Crowd Abnormality Detection Using Optical Flow and GLCM-Based Texture Features

Abstract

Detection of abnormal crowd behavior is one of the important tasks in real-time video surveillance systems for public safety in public places such as subway, shopping malls, sport complexes and various other public gatherings. Due to high density crowded scenes, the detection of crowd behavior becomes a tedious task. Hence, crowd behavior analysis becomes a hot topic of research and requires an approach with higher rate of detection. In this work, the focus is on the crowd management and present an end-to-end model for crowd behavior analysis. A feature extraction-based model using contrast, entropy, homogeneity, and uniformity features to determine the threshold on normal and abnormal activity has been proposed in this paper. The crowd behavior analysis is measured in terms of receiver operating characteristic curve (ROC) & area under curve (AUC) for UMN dataset for the proposed model and compared with other crowd analysis methods in literature to prove its worthiness. YouTube video sequences also used for anomaly detection.

Crowd Management Intelligence Framework: Umrah Use Case

“…It is critical for security reasons and requires fast algorithms, especially in large public gatherings such as Hajj and Umrah, to quickly detect potential threats or disruptions. Recent studies use a variety of algorithms to analyze the movement of people and identify abnormal behaviors [18], [25], [26], [28]- [34], [38]. For example, the algorithm can be designed to detect sudden changes in crowd density, irregular movement patterns [18], or unusual crowd formations [25].…”

“…Some studies have proposed using hand-crafted features and statistical methods for anomaly detection with a high detection rate [26], [28], [29], [31]. For instance, Guo et al [26] developed a method that combines mean shift and kmeans classification for rapid and accurate crowd anomaly detection using video data embedded in a robot.…”

“…For instance, Guo et al [26] developed a method that combines mean shift and kmeans classification for rapid and accurate crowd anomaly detection using video data embedded in a robot. Lalit & Purwar [28] focused on crowd abnormality detection using optical flow and several hand-crafted features including entropy contrast, homogeneity, and gray-level co-occurrence matrix (GLCM) texture features. In another study [29], the authors introduced a method leveraging the histograms of magnitude and momentum to detect and localize anomalies within the crowds.…”