Object based 3-D motion and structure estimation
Author
Alatan, A. Aydın
Onural, Levent
Date
1996Source Title
Proceedings of the International Conference on Image Processing, IEEE 1995
Publisher
IEEE
Pages
390 - 393
Language
English
Type
Conference PaperItem Usage Stats
171
views
views
122
downloads
downloads
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.
Keywords
AlgorithmsGibbs 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