Visual Analysis and Recognition of Crowd Behavior by Principal Component Analysis

Authors

  • Hocine Chebi Laboratoire d’Automatique appliquée ,Faculty of Hydrocarbons and Chemistry, University M’hamed Bougara Boumerdès
  • Dalila Acheli Laboratoire d’Automatique appliquée ,Faculty of Engineering, University M’hamed Bougara Boumerdès
  • Mohamed Kesraoui Laboratoire d’Automatique appliquée , Faculty of Hydrocarbons and Chemistry, University M’hamed Bougara Boumerdès

DOI:

https://doi.org/10.51485/ajss.v1i2.24

Keywords:

Visual analysis, crowd behavior, matrices of covariance, intelligent video surveillance, anomaly

Abstract

The analysis of the human behavior from video is a wide field of the vision by computer. In this work, we are presenting mainly a new approach and method of detects behavior or abnormal events continuous of crowd in the case of the dangerous situations. These scenes are characterized by the presence of a great number of people in the camera’s field of vision. A major problem is the development of an autonomous approach for the management of a great number of anomalies which is almost impossible to carry out by operators. We present in this paper an approach for the anomalies detection, the visual sequences of the video are detected like behavior normal or abnormal based on the measurement and the extraction of the points by the optical flow, then calculations of the distance between the matrices of covariance of the distributions of the vectors of movement calculated on the consecutive reinforcements.

Downloads

Download data is not yet available.

Downloads

Published

2021-02-02

How to Cite

[1]
Chebi, H. , Acheli, D. and Kesraoui, M. 2021. Visual Analysis and Recognition of Crowd Behavior by Principal Component Analysis. Algerian Journal of Signals and Systems . 1, 2 (Feb. 2021), 99-108. DOI:https://doi.org/10.51485/ajss.v1i2.24.

Issue

Section

Articles