A Review of Computer Vision Techniques for Video Violence Detection and intelligent video surveillance systems

With the advancement of technology in recent years, intelligent video surveillance systems are increasingly being used a large number of cameras, which have been installed in public spaces; such as market places, shopping malls, hospitals, banks, streets, education institutions, city administrative offices, and smart cities. This is to make public lives and assets safer and to keep the risk at a tolerable level. Such systems are being continuously developed due to the advancements in the computer vision techniques. This paper presents an overview of the most used computer vision techniques contemporary issues of the intelligent video surveillance systems for public spaces described in the world's scientific publications. In this paper, the methods of detection are divided into four main categories that are based on classification techniques used: violence detection using traditional machine learning, using Deep Learning, using Convolutional Neural Network (CNN) and using Support Vector Machine (SVM). The feature extraction techniques and object detection techniques of each single method are also presented. Essential basic concepts for computer vision and violence detection are also summarized.