Design and Assessment of an Intelligent Activity Monitoring Platform

Alberto Avanzi, François Bremond, Christophe Tornieri and Monique Thonnat

RESUME:

We are interested in designing a reusable and robust activity monitoring platform. In this paper we propose three good properties that an activity monitoring platform should have to enable its reusability for diffferent applications and to insure performance quality: 1) modularity and flexibility of the architecture, 2) separation between the algorithms and the a priori knowledge they use, and 3) automatic evaluation of algorithm results. We then propose a development methodology to fulfill the last two properties. The methodology consists in the interaction between end-users and developers during the whole development of a specific monitoring system for a new application. To validate our approach, first we present a platform that we use to generate activity monitoring systems dedicated to specific applications. Then we explain how we have managed to give concrete expression to these properties in the platform. Finally we describe in details the technical validation and the end-user assessment of an automatic metro monitoring system built with the platform. We give the corresponding validation results for two other systems built with the same platform: a bank agency monitoring system and a building lock chamber access control system.

Mots clé: Intelligent vision platform, video surveillance, autonomous system, evaluation, generic platform.

Pour télécharger cet article,  cliquez ici

BibTeX reference:

@Article{Avanzi2005,
author =      {A. Avanzi and F. Br\'emond and C. Tornieri and M. Thonnat},
title =       {Design and Assessment of an Intelligent Activity Monitoring Platform},
journal =     {EURASIP Journal on Applied Signal Processing, Special 
Issue on ``Advances in Intelligent Vision Systems: Methods and Applications''},
year =      {2005},
volume =      {14},
number =      {8},
pages =       {2359-2374},
}