A fast incremental approach for accurate measurement of the displacement field

Beghdadi, Azeddine, Mesbah, Mostefa and Monteil, Jerôme (2003) A fast incremental approach for accurate measurement of the displacement field. Image and Vision Computing, 21 4: 383-399.


Author Beghdadi, Azeddine
Mesbah, Mostefa
Monteil, Jerôme
Title A fast incremental approach for accurate measurement of the displacement field
Journal name Image and Vision Computing   Check publisher's open access policy
ISSN 0262-8856
Publication date 2003-04
Sub-type Article (original research)
DOI 10.1016/S0262-8856(03)00014-3
Volume 21
Issue 4
Start page 383
End page 399
Total pages 17
Place of publication Guildford, Surrey
Publisher Butterworths
Language eng
Subject 080104 Computer Vision
Abstract A fast method for accurate measurement of displacement field that combines template matching and differential techniques is proposed. This method, which is able to deal with the problems of non-rigid object movement as well as large inter frame displacements, operates in three steps. First, a sparse displacement field is obtained by a classic template matching technique. Then, this information is propagated through the overall image to obtain a dense displacement field. Finally, this field is considered as approximate solution before the use of classical differential technique for optical flow estimation. To illustrate the efficiency of the proposed procedure, a number of experimental results using both synthetic and real images are presented and discussed. The results show significant improvement over those obtained using standard multigrid approaches, especially in the cases of textured, very structured images or large inter frame displacements.
Keyword Optical flow
Motion estimation;
Template matching;
Cross-correlation
Multiresolution analysis
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status Unknown

Document type: Journal Article
Sub-type: Article (original research)
Collections: Excellence in Research Australia (ERA) - Collection
School of Health and Rehabilitation Sciences Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 4 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 6 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Access Statistics: 38 Abstract Views  -  Detailed Statistics
Created: Fri, 20 Mar 2009, 15:59:39 EST by Jason Parr on behalf of Marketing, Outreach and Corporate Services