View Item 

Exploiting monge structures in optimum subwindow search

Access Status
Open access
Authors
An, Senjian
Peursum, Patrick
Liu, Wan-quan
Venkatesh, Svetha
Chen, Xiaoming
Date
2010
Type
Conference Paper

Metadata
Show full item record
Citation
An, Senjian and Peursum, Patrick and Liu, Wan-quan and Venkatesh, Svetha and Chen, Xiaoming. 2010. Exploiting monge structures in optimum subwindow search, in Davis, L. & Malik, J. (ed), 2010 IEEE conference on Computer Vision and Pattern Recognition, Jun 13 2010, pp. 926-933. San Francisco, California: IEEE.
Source Title
Proceedings of the 2010 IEEE conference on Computer Vision and Pattern Recognition
Source Conference
2010 IEEE conference on Computer Vision and Pattern Recognition
ISBN
Faculty
School of Science and Computing
Department of Computing
Faculty of Science and Engineering
Remarks

Copyright © 2010 IEEE This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

URI
Collection
Abstract

Optimum subwindow search for object detection aims to find a subwindow so that the contained subimage is most similar to the query object. This problem can be formulated as a four dimensional (4D) maximum entry search problem wherein each entry corresponds to the quality score of the subimage contained in a subwindow. For n x n images, a naive exhaustive search requires O(n4) sequential computations of the quality scores for all subwindows. To reduce the time complexity, we prove that, for some typical similarity functions like Euclidian metric, X2 metric on image histograms, the associated 4D array carries some Monge structures and we utilise these properties to speed up the optimum subwindow search and the time complexity is reduced to O(n3). Furthermore, we propose a locally optimal alternating column and row search method with typical quadratic time complexity O(n2). Experiments on PASCAL VOC 2006 demonstrate that the alternating method is significantly faster than the well known efficient subwindow search (ESS) method whilst the performance loss due to local maxima problem is negligible.