A survey of video violence detection. Issue 1 (2nd January 2023)

• Record Type: Journal Article
• Authors: Yao, Huiling; Hu, Xing
• Is Part Of: Cyber-physical systems. Volume 9:Issue 1(2023)
• Page Start: 1
• Page End: 24
• Publication Date: 2023-01-02
• Subjects: Violent behaviour detection (viobd) -- intelligent video surveillance -- computer vision; Cooperating objects (Computer systems) -- Periodicals; Internet of things -- Periodicals; 006.22
• DOI: 10.1080/23335777.2021.1940303
• Languages: English
• ISSNs: 2333-5777

Abstract

ABSTRACT: As one of the important applications of intelligent video surveillance, violent behaviour detection (VioBD) plays a crucial role in public security and safety. As a particular type of behaviour recognition, VioBD aims to identify whether the behaviours that occurred in the scene is aggressive, such as fighting and assault. To comprehensively analyse the current state and predict the future trend of VioBD research, we survey the existing approaches of VioBD in this work. First, we briefly introduce the basic principle and the challenges of VioBD; Then, we category the existing approaches according to their framework, including the traditional framework, end-to-end deep learning framework, and hybrid deep learning framework. Finally, we introduce the public datasets for evaluating the performance of VioBD approaches and compare their performances on these datasets. Besides, we also summarise the open problems in VioBD and predict its future trends.