Enhancing Surveillance System through EdgeComputing: A Framework For Real-Time Human Detection

Real-time human detection is critical for modern surveillance, enabling timely responses to security threats and enhancing situational awareness. Traditional approaches often struggle with latency, bandwidth constraints, and centralized processing challenges. In this paper, we propose a framework for real-time human detection using edge computing, leveraging edge devices to process data closer to the source. Our framework employs machine learning algorithms on edge devices to detect humans in real-time, reducing latency and bandwidth usage. We detail the design and implementation of our framework, including the edge computing architecture, machine learning models, and communication protocols. Experimental results demonstrate the effectiveness and efficiency of the proposed framework in real world scenarios underscoring its potential to enhance surveillance systems across various applications.