Published Paper Details:

Flying drones in safety zones is strictly prohibited. However anti-social elements are likely to hit important targets in such zones, by using drones. The aim of this project is to continuously monitor safety zones using SAR images and raise an alarm as soon as a Drone is detected. This project contains three modules: DII (Drone Image Input) module is used to provide different drone images as input for the system. The DI (Drone Identification) module is used to monitor the images of the safety zone and to identify drones when they enter the safety zone. The 'alarm' module is used to send the message to the safety officers as soon a Drone is detected in the safety zone. This project uses the OpenCV algorithm to identify different types of drones and distance calculation algorithm to measure the distance of the Drone from the safety zone. The images of various types of drones are stored in an image file system. The file system will be stored at a specific location in directory structure. The location will be fed as input to the system. KNN classification is used to classify the drone as one of the drones types. The k-nearest neighbors algorithm (k-NN) is a non-parametric method used for classification. The input consists of the k closest training examples in the feature space. The output is a class membership. An object is classified by the class that is most common among its k nearest neighbors. The classification is based on the length, width, height and curvature of the drones.