Object Detection in Defense Applications Using Deep Learning in Fog Environment

Object detection plays a critical role in modern defense and surveillance systems. Traditional monitoring systems often rely on cloud computing which may cause delay in processing large volumes of surveillance data. This paper proposes an object detection system using deep learning techniques in a fog computing environment. Surveillance cameras and sensors collect visual data from defense areas. The data is processed at nearby fog nodes using deep learning algorithms such as Convolutional Neural Networks (CNN) and YOLO. This approach reduces latency and enables faster threat detection. The proposed system improves real-time monitoring and helps identify objects such as vehicles, drones, and intruders even in foggy environments