DocumentCode :
3489966
Title :
Feature correspondence with constrained global spatial structures
Author :
Zhang, Ziming ; Li, Ze-Nian ; Drew, Mark
Author_Institution :
Sch. of Comput. Sci., Simon Fraser Univ., Vancouver, BC, Canada
fYear :
2009
fDate :
7-10 Nov. 2009
Firstpage :
177
Lastpage :
180
Abstract :
In this paper, we consider the feature correspondence task as a graph matching problem. Our approach tends to maximize a similarity objective function, which consists of not only the feature vectors but also their corresponding constrained global spatial structures, by a new polynomial-time approximate optimization algorithm. This algorithm allows every node in a smaller graph to potentially be linked with any node in a larger graph, and thus it can handle one-to-one, many-to-one, and no match cases. Especially, our approach does not necessarily require a training set. We test on the ¿hotel¿ and ¿house¿ sequences. Matching a pair of frames takes on average 1.24 and 1.22 seconds respectively using a Matlab implementation without any optimization (over an order of magnitude speedup compared to), and with a 2-frame interval our errors are merely 0.07% and 0.09% respectively. Even going up to a 25-frame gap, errors are only 5.66% and 5.00% respectively.
Keywords :
feature extraction; graph theory; optimisation; polynomials; constrained global spatial structures; feature correspondence; graph matching problem; maximization; polynomial-time approximate optimization algorithm; similarity objective function; Computer errors; Computer vision; Constraint optimization; Iterative algorithms; Monte Carlo methods; Parameter estimation; Polynomials; Robot vision systems; Stereo vision; Testing; constrained global spatial structures; feature correspondence; polynomial-time approximate algorithm;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2009 16th IEEE International Conference on
Conference_Location :
Cairo
ISSN :
1522-4880
Print_ISBN :
978-1-4244-5653-6
Electronic_ISBN :
1522-4880
Type :
conf
DOI :
10.1109/ICIP.2009.5414186
Filename :
5414186
Link To Document :
بازگشت