• B. Venkata Rupa Vardhan
• G. Pavan Kumar
• B. Mayabrahma Chari
• D. Abhi Ram
• N. Vijaya Lakshmi

Traditional Conventional methods of surveillance are usually based on either manual surveillance or costly physical solutions like radar that are not very effective when it comes to large, fast moving drones in the real world settings. As the number of unmanned aerial vehicles (UAVs) becomes more accessible and their exploitation continues, rogue drone operation within the confines of the restricted airspaces is a major security, safety, and privacy risk. Existing systems are unable to offer continuous monitoring, prone to human error and also in complex environmental conditions they tend to fail. To overcome these drawbacks, the paper provides a drone detection system based on the ideas of deep learning and computer vision in order to identify the drones in the surveillance camera images with the help of artificial intelligence. The system uses recent models of object detection including YOLOv5 and YOLOv8, which are trained on a mix of publicly available drone datasets (VisDrone, UAVDT) and specific annotated data to enhance robustness. Such methods as multi-scale training and data augmentation will improve the ability to detect drones of a very small size, and real-time processing provides a rapid response. The system offers visual detection results, generates warnings and events by logging by an interactive dashboard that facilitates human-in-the-loop management of security personnel. The accuracy of the detection and real-time performance is high and shown by experimental results, which provides an effective and scalable solution to the current requirements of surveillance applications.

Drone Detection, Computer Vision, Deep Learning, YOLO, Object Detection, Surveillance Systems, UAV Detection, Real-Time Processing.

"Real-Time Detection of Unmanned Flying Objects Using Computer Vision and Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 3, page no.d713-d720, March-2026, Available :http://www.jetir.org/papers/JETIR2603390.pdf

"Real-Time Detection of Unmanned Flying Objects Using Computer Vision and Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 3, page no. ppd713-d720, March-2026, Available at : http://www.jetir.org/papers/JETIR2603390.pdf