Artificial intelligence in video surveillance systems for suspicious activity detection and incident response: A systematic literature review

Artificial intelligence (AI) has proven to be a key tool to improve the efficiency of video surveillance systems, contributing to public safety. This systematic review aims to analyze the contributions of artificial intelligence in this field, in line with Sustainable Development Goal 16 (SDG 16), which promotes peaceful and inclusive societies. 145 articles extracted from major databases such as Scopus, WOS, ProQuest, EBSCO, IEEE Xplore, and Science-Direct were analyzed. Using PRISMA methodology, inclusion and exclusion criteria were applied, resulting in 42 articles relevant to the review. The findings indicate that the use of advanced AI technologies, such as the internet of things, computer vision, and edge computing, are the most integrated with artificial intelligence, enhancing its capabilities in video surveillance systems. In this framework, deep learning stands out as an essential basis for optimizing these applications. Finally, the results of this review provide a solid foundation for future research on the use of artificial intelligence in video surveillance. The technologies evaluated have the potential to further contribute to the improvement of security and operational efficiency in different contexts and environments.