Séminaire de Melle LE Thi Lan, Centre MICA/ORION Inria Sopha Antipolis - Date : 4 juin 2007, 14h00 - Lieu : Centre MICA

Interprète traducteur : le séminaire sera présenté en français

In this seminal, I will present a novel query language for video indexing and retrieval that (1) enables to make queries both at the image level and at the semantic level (2) enables the users to define their own scenarios based on semantic events and (3) retrieves videos with both exact matching and similarity matching.

For a query language, four main issues must be addressed: data modeling, query formulation, query parsing and query matching. In this seminal, I  focus and give contributions on data modeling, query formulation and query matching. Color histograms and SIFT (Scale Invariant Feature Transform) features at the image level and 10 types of events at the semantic level are currently used.

The proposed query language has been tested  for the retrieval of surveillance videos of a metro station. I present also some experimental results on  the database that contains 200 indexed persons and 48 semantic events.