DocumentCode :
3403974
Title :
Fast approximate energy minimization with label costs
Author :
Delong, Andrew ; Osokin, Anton ; Isack, Hossam N. ; Boykov, Yuri
Author_Institution :
Dept. of Comput. Sci., Univ. of Western Ontario, London, ON, Canada
fYear :
2010
fDate :
13-18 June 2010
Firstpage :
2173
Lastpage :
2180
Abstract :
The α-expansion algorithm has had a significant impact in computer vision due to its generality, effectiveness, and speed. Thus far it can only minimize energies that involve unary, pairwise, and specialized higher-order terms. Our main contribution is to extend α-expansion so that it can simultaneously optimize “label costs” as well. An energy with label costs can penalize a solution based on the set of labels that appear in it. The simplest special case is to penalize the number of labels in the solution. Our energy is quite general, and we prove optimality bounds for our algorithm. A natural application of label costs is multi-model fitting, and we demonstrate several such applications in vision: homography detection, motion segmentation, and unsupervised image segmentation. Our C++/MATLAB implementation is publicly available.
Keywords :
computer vision; image segmentation; minimisation; motion estimation; α-expansion algorithm; C++/MATLAB; computer vision; fast approximate energy minimization; homography detection; label cost; motion segmentation; multimodel fitting; unsupervised image segmentation; Computer science; Computer vision; Cost function; Cybernetics; Image segmentation; Labeling; Mathematics; Minimization methods; Motion detection; Motion segmentation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on
Conference_Location :
San Francisco, CA
ISSN :
1063-6919
Print_ISBN :
978-1-4244-6984-0
Type :
conf
DOI :
10.1109/CVPR.2010.5539897
Filename :
5539897
Link To Document :
بازگشت