Mixed-state models in image motion analysis: theory and applications - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 2007

Mixed-state models in image motion analysis: theory and applications

Abstract

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.
Fichier principal
Vignette du fichier
rapport.pdf (2.65 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00182150 , version 1 (24-10-2007)
inria-00182150 , version 2 (25-10-2007)
inria-00182150 , version 3 (30-10-2007)

Identifiers

  • HAL Id : inria-00182150 , version 3

Cite

Tomas Crivelli, Bruno Cernuschi-Frias, Patrick Bouthemy, Jian-Feng Yao. Mixed-state models in image motion analysis: theory and applications. [Research Report] RR-6335, INRIA. 2007. ⟨inria-00182150v3⟩
798 View
150 Download

Share

Gmail Facebook Twitter LinkedIn More