Segmentation via annealed motion estimates

Ikhlas Abdel-Qader, Tomislav Bujanovic

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A segmentation and motion estimation are two problems that require accurate estimation for many applications in computer vision and image analysis. In this paper, an algorithm that is based on motion information and restored spatial information to segment the scene is presented. This algorithm has minimum dependency on noisy data and the motion vectors are estimated using a deterministic mean field annealing (MFA) framework. The algorithms results are very good using synthetic and real world sequences.

Original languageEnglish (US)
Title of host publication2009 IEEE MTT-S International Microwave Workshop Series on Signal Integrity and High-Speed Interconnects, IMWS 2009
PublisherIEEE Computer Society
Pages297-301
Number of pages5
ISBN (Print)9780780387508
DOIs
StatePublished - Jan 1 2004
Externally publishedYes
Event2004 IEEE Electro/Information Technology Conference, EIT 2004 - Milwaukee, WI, United States
Duration: Aug 26 2004Aug 27 2004

Publication series

Name2004 IEEE Electro/Information Technology Conference, EIT 2004

Other

Other2004 IEEE Electro/Information Technology Conference, EIT 2004
CountryUnited States
CityMilwaukee, WI
Period8/26/048/27/04

ASJC Scopus subject areas

  • Information Systems
  • Software
  • Biomedical Engineering
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Segmentation via annealed motion estimates'. Together they form a unique fingerprint.

  • Cite this

    Abdel-Qader, I., & Bujanovic, T. (2004). Segmentation via annealed motion estimates. In 2009 IEEE MTT-S International Microwave Workshop Series on Signal Integrity and High-Speed Interconnects, IMWS 2009 (pp. 297-301). [4569396] (2004 IEEE Electro/Information Technology Conference, EIT 2004). IEEE Computer Society. https://doi.org/10.1109/EIT.2004.4569396