You are not logged in.
Openly accessible

Efficient algorithms for subwindow search in object detection and localization

An, Senjian, Peursum, Patrick, Liu, Wanquan and Venkatesh, Svetha 2009, Efficient algorithms for subwindow search in object detection and localization, in CVPR 2009 : Proceeding of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, IEEE, Washington, D. C., pp. 264-271.

Attached Files
Name Description MIMEType Size Downloads
venkatesh-efficientalgorithms-2009.pdf Published version application/pdf 439.54KB 380

Title Efficient algorithms for subwindow search in object detection and localization
Author(s) An, Senjian
Peursum, Patrick
Liu, Wanquan
Venkatesh, SvethaORCID iD for Venkatesh, Svetha orcid.org/0000-0001-8675-6631
Conference name IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2009 : Miami, Fla.)
Conference location Miami, Fla.
Conference dates 20-25 Jun. 2009
Title of proceedings CVPR 2009 : Proceeding of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Editor(s) [Unknown]
Publication date 2009
Conference series IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Start page 264
End page 271
Total pages 8
Publisher IEEE
Place of publication Washington, D. C.
Keyword(s) Australia
computational complexity
computational efficiency
computer vision
electronic switching systems
feature extraction
histograms
image converters
object detection
search problems
Summary 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.
Notes 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.
ISBN 1424439914
9781424439911
ISSN 1063-6919
Language eng
Field of Research 089999 Information and Computing Sciences not elsewhere classified
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category E1.1 Full written paper - refereed
Copyright notice ©2009, IEEE
Persistent URL http://hdl.handle.net/10536/DRO/DU:30044565

Document type: Conference Paper
Collections: School of Information Technology
Open Access Collection
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 11 times in TR Web of Science
Scopus Citation Count Cited 43 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 378 Abstract Views, 380 File Downloads  -  Detailed Statistics
Created: Fri, 20 Apr 2012, 11:32:34 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.