Video Understanding for Complex Activity Recognition

Florent Fusier (1) , Valery Valentin (1) , François Bremond (1, 2) , Monique Thonnat (1) , Mark Borg (3) , David Thirde (3) , James Ferryman (3)

1 PULSAR - Perception Understanding Learning Systems for Activity Recognition
2 ORION - Intelligent environments for the resolution of problems for autonomous systems
3 UOR - University of Reading

This paper presents a real-time video understanding system which automatically recognises activities occuring in environments observed through video surveillance cameras. Our approach consists in three main stages : Scene Tracking, Coherence Maintenance, and Scene Understanding. The main challenges are to provide a robust tracking process to be able to recognise events in outdoor and in real applications conditions, to allow the monitoring of a large scene through a camera network, and to automatically recognise complex events involving several actors interacting with each others. This approach has been validated for Airport Activity Monitoring in the framework of the European project AVITRACK.

Mots clés: Video Surveillance; Video Understanding; Scene Tracking; Activity Recognition; Airport Activity Monitoring

Domaines: Traitement des images [eess.IV]

Florent Fusier, Valery Valentin, François Bremond, Monique Thonnat, Mark Borg, et al.. Video Understanding for Complex Activity Recognition. Machine Vision and Applications, 2007, 18, pp.167-188. ⟨inria-00276936⟩