A motion parameter estimation algorithm based on the multiresolution edge detection

Bing Wang, Rong Chun Zhao, Yan Ning Zhang, Hong Bo Yu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

This paper presents a novel motion parameter estimation algorithm based on the multiresolution edge detection. First, moving object edges is detected based on wavelet transform between two consecutive frames. Then, edges location of moving objects is generated through multiresolution relevant operator. Finally, moving object vector fields is detected according to its edge location. Based on the edge detection method not only the intraframe intensity information of spatial domain is used, but also the interframe information in temporal domain. Experimental results show that the proposed algorithm is effective with robustness.

Original languageEnglish
Title of host publicationInternational Conference on Machine Learning and Cybernetics
Pages2741-2745
Number of pages5
StatePublished - 2003
Event2003 International Conference on Machine Learning and Cybernetics - Xi'an, China
Duration: 2 Nov 20035 Nov 2003

Publication series

NameInternational Conference on Machine Learning and Cybernetics
Volume5

Conference

Conference2003 International Conference on Machine Learning and Cybernetics
Country/TerritoryChina
CityXi'an
Period2/11/035/11/03

Keywords

  • Edge detection
  • Image sequence
  • Motion estimation
  • Multiresolution
  • Wavelet transform

Fingerprint

Dive into the research topics of 'A motion parameter estimation algorithm based on the multiresolution edge detection'. Together they form a unique fingerprint.

Cite this