A Survey on Video Analytics in Cloud-Edge-Terminal Collaborative Systems

TL;DR

The paper tackles the challenge of scalable, real-time video analytics in cloud-edge-terminal collaborative (CETC) systems by surveying architectural paradigms (hierarchical, distributed, hybrid), edge and cloud processing paradigms, and optimization strategies. It presents a structured taxonomy and synthesizes edge-centric, cloud-centric, and hybrid approaches, detailing processing pipelines, offloading, training/inference strategies, and resource management metrics such as $L_{sys}=L_{proc}+L_{trans}+L_{queue}$, $\rho=\frac{\lambda}{N_s \mu}$, and Little's law $W=\frac{q_l}{\lambda}$. Key contributions include a comprehensive review of edge processing, edge-assisted offloading, and cloud-based training/serving, plus discussion of data protection, platform integration, scalability, and resilience, with emphasis on emerging trends like LLMs and multimodal video understanding. The survey offers concrete guidance for designing CETC pipelines that balance latency, energy, bandwidth, and accuracy, while outlining future directions such as explainable AI, efficient processing, and robust platform integration. Overall, the work provides a roadmap for researchers and practitioners to build scalable, privacy-preserving, and reliable CETC video analytics systems in dynamic environments.

Abstract

The explosive growth of video data has driven the development of distributed video analytics in cloud-edge-terminal collaborative (CETC) systems, enabling efficient video processing, real-time inference, and privacy-preserving analysis. Among multiple advantages, CETC systems can distribute video processing tasks and enable adaptive analytics across cloud, edge, and terminal devices, leading to breakthroughs in video surveillance, autonomous driving, and smart cities. In this survey, we first analyze fundamental architectural components, including hierarchical, distributed, and hybrid frameworks, alongside edge computing platforms and resource management mechanisms. Building upon these foundations, edge-centric approaches emphasize on-device processing, edge-assisted offloading, and edge intelligence, while cloud-centric methods leverage powerful computational capabilities for complex video understanding and model training. Our investigation also covers hybrid video analytics incorporating adaptive task offloading and resource-aware scheduling techniques that optimize performance across the entire system. Beyond conventional approaches, recent advances in large language models and multimodal integration reveal both opportunities and challenges in platform scalability, data protection, and system reliability. Future directions also encompass explainable systems, efficient processing mechanisms, and advanced video analytics, offering valuable insights for researchers and practitioners in this dynamic field.

Figures (3)

• Figure 1: Publication and citation statistics over the last decade.
• Figure 2: Taxonomy of video analytics in CETC systems.
• Figure 3: Example of CETC video analytics workflow.