Design and Assessment of an Intelligent Activity Monitoring Platform
- PDF / 2,206,521 Bytes
- 16 Pages / 600 x 792 pts Page_size
- 89 Downloads / 196 Views
Design and Assessment of an Intelligent Activity Monitoring Platform Alberto Avanzi i-DTV Group, Bull SA, avenue Jean Jaur`es, 78340 Les Clayes-Sous-Bois, France Email: alberto.avanzi@sophia.inria.fr
´ Franc¸ois Bremond ORION Group,INRIA Sophia Antipolis, 2004 route des Lucioles, B.P. 93, 06902 Sophia Antipolis Cedex, France Email: francois.bremond@sophia.inria.fr
Christophe Tornieri ORION Group, INRIA Sophia Antipolis, 2004 route des Lucioles, B.P. 93, 06902 Sophia Antipolis Cedex, France Email: christophe.tornieri@sophia.inria.fr
Monique Thonnat ORION Group, INRIA Sophia Antipolis, 2004 route des Lucioles, B.P. 93, 06902 Sophia Antipolis Cedex, France Email: monique.thonnat@sophia.inria.fr Received 26 January 2004; Revised 25 January 2005 We are interested in designing a reusable and robust activity monitoring platform. We propose three good properties that an activity monitoring platform should have to enable its reusability for different 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. To validate our approach, we present a platform used to generate activity monitoring systems dedicated to specific applications, we also describe in details the technical validation and the end-user assessment of an automatic metro monitoring system built with the platform and briefly the validation results for bank agency monitoring and building access control. Keywords and phrases: intelligent vision platform, video surveillance, autonomous system, evaluation, generic platform.
1.
INTRODUCTION
The task of developing algorithms able to recognize human activities in video sequences has been an active field of research for the last ten years. Nevertheless, the lack of genericity and robustness of the proposed solutions is still an open problem. To break down this challenging problem into smaller and easier ones, a possible approach is to limit the field of application to specific activities in well-delimited environments. So the scientific community has led researches on automatic traffic surveillance on highways, on pedestrian and vehicle interaction analysis in parking lots or roundabouts [1], or on human activity monitoring in outdoor (like This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
streets and public places) or indoor (like metro stations, bank agencies, houses) environments [2, 3, 4]. We believe that to obtain a reusable and performant activity monitoring platform, a unique global and sophisticated algorithm is not adapted because it cannot handle the large diversity o
Data Loading...
