Recognition of normal and abnormal human actions

Abstract

This paper presents an intelligent framework video surveillance system in an academic environment that takes into account the security and emergency aspects. The system proposes an abnormal human activity classification by the detection motion algorithm based on the Gaussian mixture model (GMM) followed by the Fuzzy C-Means (FCM) segmentation algorithm. It combines HARRIS-SIFT algorithms together to extract features, and the Kalman Filter for tracking targets. Finally, the K-Nearest Neighbor (KNN) algorithm used for the classification of the activities that belong to three different datasets tested. The results show the efficiency of the system: the datasets have the accuracy ratio 97%, the detection ratio is %97, and the false alarm ratio is 4%.