Title :
A parallel feature tracker for extended image sequences
Author :
Szeliski, Richard ; Kang, Sing Bing ; Shum, Heung-Yeung
Author_Institution :
Res. Lab., Digital Equipment Corp., Cambridge, MA, USA
Abstract :
This paper presents a feature tracker for long image sequences based on simultaneously estimating die motions and deformations of a collection of adjacent image patches. By sharing common corner nodes, the patches achieve greater stability than independent patch trackers. Modeling full bilinear deformations enables tracking in sequences which have large non-translational motions and/or foreshortening effects. We demonstrate the advantages of our technique with respect to previous algorithms using experimental results
Keywords :
computer vision; feature extraction; image registration; image sequences; parallel algorithms; bilinear deformations; corner nodes; die motions; extended image sequences; feature tracker; foreshortening; image patches; image sequences; stability; Computer vision; Deformable models; Grasping; Image sequences; Motion estimation; Robot vision systems; Robotics and automation; Surveillance; Tracking; Vehicles;
Conference_Titel :
Computer Vision, 1995. Proceedings., International Symposium on
Conference_Location :
Coral Gables, FL
Print_ISBN :
0-8186-7190-4
DOI :
10.1109/ISCV.1995.477008
