Abnormal activity detection in surveillance video scenes

Abstract

Automated detection of abnormal activity assumes a significant task in surveillance applications. This paper presents an intelligent framework video surveillance to detect abnormal human activity in an academic environment that takes into account the security and emergency aspects by focusing on three abnormal activities (falling, boxing and waving). This framework designed to consist of the two essential processes: the first one is a tracking system that can follow targets with identify sets of features to understand human activity and measure descriptive information of each target. The second one is a decision system that can realize if the activity of the target track is "normal" or "abnormal" then energizing alarm when recognized abnormal activities.