Manuscript received August 23, 2025; revised October 14, 2025; accepted December 25, 2025; published June 22, 2026.

Abstract—This study presents an intelligent data center monitoring and surveillance framework for green cities, integrating Internet of Things (IoT) technology with You Only Look Once (YOLO)-based object detection. The proposed system enhances data center security and operational efficiency by enabling real-time identification of critical components such as servers, routers, cooling systems, and unauthorized personnel. Leveraging computer vision and deep learning, the framework provides proactive monitoring and rapid response to potential threats. The YOLO model is trained on a large, annotated dataset specifically curated for data center environments, allowing precise detection and localization of IoT-based objects of interest. Additional modules incorporating thermal imaging and motion detection further strengthen anomaly recognition and intrusion prevention capabilities. Performance evaluation across multiple data center scenarios demonstrates high detection accuracy, low latency, and strong robustness under varying environmental conditions. The study also highlights the computational efficiency achieved through GPU parallelization and model optimization, ensuring real-time processing in large-scale deployments. Overall, the proposed framework offers a scalable, energy-efficient, and secure solution for smart data center management, contributing to the advancement of sustainable and resilient green city infrastructures.

Keywords—Internet of Things (IoT), You Only Look Once (YOLO) object detection, smart data centers, green cities, deep learning, real-time monitoring, edge computing

Cite: Yousef Farhaoui, Ahmad El Allaoui, Hamed Taherdoost, and Bharat Bhushan, "An IoT-Enabled Intelligent Data Center Monitoring Framework Using YOLO-Based Image Analysis for Green Cities," Journal of Image and Graphics, Vol. 14, No. 3, pp. 521-531, 2026.

Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).