Abstract

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.

Highlights

  • 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

  • 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 present a platform used to generate activity monitoring systems dedicated to specific applications, we 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

Read more

Summary

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. We have built with VSIP three AMSs which have been validated by end-users: an activity monitoring system in metro stations, a bank agency monitoring system, and a lock chamber access control system for buildings security These applications present some characteristics which make them interesting for research purposes: the observed scenes vary from large open spaces (like metro halls) to small and closed spaces (corridors and lock chambers); cameras can have both nonoverlapping (like in metro stations and lock chambers systems) and overlapping fields of view (metro stations and bank agencies); humans can interact with the equipment (like ticket vending machines or access control barriers, bank safes and lock chambers doors) either in simple ways (open/close) or in more complex ones

STATE OF THE ART
PLATFORM OVERVIEW
MODULARITY AND FLEXIBILITY OF THE ARCHITECTURE
SEPARATION BETWEEN ALGORITHMS AND A PRIORI KNOWLEDGE
AUTOMATIC EVALUATION
INTERACTION BETWEEN THE END-USERS AND THE DEVELOPERS
END-USER ASSESSMENT AND VALIDATION FOR METRO STATIONS MONITORING APPLICATION
End-user assessment
Technical validation
Ground-truth of the validation data
Scenario recognition validation results
Bank agency monitoring system
Lock chamber access monitoring system
Findings
10. CONCLUSION

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.