Video Sequence Interpretation for Visual Surveillance

Nathanael Rota and Monique Thonnat
INRIA Sophia Antipolis, France

Abstract:

This paper presents recent work done on image understanding in the context of visual surveillance applications. We propose a video understanding framework based on a priori knowledge. More precisely the objective is to infer high level description of human behavior from image sequences. The main motivation of this research activity is the automatic generation of alarms towards human operators if interesting scenarios have been recognized by the system.