Authors:
Tomas Crivelli
1
;
Bruno Cernuschi-Frias
2
;
Patrick Bouthemy
3
and
Jian-Feng Yao
4
Affiliations:
1
Faculty of Engineering, University of Buenos Aires, Argentina
;
2
Faculty of Engineering, University of Buenos Aires; CONICET, Argentina
;
3
IRISA/INRIA, France
;
4
IRMAR/Univ. of Rennes 1, France
Keyword(s):
Motion analysis, Markov random fields, image content classification, dynamic textures.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computer Vision, Visualization and Computer Graphics
;
Data Manipulation
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Image and Video Analysis
;
Methodologies and Methods
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Soft Computing
;
Statistical Approach
Abstract:
The aim of this work is to model, learn and recognize, dynamic contents in video sequences, displayed mostly
by natural scene elements, such as rivers, smoke, moving foliage, fire, etc. We adopt the mixed-state Markov random fields modeling recently introduced to represent the so-called motion textures. The approach consists
in describing the spatial distribution of some motion measurements which exhibit values of two types: a discrete component related to the absence of motion and a continuous part for measurements different from zero. Based on this, we present a method for recognition and classification of real motion textures using the generative statistical models that can be learned for each motion texture class. Experiments on sequences from the DynTex dynamic texture database demonstrate the performance of this novel approach.