Measurement Function Design for Visual Tracking Applications

Smith, A. W. B. and Lovell, B. C. (2006). Measurement Function Design for Visual Tracking Applications. In: Y. Tang, P. Wang, G. Lorette and D. S. Yeung, Proceedings of the 18th International Conference on Pattern Recognition (ICPR 2006). 18th International Conference on Pattern Recognition (ICPR 2006), Hong Kong, (789-792). 20-24 August, 2006.

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
Smith-Measurement.pdf Smith-Measurement.pdf application/pdf 519.71KB 149

Author Smith, A. W. B.
Lovell, B. C.
Title of paper Measurement Function Design for Visual Tracking Applications
Conference Paper Type Fully Published Paper
Conference name 18th International Conference on Pattern Recognition (ICPR 2006)    (ERA 2010 Rank B)
Conference location Hong Kong
Conference dates 20-24 August, 2006
Proceedings title Proceedings of the 18th International Conference on Pattern Recognition (ICPR 2006)
Editor Y. Tang
P. Wang
G. Lorette
D. S. Yeung
Place published U.S.A.
Publisher IEEE
Publication date 2006
Volume number 1
ISBN 0-7695-2512-0
Start page 789
End page 792
Total pages 4
Language eng
Abstract/Summary Extracting human postural information from video sequences has proved a difficult research question. The most successful approaches to date have been based on particle filtering, whereby the underlying probability distribution is approximated by a set of particles. The shape of the underlying observational probability distribution plays a significant role in determining the success, both accuracy and efficiency, of any visual tracker. In this paper we compare approaches used by other authors and present a cost path approach which is commonly used in image segmentation problems, however is currently not widely used in tracking applications.
Subjects 280208 Computer Vision
280203 Image Processing
Keyword iris-research
nictawp1
Q-Index Code E1
Additional Notes Digital Object Identifier 10.1109/ICPR.2006.785
 
Versions
Version Filter Type
Citation counts: Thomson Reuters Citation Count Cited 0 times in Thomson Reuters Researcher ID
Access Statistics: 149 Abstract Views, 150 File Downloads  -  Detailed Statistics
Created: Tue, 15 May 2007, 14:56:28 EST by Prof Brian Lovell on behalf of Social Sciences and Humanities Library Service  -  Detailed History