Object based 3-D motion and structure estimation

Date
1996
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
Source Title
Proceedings of the International Conference on Image Processing, IEEE 1995
Print ISSN
Electronic ISSN
Publisher
IEEE
Volume
Issue
Pages
390 - 393
Language
English
Type
Conference Paper
Journal Title
Journal ISSN
Volume Title
Series
Abstract

Motion analysis is the most crucial part of object-based coding. A motion in 3-D environment can be analyzed better by using a 3-D motion model compared to its 2-D counterpart and hence may improve coding efficiency. Gibbs formulated joint segmentation and estimation of 2-D motion not only improves performance, but also generates robust point correspondences which are necessary for linear 3-D motion estimation algorithms. Estimated 3-D motion parameters are used to find the structure of the previously segmented objects by minimizing another Gibbs energy. Such an approach achieves error immunity compared to linear algorithms. Experimental results are promising and hence the proposed motion and structure analysis method is a candidate to be used in object-based (or even knowledge-based) video coding schemes.

Course
Other identifiers
Book Title
Keywords
Algorithms, Gibbs free energy, Image compression, Image segmentation, Knowledge based systems, Mathematical models, Optical flows, Parameter estimation, Three dimensional, Vectors, Exponential joint distribution, Motion analysis, Motion estimation algorithms, Object segmentation, Image coding
Citation
Published Version (Please cite this version)