Unmanned aerial vehicles (UAVs) or drones have become a popular technology in various fields, including agriculture, delivery services, and surveillance. However, the use of drones in susceptible areas such as airport, armed forces bases, and critical infrastructure facilities has raised security concerns. Developing an efficient drone detection system has thus become a pressing need. In this editorial, we propose a drone discovery system that uses computer vision techniques to detect drones in real-time video streams. The proposed system is designed to work with different types of drones, regardless of their size, shape, and flight patterns. The system utilizes state-of-the-art object recognition algorithms, such as YOLOv5, and tracks the detected drones over time. The system's presentation is evaluated on a novel rf-based buzz detection dataset, and the results demonstrate the system's effectiveness in detecting drones in various environments. In similar way Deep Residual Neural Network (DRNN) framework used for drone detection as well as for categorization. The proposed system has the potential for use in a diversity of applications, such as security plus surveillance, public safety, and disaster management.