Drones are one of the popular devices now a days not only for entertainment purposes but also in various of applications such as engineering, security in airport disaster management, delivery of goods and others. In addition to their useful applications, frightening concern regarding physical infrastructure safety and airports surveillance has arisen due to the frequency of their use in nasty activities. These days, there have been numerous incidents of drones being used improperly at airports and interfering with airline operations. This work suggested a deep learning-based solution for the effective detection and identification of two types of drones, birds and helicopter to solve this problem. Evaluation of the proposed approach with the prepared image dataset demonstrates better efficiency compared to existing detection systems in the literature. Furthermore, due to their physical characteristics and behaviours, drones are frequently mistaken with birds and helicopter . The suggested YOLOv5 method is not only capable of determining if drones are present or absent in the given area, but it can also recognize two types ie, multirotor and single rotor drones, birds and helicopters as helicopter has very much resemblance of single rotor drones . The dataset used in this work to train the network consists of 4000 visible images containing two types of drones as multirotors, Single rotor, helicopters, and also birds. The suggested deep learning method can directly detect and recognize two types of drones and distinguish them from birds and helicopter with a precision score of 0.9757, recall score of 0.98, as well as mAP(Mean Average Precision) scores of 0.98 and 0.62 for @0.5 IOU (Intersection Over Union)and @0.95 IOU respectively

Deep learning, YOLOv5, precision, reall, mAP, IOU