Share Email Print
cover

Proceedings Paper

Segmentation of motion textures using mixed-state Markov random fields
Author(s): T. Crivelli; B. Cernuschi-Frías; P. Bouthemy; J. F. Yao
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The aim of this work is to model the apparent motion in image sequences depicting natural dynamic scenes (rivers, sea-waves, smoke, fire, grass etc) where some sort of stationarity and homogeneity of motion is present. We adopt the mixed-state Markov Random Fields models recently introduced to represent so-called motion textures. The approach consists in describing the distribution of some motion measurements which exhibit a mixed nature: a discrete component related to absence of motion and a continuous part for measurements different from zero. We propose several extensions on the spatial schemes. In this context, Gibbs distributions are analyzed, and a deep study of the associated partition functions is addressed. Our approach is valid for general Gibbs distributions. Some particular cases of interest for motion texture modeling are analyzed. This is crucial for problems of segmentation, detection and classification. Then, we propose an original approach for image motion segmentation based on these models, where normalization factors are properly handled. Results for motion textures on real natural sequences demonstrate the accuracy and efficiency of our method.

Paper Details

Date Published: 25 August 2006
PDF: 12 pages
Proc. SPIE 6315, Mathematics of Data/Image Pattern Recognition, Compression, and Encryption with Applications IX, 63150J (25 August 2006); doi: 10.1117/12.674648
Show Author Affiliations
T. Crivelli, Univ. of Buenos Aires (Argentina)
B. Cernuschi-Frías, Univ. of Buenos Aires (Argentina)
CONICET (Argentina)
P. Bouthemy, IRISA/INRIA (France)
J. F. Yao, IRMAR/Univ. of Rennes 1 (France)


Published in SPIE Proceedings Vol. 6315:
Mathematics of Data/Image Pattern Recognition, Compression, and Encryption with Applications IX
Gerhard X. Ritter; Mark S. Schmalz; Junior Barrera; Jaakko T. Astola, Editor(s)

© SPIE. Terms of Use
Back to Top