Networking Systems for Video Anomaly Detection: A Tutorial and Survey
Jing Liu, Yang Liu, Jieyu Lin, Jielin Li, Liang Cao, Peng Sun, Bo Hu, Liang Song, Azzedine Boukerche, Victor C. M. Leung
TL;DR
This paper reframes video anomaly detection as Networking Systems for Video Anomaly Detection (NSVAD), integrating sensing, communication, and AI-based detection across hardware, system, algorithm, and application layers. It provides a structured tutorial of UVAD, WsVAD, and FuVAD, including definitions, learning paradigms, emerging tasks, and representative models, while highlighting open-set and multimodal directions enabled by large language models. The authors offer systematic resources, datasets, and deployment-oriented insights from industrial NSVAD deployments, and present a forward-looking analysis of data, label, model, and system challenges, along with hardware, system, algorithm, and application trends. The work aims to bridge AI, IoVT, and edge computing communities, propose practical NSVAD system designs, and guide future research toward deployable, privacy-preserving, and scalable video anomaly detection in smart cities and mobile/video networks.
Abstract
The increasing utilization of surveillance cameras in smart cities, coupled with the surge of online video applications, has heightened concerns regarding public security and privacy protection, which propelled automated Video Anomaly Detection (VAD) into a fundamental research task within the Artificial Intelligence (AI) community. With the advancements in deep learning and edge computing, VAD has made significant progress and advances synergized with emerging applications in smart cities and video internet, which has moved beyond the conventional research scope of algorithm engineering to deployable Networking Systems for VAD (NSVAD), a practical hotspot for intersection exploration in the AI, IoVT, and computing fields. In this article, we delineate the foundational assumptions, learning frameworks, and applicable scenarios of various deep learning-driven VAD routes, offering an exhaustive tutorial for novices in NSVAD. In addition, this article elucidates core concepts by reviewing recent advances and typical solutions and aggregating available research resources accessible at https://github.com/fdjingliu/NSVAD. Lastly, this article projects future development trends and discusses how the integration of AI and computing technologies can address existing research challenges and promote open opportunities, serving as an insightful guide for prospective researchers and engineers.