A Framework Dealing with Uncertainty for Complex Event Recognition

Abstract

This paper presents a constraint-based approach forvideo event recognition with probabilistic reasoning forhandling uncertainty. The main advantage of constraintbasedapproaches is the possibility for human expert tomodel composite events with complex temporal constraints.But the approaches are usually deterministic and do notenable the convenient mechanism of probability reasoningto handle the uncertainty. The first advantage of the proposedapproach is the ability to model and recognize compositeevents with complex temporal constraints. The secondadvantage is that probability theory provides a consistentframework for dealing with uncertain knowledge for arobust and reliable recognition of complex event. This approachis evaluated with 4 real healthcare videos and a publicvideo ETISEO’06. The results are compared with stateof the art method. The comparison shows that the proposedapproach improves significantly the process of recognitionand characterizes the likelihood of the recognized events.