Gibbs random field model based 3-D motion estimation from video sequences

Date
1994
Authors
Alatan, A. A.
Levent, O.
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
Source Title
Proceedings of SPIE - The International Society for Optical Engineering
Print ISSN
0277-786X
Electronic ISSN
Publisher
IEEE
Volume
2308
Issue
Pages
626 - 637
Language
English
Type
Article
Journal Title
Journal ISSN
Volume Title
Series
Abstract

In contrast to previous global 3D motion concept, a Gibbs random field based method, which models local interactions between motion parameters defined at each point on the object, is proposed. An energy function which gives the joint probability distribution of motion vectors, is constructed. The energy function is minimized in order to find the most likely motion vector set. Some convergence problems, due to ill-posedness of the problem, are overcome by using the concept of hierarchical rigidity. In hierarchical rigidity, the objects are assumed to be almost rigid in the coarsest level and this rigidness is weakened at each level until the finest level is reached. The propagation of motion information between levels, is encouraged. At the finest level, each point have a motion vector associated with it and the interaction between these vectors are described by the energy function. The minimization of the energy function is achieved by using hierarchical rigidity, without trapping into a local minimum. The results are promising.

Course
Other identifiers
Book Title
Keywords
Gibbs random field, Motion estimation, Three dimensional motion, Computer vision, Probability, Three dimensional, Video signal processing, Image processing
Citation
Published Version (Please cite this version)