ADVANCED DRONE DETECTION WITH CONVOLUTIONAL NEURAL NETWORKS

Abstract

The increasing popularity of unmanned aerial vehicles (UAVs) and drones has brought about significant benefits in various industries. However, it has also raised concerns regarding secu-rity and privacy, as malicious actors may exploit these devices for unauthorized surveillance, smuggling, or other illicit activities. This project proposes an innovative approach to address this issue through drone and UAV detection for security applications using deep learning tech-niques. The proposed system leverages the power of Convolutional Neural Networks (CNNs) and other deep learning models to automatically detect and identify UAVs and drones from visual data captured by surveillance cameras, security systems, or drones equipped with on board cameras. By analyzing the distinct characteristics and patterns of UAVs, such as their unique shapes and flight trajectories, the system can efficiently differentiate them from other objects in the environment. This camera rotates on servo motor, so that it can capture wide area. This proposed project title is Drone and UAV detection for security applications using deep learning a systematic approach to drone detection and classification using deep learning with different modalities. The YOLOv3 object detector is used to detect the moving or still objects. It uses a computer vision-based approach as a reliable solution. The convolution neural network helps to extract features from images and to detect the object with maximum accuracy. The model is trained with a proper dataset and trained for 150 epoch only to detect various types of drones. A convolutional neural network with modern object detection methods shows an excellent approach for real-time detection of drones.