Vision based smart crowd surveillance system

Abstract

Video surveillance has become one of the important topics and research interests among researchers nowadays due to the increasing need for security especially after the 9/11 tragedy. Video surveillance systems involve processing vast amounts of image data in a timely manner for the purpose of extracting useful information. Visual analysis of human motion is currently one of the most active researches for smart video surveillance system. Human motion analysis deals with the detection, tracking and recognition of people, and generally, the understanding of human behaviors, from image sequences involving humans. The aim of this project is to develop algorithms suitable for implementation in human detection and posture classification, tracking and activity/event understanding/interpretation tasks.