Public security is a crucial aspect of maintaining social order. Although crime rates in western cultures may be considered socially acceptable, it is important to continually improve security measures to prevent potential risks.  With the advancements in artificial intelligence methods, particularly in deep learning and computer vision, it has become possible to detect abnormal event patterns in groups of people. This paper presents a systematic review of deep learning techniques employed for identifying gatherings of people and detecting anomalous events to enhance public security. Some of the open research areas are identified, including the lack of works addressing multiple cases of anomalies in large concentrations of people, which leaves open an important avenue for future scientific work.