Show simple item record

dc.contributor.authorAn, S.
dc.contributor.authorPeursum, P.
dc.contributor.authorLiu, Wan-Quan
dc.contributor.authorVenkatesh, S.
dc.date.accessioned2017-01-30T13:44:27Z
dc.date.available2017-01-30T13:44:27Z
dc.date.created2016-09-12T08:36:41Z
dc.date.issued2009
dc.identifier.citationAn, S. and Peursum, P. and Liu, W. and Venkatesh, S. 2009. Efficient algorithms for subwindow search in object detection and localization, pp. 264-271.
dc.identifier.urihttp://hdl.handle.net/20.500.11937/34590
dc.identifier.doi10.1109/CVPRW.2009.5206822
dc.description.abstract

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) for n × n 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 branchand- 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 wellsuited for real time object detection. ©2009 IEEE. [1] H. Bay, T. Tuytelaars, and L. J. Gool. SURF: Speeded Up Robust Features. In Proceedings of ECCV, 2006. 1.

dc.titleEfficient algorithms for subwindow search in object detection and localization
dc.typeConference Paper
dcterms.source.startPage264
dcterms.source.endPage271
dcterms.source.title2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
dcterms.source.series2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
dcterms.source.isbn9781424439935
curtin.departmentDepartment of Computing
curtin.accessStatusFulltext not available


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record