Share Email Print

Proceedings Paper

Accurate segmentation and estimation of parametric motion fields for object-based video coding using mean field theory
Author(s): Radhakrishnan Haridasan; John S. Baras
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We formulate the problem of decomposing a scene into its constituent objects as one of partitioning the current frame into objects comprising it. The motion parameter is modeled as a non-random but unknown quantity and the problem is posed as one of maximum likelihood (ML) estimation. The MRF potential s which characterize the underlying segmentation field are defined in a way that the spatio-temporal segmentation is constrained by the static image segmentation of the current frame. To compute the motion vector and the segmentation simultaneously we use the expectation maximization (EM) algorithm. The E-step of the EM algorithm, which computes the conditional expectation of the segmentation field, now reflects interdependencies more accurately because of neighborhood interactions. We take recourse to mean field theory to compute the expected value of the conditional MRF. Robust M-estimation methods are used int he M-step. To allow for motions of large magnitudes image frames are represented at various scales and the EM procedure is embedded in a hierarchical coarse-to-fine framework. Our formulation results in a highly parallel algorithm that computes robust and accurate segmentations as well as motion vectors for use in low bit rate video coding.

Paper Details

Date Published: 9 January 1998
PDF: 9 pages
Proc. SPIE 3309, Visual Communications and Image Processing '98, (9 January 1998); doi: 10.1117/12.298346
Show Author Affiliations
Radhakrishnan Haridasan, Univ. of Maryland/College Park (United States)
John S. Baras, Univ. of Maryland/College Park (United States)

Published in SPIE Proceedings Vol. 3309:
Visual Communications and Image Processing '98
Sarah A. Rajala; Majid Rabbani, Editor(s)

© SPIE. Terms of Use
Back to Top