Tracking Scale-Space Blobs for Video Description
IEEE MultiMedia
Hi-index | 0.00 |
We present an original approach for motion-based retrieval involving partial query. More precisely, we propose an unified statistical framework both to extract entities of interest in video shots and to achieve the associated content-based characterization to be exploited for retrieval issues. These two stages rely on the characterization of scene activity in video sequences based on a non-parametric statistical modeling of motion information. Areas comprising relevant scene activity are extracted from an ascendant hierarchical classification applied to the adjacency graph of an initial block-based partition of the image. Therefore, given a video base, we are able to construct a base of samples of entities of interest characterized by their associated scene activity model. The retrieval operations is then formulated as a Bayesian inference issue using the MAP criterion.We report different results of extraction of entities of interest in video sequences and examples of retrieval operations performed on a video base composed of a hundred samples.