Name
Title | ||
|---|---|---|
Nonparametric motion characterization using causal probabilistic models for video indexing and retrieval. |
Abstract | ||
|---|---|---|
This paper describes an original approach for content-based video indexing and retrieval. We aim at providing a global interpretation of the dynamic content of video shots without any prior motion segmentation and without any use of dense optic flow fields. To this end, we exploit the spatio-temporal distribution, within a shot, of appropriate local motion-related measurements derived from the spatio-temporal derivatives of the intensity function. These distributions are then represented by causal Gibbs models. To be independent of camera movement, the motion-related measurements are computed in the image sequence generated by compensating the estimated dominant image motion in the original sequence. The statistical modeling framework considered makes the exact computation of the conditional likelihood of a video shot belonging to a given motion or more generally to an activity class feasible. This property allows us to develop a general statistical framework for video indexing and retrieval with query-by-example. We build a hierarchical structure of the processed video database according to motion content similarity. This results in a binary tree where each node is associated to an estimated causal Gibbs model. We consider a similarity measure inspired from Kullback-Leibler divergence. Then, retrieval with query-by-example is performed through this binary tree using the maximum a posteriori (MAP) criterion. We have obtained promising results on a set of various real image sequences. |
Year | DOI | Venue |
|---|---|---|
2002 | 10.1109/TIP.2002.999674 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
content-based retrieval,image sequences,maximum likelihood estimation,motion compensation,motion estimation,probability,query processing,statistical analysis,trees (mathematics),video databases,Kullback-Leibler divergence,MAP criterion,binary tree,causal probabilistic models,conditional likelihood,content-based video indexing,content-based video retrieval,estimated causal Gibbs model,image motion compensation,image sequence,intensity function,local motion-related measurements,maximum a posteriori criterion,maximum likelihood estimation,motion content similarity,nonparametric motion characterization,query-by-example,spatio-temporal distribution,statistical modeling,video database,video shots | Computer vision,Block-matching algorithm,Similarity measure,Pattern recognition,Motion compensation,Search engine indexing,Binary tree,Artificial intelligence,Maximum a posteriori estimation,Real image,Motion estimation,Mathematics | Journal |
Volume | Issue | ISSN |
11 | 4 | 1057-7149 |
Citations | PageRank | References |
37 | 1.89 | 37 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ronan Fablet | 1 | 102 | 6.88 |
| Patrick Bouthemy | 2 | 2675 | 286.70 |
| Patrick Pérez | 3 | 6529 | 391.34 |