Non parametric motion recognition using temporal multiscale Gibbs models

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Volumn 1, Issue , 2001, Pages

  Fablet, R ^a   Bouthemy, P ^a  

^a CAMPUS DE BEAULIEU   (France)

Author keywords

[No Author keywords available]

Indexed keywords

FEATURE EXTRACTION; MOTION ESTIMATION; OBJECT RECOGNITION; PROBABILISTIC LOGICS; STATISTICAL METHODS;

IMAGE SEQUENCES;

IMAGE ANALYSIS;

EID: 0035683811     PISSN: 10636919     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. Ill-posed problems in early vision
2. Movement, activity, and action: The role of knowledge in the perception of motion
3. Texture recognition using a non-parametric multi-scale statistical model
4. The representation and recognition of human movement using temporal templates
5. Statistical motion-based video indexing and retrieval
6. Vision and action
7. Stochastic relaxation, Gibbs distribution and the Bayesian restoration of images
8. Texture modeling by multiple pairwise pixel interactions
9. Multimodal estimation of discontinuous optical flow using Markov random fields
10. Determining optical flow
11. Statistics of natural images and models
12. Qualitative recognition of motion using temporal texture
13. Separation of moving regions from background in an image sequence acquired with a mobile camera
14. Exploring video content in extended spatio-tumporal textures
15. A parametric texture model based on joint statistics of complex wavelet coefficients
16. Temporal texture modeling
17. Qualitative spatiotemporal analysis using an oriented energy representation
18. Filters, random fields and maximum entropy (FRAME): Towards a unified theory for texture modeling