venkatesh-exploitingmonge-2010.pdf (158.86 kB)
Exploiting monge structures in optimum subwindow search
conference contribution
posted on 2010-01-01, 00:00 authored by S An, P Peursum, W Liu, Svetha VenkateshSvetha Venkatesh, X ChenOptimum 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, χ2 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.
History
Event
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2010 : San Francisco, Calif.)Pagination
926 - 933Publisher
IEEELocation
San Francisco, Calif.Place of publication
[San Francisco, Calif.]Publisher DOI
Start date
2010-06-13End date
2010-06-18ISSN
1063-6919ISBN-13
9781424469840Language
engNotes
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.Publication classification
E1.1 Full written paper - refereedCopyright notice
2010, IEEETitle of proceedings
CVPR 2010 :Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern RecognitionUsage metrics
Categories
No categories selectedKeywords
electronic switching systemsfeature extractionhistogramsobject detectionperformance losssearch methodssearch problemsshapeupper boundScience & TechnologyTechnologyPhysical SciencesComputer Science, Artificial IntelligenceComputer Science, Software EngineeringMathematics, AppliedImaging Science & Photographic TechnologyComputer ScienceMathematicsSUPPORT VECTOR MACHINE
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC