Monitoring Crowd Movement for Anomaly Detection Using Scale Invariant Feature Transform

Abstract

In order to detect the potentially dangerous arrears and the situation of a crowd in public security systems, the automated analysis of crowd monitoring using surveillance video is playing vital role. Even though many works are focused on the analysis related to the crowd behavior analysis, complexity in algorithm, real time working module and predefined rigid automatically selection rules are the major problems in the behavior analysis crowd detection. This work proposed a real time algorithm to detect the global anomalies in Scale Invariant Feature Transform(SIFT) based on holistic approach. Significantly deviation in the normal behavior from the previously stored data set, that is people running away from the crowd or suddenly gathering into a particular point were consider an the anomalies are the framework of the approach. The experimental result shows that, compared with the existing methods, the proposed method could able to run in real time and have less complexity in algorithm.