Violent Crowd Research Articles

Violent crowd flow detection from surveillance cameras using deep transfer learning–gated recurrent unit

AbstractViolence can be committed anywhere, even in crowded places. It is hence necessary to monitor human activities for public safety. Surveillance cameras can monitor surrounding activities but require human assistance to continuously monitor every incident. Automatic violence detection is needed for early warning and fast response. However, such automation is still challenging because of low video resolution and blind spots. This paper uses ResNet50v2 and the gated recurrent unit (GRU) algorithm to detect violence in the Movies, Hockey, and Crowd video datasets. Spatial features were extracted from each frame sequence of the video using a pretrained model from ResNet50V2, which was then classified using the optimal trained model on the GRU architecture. The experimental results were then compared with wavelet feature extraction methods and classification models, such as the convolutional neural network and long short‐term memory. The results show that the proposed combination of ResNet50V2 and GRU is robust and delivers the best performance in terms of accuracy, recall, precision, and F1‐score. The use of ResNet50V2 for feature extraction can improve model performance.

Conditional autoregressive-tunicate swarm algorithm based generative adversarial network for violent crowd behavior recognition

Conditional autoregressive-tunicate swarm algorithm based generative adversarial network for violent crowd behavior recognition

Anomaly Based Camera Prioritization in Large Scale Surveillance Networks

Digital surveillance systems are ubiquitous and continuously generate massive amounts of data, and manual monitoring is required in order to recognise human activities in public areas. Intelligent surveillance systems that can automatically ide.pngy normal and abnormal activities are highly desirable, as these would allow for efficient monitoring by selecting only those camera feeds in which abnormal activities are occurring. This paper proposes an energy-efficient camera prioritisation framework that intelligently adjusts the priority of cameras in a vast surveillance network using feedback from the activity recognition system. The proposed system addresses the limitations of existing manual monitoring surveillance systems using a three-step framework. In the first step, the salient frames are selected from the online video stream using a frame differencing method. A lightweight 3D convolutional neural network (3DCNN) architecture is applied to extract spatio-temporal features from the salient frames in the second step. Finally, the probabilities predicted by the 3DCNN network and the metadata of the cameras are processed using a linear threshold gate sigmoid mechanism to control the priority of the camera. The proposed system performs well compared to state-of-the-art violent activity recognition methods in terms of efficient camera prioritisation in large-scale surveillance networks. Comprehensive experiments and an evaluation of activity recognition and camera prioritisation showed that our approach achieved an accuracy of 98% with an F1-score of 0.97 on the Hockey Fight dataset, and an accuracy of 99% with an F1-score of 0.98 on the Violent Crowd dataset.

Uncivil Performances: National Politics of the Sri Lankan Theater Space

The 2016 performance of Dutu Thena Allanu (Wanted) by Kaushalya Fernando in the Ediriweera Sarachchandra Open-Air Theater, at the University of Peradeniya, Sri Lanka, was brought to a halt, mid-performance, by a violent crowd in the audience that determined the play to be inappropriate for such a “sacred” performance space. Better known as “Wala,” the Ediriweera Sarachchandra Open-Air Theater is considered unique and unlike any other performance space in Sri Lanka primarily due to its origins being tied to the playwright and dramatist Ediriweera Sarachchandra whose plays, such as Maname (1956) and Sinhabahu (1961), hold an unparalleled significance within the new patriotic discursive and theatrical re-performance of quintessential Sri Lankan postcolonial theater. In this study, I examine how this re-signification of “Sarachchandralatory” (what G. A Haththotuwegama terms the unique adulation and aggrandization of Sarachchandra and his work) allows for the self-proclaimed custodians of the performance space to solidify patriarchal politics of the contemporary Sinhala Buddhist nation state. With the 2016 performance of Dutu Thena Allanu by Kaushalya Fernando in Wala as a case study, the paper investigates how Wala is a site of struggle where the spatialization of the gendered, anticolonial nationalist, historical past of Sri Lanka manifests in gatekeeping mechanisms that continue to delegitimize women’s postcolonial work, narratives of sexuality, and their critiques of the male-authored nation as “uncivil.” It further examines how Dutu Thena, in spite and on account of being violently intervened, can be read as Fernando’s exegesis of ethnotionalist politics that govern not only the politics of the performance space but also the hegemonic history of Sri Lankan postcolonial theater that peripheralizes the Gendered and the ethnic Other.

