Accurate crowd counting is of great importance to a wide range of real-world applications such as public safety monitoring, traffic management, event organisation, urban planning and emergency response. However, existing crowd counting techniques often suffer from severe occlusions, large variations in crowd density, perspective distortion and complex background environments, leading to reduced detection accuracy. In this paper, a new crowd counting framework is proposed based on patch-level annotation and YOLO (You Only Look Once) deep learning architecture to improve detection performance and real-time processing capability. The suggested method separates high-resolution crowd photos into smaller patches. It performs accurate patch-level annotation, allowing the model to learn local crowd characteristics, minimise annotation complexity, and better localise tightly packed people. Processing these image patches with YOLO's quick object detection allows reliable crowd estimation with low inference time. The proposed framework surpasses state-of-the-art approaches in accuracy, robustness, and computational efficiency, as demonstrated by extensive trials on benchmark crowd-counting datasets. A performance study using standard measures demonstrates that identification and counting accuracy improve significantly across diverse crowd densities and challenging conditions. The suggested system is effective and scalable for intelligent surveillance, smart city monitoring, public event management, and real-time crowd analysis.
Saw Mya Nandar, Hlaing Htake Khaung Tin, Bhopendra Singh et al.· FMDB Transactions on Sustain...· 0 citations
Syria’s digital reconstruction offers a unique opportunity to deploy a next-generation distributed computing infrastructure that leverages three strategic international gateways (IGWs): a submarine cable from Cyprus to Tartus (10 Tbps), a terrestrial link from Jordan to Damascus (10 Tbps), and a terrestrial link from Turkey to Aleppo (10 Tbps). This paper proposes and rigorously evaluates a hybrid edge cloud architecture comprising three regional edge nodes (Damascus, Aleppo, and Coastal) and a central cloud in Homs, all interconnected via an ultra-high-speed domestic backbone (10 Tbps). Using analytical models and simulations, researchers demonstrate that edge nodes reduce end-to-end latency to <0.5 ms locally (10–20× improvement over cloud-only), cut backbone traffic by 99% through intelligent preprocessing, and ensure full compliance with the Syrian data residency law (Law No. 12/2016). Furthermore, the integration of 10 Tbps IGWs enables low-latency international peering (RTT ≤ 2.9 ms from the coast to Europe) while preserving data sovereignty. Total cost of ownership (TCO) is reduced by 52% compared to a cloud-only model, even with 10× higher capacity. Researchers provide a comprehensive set of Mermaid-based diagrams and tables quantifying latency, bandwidth, cost, and failover scenarios. The paper concludes with actionable recommendations for the Syrian Ministry of Communications and Technology and international partners.
Jouma Ali Al-Mohamad, M. Paslavskyi, Julio Suárez Albanchez et al.· FMDB Transactions on Sustain...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
