Statistical Motion-Based Retrieval with Partial Query

We present an original approach for motion-based retrieval involving partial query. More precisely, we propose an uni ed 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 classi cation 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 di erent results of extraction of entities of interest in video sequences and examples of retrieval operation...

• Type: Conference
• Year: 2000
• Where: VISUAL
• Authors: Ronan Fablet, Patrick Bouthemy
• Keywords: Information Management, Retrieval Operations, Scene Activity, Video Sequences, VISUAL 2000