Title :
Object tracking using affine structure for point correspondences
Author :
Manku, Gurmeet Singh ; Jain, Pankaj ; Aggarwal, Amit ; Kumar, Lalit ; Banerjee, Subhashis
Author_Institution :
Dept. of Comput. Sci. & Eng., Indian Inst. of Technol., New Delhi, India
Abstract :
A new object tracking algorithm based on affine structure has been developed and it is shown that its performance is better than that of a Kalman filter based correlation tracker. The algorithm is fast, reliable, viewpoint invariant, and insensitive to occlusion and/or individual corner disappearance or reappearance. Detailed experimental analysis on a long real image sequence is also presented
Keywords :
Kalman filters; image matching; image sequences; motion estimation; object recognition; software performance evaluation; tracking; Kalman filter; affine structure; correlation tracker; experimental analysis; image sequence; individual corner disappearance; individual corner reappearance; motion analysis; object tracking algorithm; occlusion; performance; point correspondences; viewpoint invariant; Cameras; Computer science; Image analysis; Image motion analysis; Image sequence analysis; Image sequences; Kalman filters; Matched filters; Motion analysis; Tracking;
Conference_Titel :
Computer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on
Conference_Location :
San Juan
Print_ISBN :
0-8186-7822-4
DOI :
10.1109/CVPR.1997.609403
