Identification of Anomalous Behavioral Patterns in Crowd Scenes

Abstract

Real time crowd anomaly detection and analyses has become an active and challenging area of research in computer vision since the last decade. The emerging need of crowd management and crowd monitoring for public safety has widen the countless paths of deep learning methodologies and architectures. Although, researchers have developed many sophisticated algorithms but still it is a challenging and tedious task to manage and monitor crowd in real time. The proposed research work focuses on detection of local and global anomaly detection of crowd. Fusion of spatial-temporal features assist in differentiation of feature trained using Mask R-CNN with Resnet101 as a backbone architecture for feature extraction. The data from, BIWI Walking Pedestrian dataset and the Crowds-By-Examples (CBE) dataset and Self-Generated dataset has been used for experimentation. The data deals with different situations like one set of data deals with normal situations like people walking and acting individually, in a group or in a dense crowd. The other set of data contains images four unique anomalies like fight, accident, explosion and people behaving normally. The simulated results show that in terms of precision and recall, our system performs well with Self-Generated dataset. Moreover, our system uses an early stopping mechanism, which allows our system to outperform to make our model efficient. That is why, on 89th epoch our system starts generating finest results.

A Cloud Exhibition Hall System of Extended Reality Using Apriori Algorithm

“…The system realizes the rotation and movement functions. The first-person movement is completed by the SimpleMove() method of the CharacterController component, and the first-person rotation is completed by the Rotate() method of the Transform component [23] .The interactive display of the product mainly realizes the collision detection of the first-person game object controlled by the user to the animation works and the playback of the animation [24] . The products are stored in the form of an array, and the objects in the collision scene are determined by the collision detection of the trigger, and the corresponding products of the collision objects are detected circularly [25] .…”

Crowd Management Intelligence Framework: Umrah Use Case

“…These simulations facilitate the creation of different crowd scenarios, allowing an in-depth evaluation of diverse management strategies. Alternatively, other researchers have developed models leveraging deep learning (DL) techniques to detect or predict crowd patterns [14]- [18], [30], [36], [38]. These techniques include Convolutional Neural Network (CNN) [15], [16], [18], [36], Fully CNN (FCNN) [14], YOLO net v4 [17], Faster Region-based CNN (Faster R-CNN) [12], Generative Adversarial Network (GAN) [38], Mask R-CNN with Resnet [30], and Random Forests [18].…”

“…Alternatively, other researchers have developed models leveraging deep learning (DL) techniques to detect or predict crowd patterns [14]- [18], [30], [36], [38]. These techniques include Convolutional Neural Network (CNN) [15], [16], [18], [36], Fully CNN (FCNN) [14], YOLO net v4 [17], Faster Region-based CNN (Faster R-CNN) [12], Generative Adversarial Network (GAN) [38], Mask R-CNN with Resnet [30], and Random Forests [18]. This study focuses on the application of crowd anomaly detection using sensorbased data in crowd management within the context of Hajj and Umrah.…”

“…This method captures the spatial and temporal characteristics of crowd movement to identify abnormal behaviors. Naik & Thimmaiah [31] Recent studies have used deep learning techniques for crowd anomaly detection [18], [30], [33], [34], [38]. Direkoglu [33] proposed a method that uses motion information images and CNN for abnormal crowd behavior detection.…”

“…This approach aggregates the predictions of multiple CNN networks to improve the accuracy of anomaly detection. Nauman and Shoaib [30] proposed a DL model for the identification of anomalous behavioral patterns in crowd scenes using spatial-temporal features and Mask R-CNN with Resnet101 architecture. They focused on both local and global anomaly detection in crowds.…”