Effective algorithms for subwindow search in object detection and localization
|dc.contributor.editor||Huttenlocher, Medioni and Rehg|
|dc.identifier.citation||An, Senjian and Peursum, Patrick and Liu, Wan-quan and Venkatesh, Svetha. 2009. Effective algorithms for subwindow search in object detection and localization, in Huttenlocher and Medioni and Rehg (ed), CVPR 2009, Jun 20 2009, pp. 264-271.Miami,FL,USA: IEEE Computer society.|
Recently, a simple yet powerful branch-and-bound method called Efficient Subwindow Search (ESS) was developed to speed up sliding window search in object detection. A major drawback of ESS is that its computational complexity varies widely from O(n2) to O(n4) form matrices. Our experimental experience shows that the ESS's performance is highly related to the optimal confidence levels which indicate the probability of the object's presence. In particular, when the object is not in the image, the optimal subwindow scores low and ESS may take a large amount of iterations to converge to the optimal solution and so perform very slow. Addressing this problem, we present two significantly faster methods based on the linear-time Kadane's Algorithm for 1D maximum subarray search. The first algorithm is a novel, computationally superior branch-and-bound method where the worst case complexity is reduced to O(n3). Experiments on the PASCAL VOC 2006 data set demonstrate that this method is significantly and consistently faster (approximately 30 times faster on average) than the original ESS. Our second algorithm is an approximate algorithm based on alternating search, whose computational complexity is typically O(n2). Experiments shows that (on average) it is 30 times faster again than our first algorithm, or 900 times faster than ESS. It is thus well suited for real time object detection.
|dc.publisher||IEEE Computer society|
|dc.title||Effective algorithms for subwindow search in object detection and localization|
|dcterms.source.title||2009 IEEE Conference on computer vision and pattern recognition|
|dcterms.source.series||2009 IEEE Conference on computer vision and pattern recognition|
|dcterms.source.conference-start-date||Jun 20 2009|
Copyright © 2009 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.
|curtin.faculty||School of Science and Computing|
|curtin.faculty||Department of Computing|
|curtin.faculty||Faculty of Science and Engineering|