With the rapid development of commercial drones, drone detection and classification have emerged and grown recently. Drone detection works to detect unmanned aerial vehicles (UAVs). Usually, systems for drone detection utilize a combination of one or more sensors and some methodology. Many unique technologies and methods are used to detect drones. However, each type of technology offers its benefits and limitations. Most approaches use computer vision or machine learning, but one methodology that has not been given much attention is Sensor Fusion. Sensor Fusion has less uncertainty than most methods, making it suitable for drone detection. In this paper, we propose an artificial neural network-based detection system that uses a deep neural network (DNN) to process the RF data and a convolutional neural network (CNN) to process image data. The features from CNNs and DNNs are concatenated and input into another DNN, which outputs a single prediction score of drone presence. Our model achieved a validation accuracy of 75% that shows the feasibility of a sensor fusion based technique for drone detection.
Sensor Fusion for Drone Detection
2021-04-01
3780097 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Drone-passing multiple detection sensor gate and drone game system using same
Europäisches Patentamt | 2024
|DRONE-PASSING MULTIPLE DETECTION SENSOR GATE AND DRONE GAME SYSTEM USING SAME
Europäisches Patentamt | 2022
|DRONE-PASSING MULTIPLE DETECTION SENSOR GATE AND DRONE GAME SYSTEM USING SAME
Europäisches Patentamt | 2020
|Indoor drone positioning: accuracy and cost trade-off for sensor fusion
BASE | 2022
|