Evaluation and Knowledge Representation Formalisms to Improve Video Understanding

LES AUTEURS Benoit Georis, Magali Maziere, François Bremond and Monique Thonnat


This article presents a methodology to build efficient real-time semantic video understanding systems addressing real world problems. In our case, semantic video understanding consists in the recognition of predefined scenario models in a given application domain starting from a pixel analysis up to a symbolic description of what is happening in the scene viewed by cameras. This methodology proposes to use evaluation to acquire knowledge of programs and to represent this knowledge with appropriate formalisms. First, to obtain efficiency, a formalism enables to model video processing programs and their associated parameter adaptation rules. These rules are written by experts after performing a technical evaluation. Second, a scenario formalism enables experts to model their needs and to easily refine their scenario models to adapt them to real-life situations. This refinement is performed with an end-user evaluation. This second part ensures that systems match end-user expectations. Results are reported for scenario recognition performances on real video sequences taken from a bank agency monitoring application.

Mots clé: video understanding, performance evaluation, knowledge representation

Pour télécharger cet article,  cliquez ici

BibTeX reference:

author = {B. Georis and M. Mazière and F. Br\'emond and M. Thonnat},
title = {Evaluation and Knowledge Representation Formalisms to Improve Video Understanding},
booktitle = {to appear in Proceedings of the International Conference on Computer Vision Systems (ICVS'06)},
address = {New-York, NY, USA},
month = {January},
year = {2006},

Dernière mise à jour : 3/11/05