Iterative technique for 3-D motion estimation in videophone applications

Date
1994-04
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
Source Title
Proceedings of MELECON '94. Mediterranean Electrotechnical Conference
Print ISSN
Electronic ISSN
Publisher
IEEE
Volume
Issue
Pages
199 - 202
Language
English
Type
Conference Paper
Journal Title
Journal ISSN
Volume Title
Series
Abstract

In object based coding of facial images, the accuracy of motion and depth parameter estimates strongly affects the coding efficiency. We propose an improved algorithm based on stochastic relaxation for 3-D motion and depth estimation that converges to true motion and depth parameters even in the presence of 50% error in the initial depth estimates. The proposed method is compared with an existing algorithm (MBASIC) in case of different number of point correspondences. The simulation results show that the proposed method provides significantly better results than the MBASIC algorithm.

Course
Other identifiers
Book Title
Keywords
Algorithms, Image analysis, Iterative methods, Parameter estimation, Relaxation processes, Three dimensional, Vectors, Video signal processing, Visual communication, White noise, Coding efficiency, Depth estimation, Object based image coding, Stochastic relaxation, Three dimensional motion estimation, Videophone, Voice variance, Image coding
Citation
Published Version (Please cite this version)