]  Michael Werman,et al.  Representing local motion as a probability distribution matrix and object tracking , 1997 .

[7]  Philip H. S. Torr,et al.  Outlier detection and motion segmentation , 1993, Other Conferences.

[8]  Michael Werman,et al.  Real-time object tracking from a moving video camera: a software approach on a PC , 1998, Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201).