 |
|
 |
|
|
|
| HAL: inria-00182150, version 3 |
| See detailed view |  BibTeX,EndNote,... |
|
|
| Available versions | v3 (2007-10-31) |
|
|
|
|
| Mixed-state models in image motion analysis: theory and applications |
|
|
| Tomas Crivelli 1, 2Bruno Cernuschi-Frias 1, 3 |
|
|
| (2007) |
|
|
|
| The aim of this work is to model the apparent motion in image sequences depicting textured motion patterns. We adopt the mixed-state Markov Random Fields (MRF) models recently introduced to represent the so-called motion textures. The approach consists in describing the spatial distribution of local motion measurements which exhibit values of two types: a discrete component related to the absence of motion and a continuous part for actual measurements. The former accounts for symbolic information that is beyond the null value of motion itself, providing crucial information on the dynamic content of the scene. We propose several significant extensions and we give theoretical results regarding this model, which are of great importance for its application to motion analysis. In this context, dynamic content recognition applications are analyzed. We have defined a motion texture classification scheme, and a motion texture segmentation method exploiting this modeling. Results on real examples demonstrate the accuracy and efficiency of our method. |
|
|
|
|
|
|
|
|
|
|
|
| 1: | VISTA (INRIA - IRISA) |
|
|
|
CNRS : UMR6074 – INRIA – Université de Rennes 1 – Institut National des Sciences Appliquées (INSA) |
|
|
| 2: | Facultad de Ingenieria [Buenos Aires] (LFD) |
|
|
|
Universidad de Buenos Aires |
|
|
| 3: | Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET) |
|
|
|
University of Buenos Aires |
|
|
| 4: | Institut de Recherche Mathématique de Rennes (IRMAR) |
|
|
|
CNRS : UMR6625 – Université de Rennes 1 – École normale supérieure de Cachan - ENS Cachan – Institut National des Sciences Appliquées (INSA) : - RENNES – Université de Rennes II - Haute Bretagne |
|
|
|
|
|
|
|
|
|
| Domain | : | Mathematics/Probability |
|
|
| Markov random fields – dynamic textures – mixed-state models – segmentation – classification |
|
|
|
| Attached file list to this document: | ||||||||||
|
||||||||||
|
|
|
| inria-00182150, version 3 | |
| http://hal.inria.fr/inria-00182150 | |
| oai:hal.inria.fr:inria-00182150 | |
| From: Bruno Cernuschi-Frias | |
| Submitted on: Tuesday, 30 October 2007 21:34:52 | |
| Updated on: Wednesday, 24 March 2010 14:28:07 | |
