DocumentCode :
2089242
Title :
Piecewise Image Registration in the Presence of Multiple Large Motions
Author :
Bhat, Pravin ; Zheng, Ke Colin ; Snavely, Noah ; Agarwala, Aseem ; Agrawala, Maneesh ; Cohen, Michael F. ; Curless, Brian
Author_Institution :
University of Washington, USA
Volume :
2
fYear :
2006
fDate :
2006
Firstpage :
2491
Lastpage :
2497
Abstract :
We present a technique for computing a dense pixel correspondence between two images of a scene containing multiple large, rigid motions. We model each motion with either a homography (for planar objects) or a fundamental matrix. The various motions in the scene are first extracted by clustering an initial sparse set of correspondences between feature points; we then perform a multi-label graph cut optimization which assigns each pixel to an independent motion and computes its disparity with respect to that motion. We demonstrate our technique on several example scenes and compare our results with previous approaches.
Keywords :
Birds; Computer vision; Image reconstruction; Image registration; Labeling; Layout; Markov random fields; Pixel; Sparse matrices; Transmission line matrix methods;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on
ISSN :
1063-6919
Print_ISBN :
0-7695-2597-0
Type :
conf
DOI :
10.1109/CVPR.2006.225
Filename :
1641059
Link To Document :
بازگشت