Networking Systems for Video Anomaly Detection: A Tutorial and Survey

2024-05-16

arXiv.org

AI Summary

To address the real-time processing, privacy preservation, and practical deployment challenges arising from the rapid expansion of surveillance infrastructure in smart cities and video-internet applications, this paper proposes the Networked Surveillance Video Anomaly Detection (NSVAD) paradigm. Methodologically, it introduces an edge-cloud collaborative architecture integrating self-supervised and weakly supervised deep learning models, edge-cloud co-computation, Internet-of-Video-Things (IoVT) streaming analytics, and distributed inference optimization. Key contributions include: (i) the first systematic formalization of the NSVAD theoretical framework and technical ecosystem; (ii) a unified pedagogical resource covering foundational assumptions, architectural principles, and representative application scenarios; (iii) the open-sourcing of the first comprehensive NSVAD repository—including benchmark models, annotated datasets, and end-to-end toolchains; and (iv) a reproducible technology roadmap with full implementation tutorials. Experimental evaluation demonstrates millisecond-scale low-latency anomaly detection in industrial IoT and smart city deployments, and the repository has been adopted in multiple real-world implementations.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Learning on the Edge & Model Compression
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Security and Privacy: Data transparency and provenance

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. This article elucidates core concepts by reviewing recent advances and typical solutions and aggregating available research resources accessible at https://github.com/fdjingliu/NSVAD. Additionally, we showcase our latest NSVAD research in industrial IoT and smart cities, along with an end-cloud collaborative architecture for deployable 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.

Problem

• Automated Video Anomaly Detection for public security
• Networking Systems for VAD in smart cities
• Integration of AI and computing for VAD challenges

Innovation

• Deep learning-driven Video Anomaly Detection routes
• Integration of AI and edge computing technologies
• Networking Systems for deployable VAD solutions