Publication

2003-12

English

http://archimer.ifremer.fr/doc/00000/10714/9323.pdf (Publisher's official version, 0.64 Mo)

2003 IEEE

Fablet Ronan, Bouthemy P

IFREMER, LASAA, F-29280 Plouzane, France.
IRISA, INRIA, F-35042 Rennes, France.

Ieee Transactions On Pattern Analysis And Machine Intelligence (0162-8828) (Ieee Computer Soc), 2003-12 , Vol. 25 , N. 12 , P. 1619-1624

41

Mathematics-Computer Science

nonparametric motion analysis, motion recognition, multiscale analysis, Gibbs models, co occurrences, ML criterion

A new approach for motion characterization in image sequences is presented. It relies on the probabilistic modeling of temporal and scale co-occurrence distributions of local motion-related measurements directly computed over image sequences. Temporal multiscale Gibbs models allow us to handle both spatial and temporal aspects of image motion content within a unified statistical framework. Since this modeling mainly involves the scalar product between co-occurrence values and Gibbs potentials, we can formulate and address several fundamental issues: model estimation according to the ML criterion (hence, model training and learning) and motion classification. We have conducted motion recognition experiments over a large set of real image sequences comprising various motion types such as temporal texture samples, human motion examples, and rigid motion situations.