Mixed-State Markov Random Fields for Motion Texture Modeling and Segmentation

  title={Mixed-State Markov Random Fields for Motion Texture Modeling and Segmentation},
  author={Tom{\'a}s Crivelli and Bruno Cernuschi-Fr{\'i}as and Patrick Bouthemy and Jian-Feng Yao},
  journal={2006 International Conference on Image Processing},
The aim of this work is to model the apparent motion in image sequences depicting natural dynamic scenes. We adopt the mixed-state Markov random fields (MRF) models recently introduced to represent so-called motion textures. The approach consists in describing the spatial distribution of some motion measurements which exhibit mixed-state nature: a discrete component related to the absence of motion and a continuous part for measurements different from zero. We propose several significative… CONTINUE READING
Highly Cited
This paper has 17 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.
Showing 1-10 of 13 extracted citations


Publications referenced by this paper.
Showing 1-8 of 8 references

Bouthemy , " Motion recognition using non - parametric image motion models estimated from temporal and multiscale coocurrence statistics

  • R. Fablet, P.
  • Pattern Analysis and Machine Intelligence

Similar Papers

Loading similar papers…