Fear of the angry mob

ABSTRACT The Capitol breach that occurred on 6 January 2021 immediately revived images of protest crowds as irrational, emotional, violent, and out of control. This frame had flourished for millennia, but had been displaced by more sympathetic ideas about protest in recent decades. Inspired by the civil rights and feminist movements, scholars had come to see street protest as politics by extraordinary means for those closed off from more mainstream channels of influence. Journalists, politicians, and police did not entirely change their minds along with researchers, but they had softened their views somewhat: protestors are not necessarily criminals to be attacked. In a society where protest is common, Americans had developed more nuanced thinking and feelings about crowds – all of which went out the window on January 6th. In this paper I trace some of the history of European and American ideas about crowds in order to show how easy – and how mistaken – it is to see a crowd of protestors as “a hostile crowd” or “a violent crowd,” or simply “the mob.”

The Causes and Consequences of Urban Riot and Unrest

This review explores those varied bodies of work that have sought to understand crowd behavior and violent crowd conduct in particular. Although the study of such collective conduct was once considered central to social science, this has long ceased to be the case and in many respects the study of protest and riot now receives relatively little attention, especially within criminology. In addition to offering a critical overview of work in this field, this review argues in favor of an expanded conception of its subject matter. In recent times, scholarly concern has increasingly been focused on questions of etiology, i.e., asking how and why events such as riots occur, with the consequence that less attention is paid to other, arguably equally important questions, including how riots spread, how they end, and, critically, what happens in their aftermath. Accordingly, as a corrective, the review proposes a life-cycle model of riots.

Fuzzy logic approach and sensitivity analysis for agent-based crowd injury modeling

A crowd is a group of people attending a public gathering with some joint purpose, such as protesting against the government or celebrating an event. In some countries, these kinds of activities are the only way to express public displeasure with their government. The government’s reactions to such activities may or may not be tolerant. For this reason, such situations must be eliminated by recognizing when and how they are likely to occur, and then providing guidelines to mitigate them. In urban areas, police and military forces use non-lethal weapons (NLWs), such as rubber bullets or clubs, to control a violent and destructive crowd. In order to estimate the results of this engagement, ensuring minimum injuries and reaching an optimal end state, simulating such actions in a virtual environment is necessary. In this work, a fuzzy logic-based crowd injury model for determining the physical effects of NLWs is proposed. Fuzzy logic concepts can be applied to a problem by using linguistic rules, which are determined by problem domain experts. A group of police and military officers were consulted for a set of injury model rules, and those rules were then included in the simulation platform. Sensitivity analysis has been conducted to analyze parameters in the model. As a proof of the concept, a prototype system was implemented using the Repast Simphony agent-based simulation toolkit. Simulation results illustrated the effectiveness of the simulation framework.

Violent and peaceful crowd reactions in the Middle East: cultural experiences and expectations

Collective honor in Middle Eastern crowds may serve as an important basis for both conflict and conflict resolution between security forces and crowd members. To investigate this issue, we extended a social–cognitive model of crowd behavior to account for the role of honor in social identities and relations, and tested the model in two studies. In Study 1, we collected critical incidents representing crowd experiences in the Middle East. The interview data were coded to include security actions that escalate force and those that generate understanding or exhibit restraint. Study 2 used a scenario-based interview procedure to test the hypothesis that Middle Eastern civilians and Americans with no Middle Eastern cultural experience hold differing beliefs and expectations about crowd reactions to security force actions. The results showed that escalation of force against the crowd led to an increase in the level of conflict more often than not, whereas attempting to understand the crowd or exhibiting restraint tended to decrease conflict. Middle Eastern expectations were largely congruent with these findings, whereas American beliefs diverged. The results have implications regarding the cultural and cognitive determinants of crowd behavior, and for the management of crowds by regional governments and in international peacekeeping situations.

Like water and vapor—conformity and independence in the large group

Conformity and independence in the large group may, in part, be due to collective phenomena analogous to those producing different physical phases like solid, liquid and vapor. This phase model of the large group explains several previous anecdotal observations: It predicts a suddenness in the decision making, it explains the apparent contradiction between crowd suggestibility on the one hand and the difficulty of controlling a crowd on the other hand, and it provides a new rationalization for the phenomenon of splitting. The model is of use to both leaders and members of the large group. For example, it suggests what social parameters to change to disperse a violent crowd, and why crowd crystals, a concept examined by the writer Canetti, can suddenly make the large group conform.

The Ritual of the Streets in Mid-19th-Century Toronto

The central streets of mid-19th-century Toronto, the principal public open spaces of the city, were the preferred place for enacting a wide variety of demonstrations which ranged from well-organized official processions to informal and even violent crowd scenes, Their use for these rituals of collective behaviour followed a tradition, still honoured at mid-century, of almost unhindered public accessibility to the streets. The claims which groups asserted for the use and enjoyment of this symbolic space, and the responses of the inhabitants and city government to the exercise of these rights, reveal the process by which the community adjudicated social conflict and built consensus through the manipulation and control of a valuable collective asset: the streets.