With the rising interest in drones, the drone industry has made a deliberate effort to open its market to the general public, allowing these unmanned aircraft to become an integral part of daily life. However, this increased accessibility has given rise to concerns about safety and security. The ease of drone operation has led to a higher likelihood of accidents, such as collisions with people due to loss of control or instances of drones trespassing into restricted areas. To address these safety concerns effectively, it becomes crucial for both drone operators and observers to be aware of approaching drones in their vicinity. In this paper, we present a comprehensive drone detection system based on cutting-edge machine-learning techniques. The system is specifically designed to be implemented on drones equipped with cameras. By analyzing the camera images, our system is capable of deducing the location of the drone in the image and identifying the drone’s vendor model using sophisticated machine classification algorithms. For its implementation, we have utilized the You Only Look Once (YOLO) and OpenCV [4] libraries, which have proven to be robust and efficient tools for this purpose. Through the integration of this machine learning-based drone detection system, we aim to enhance safety and security in drone usage, mitigating potential risks and ensuring responsible and informed drone operation in various environments.