DocumentCode :
3082062
Title :
Optimal multi-scale matching
Author :
Lew, Michael S. ; Huang, Thomas S.
Author_Institution :
Inst. for Adv. Comput. Sci., Leiden Univ., Netherlands
Volume :
1
fYear :
1999
fDate :
1999
Abstract :
The coarse-to-fine search strategy is extensively used in current reported research. However, it has the same problem as any hill climbing algorithm, most importantly, it often finds local instead of global minima. Drawing upon the artificial intelligence literature, we applied an optimal graph search, namely A*, to the problem. Using real stereo and video test sets, we compared the A* method to both template and hill climbing. Our results show that A* has greater accuracy than the ubiquitous coarse-to-fine hill climbing pyramidal search algorithm in both stereo matching and motion tracking
Keywords :
image matching; search problems; hill climbing; motion tracking; multi-scale matching; optimal graph search; search strategy; stereo matching; template; Artificial intelligence; Biological system modeling; Cameras; Computer science; Image coding; Motion analysis; Stereo image processing; Stereo vision; Tracking; Video compression;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on.
Conference_Location :
Fort Collins, CO
ISSN :
1063-6919
Print_ISBN :
0-7695-0149-4
Type :
conf
DOI :
10.1109/CVPR.1999.786922
Filename :
786922
Link To Document :
بازگشت