Moving object segmentation using phase information

Shi Wei Gao, Lei Guo, Liang Chen, Yong Yu

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

Abstract

In order to get moving object in video frames, a segmentation method is proposed. The phase-based method is devised for detection of moving object boundary area in the video frame. This boundary detection scheme is based on the characteristics of a phase-matched difference image frame, and based on the assessment of the phase-matched difference between image frames. It is shown to be sensitive to even small disruptions to a consistent motion field using this segment scheme. Then, we use active contour model to find the final boundary based on the boundary area we found using phase information. The eventual results demonstrate the efficiency of the proposed moving object segmentation method.

Original languageEnglish
Title of host publicationProceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR '07
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages397-402
Number of pages6
ISBN (Print)1424410665, 9781424410668
DOIs
StatePublished - 2007
Event2007 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR '07 - Beijing, China
Duration: 2 Nov 20074 Nov 2007

Publication series

NameProceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR '07
Volume1

Conference

Conference2007 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR '07
Country/TerritoryChina
CityBeijing
Period2/11/074/11/07

Keywords

  • Active contour model
  • Boundary detection
  • Moving object segmentation
  • Phase detection

Fingerprint

Dive into the research topics of 'Moving object segmentation using phase information'. Together they form a unique fingerprint.

Cite this