Improving real-time drone detection for counter-drone systems
| Autor: | E. Çetin, E. Pastor, C. Barrado |
|---|---|
| Přispěvatelé: | Universitat Politècnica de Catalunya. Doctorat en Ciència i Tecnologia Aeroespacials, Universitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors, Universitat Politècnica de Catalunya. ICARUS - Intelligent Communications and Avionics for Robust Unmanned Aerial Systems |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Artificial intelligence
Computer science UAV Real-time computing Avions no tripulats Aerospace Engineering Airsim 02 engineering and technology Accuracy improvement 01 natural sciences Flight simulator Object Detection 0202 electrical engineering electronic engineering information engineering YOLO Reconeixement de formes (Informàtica) Drone aircraft Counter-Drone Drones Pixel business.industry Deep learning Intel·ligència artificial 010401 analytical chemistry deep learning 020206 networking & telecommunications Pattern recognition systems EfficientNet Object detection Drone 0104 chemical sciences Identification (information) Aeronàutica i espai [Àrees temàtiques de la UPC] Transfer of learning business |
| Zdroj: | UPCommons. Portal del coneixement obert de la UPC Universitat Politècnica de Catalunya (UPC) |
| Popis: | The number of unmanned aerial vehicles (UAVs, also known as drones) has increased dramatically in the airspace worldwide for tasks such as surveillance, reconnaissance, shipping and delivery. However, a small number of them, acting maliciously, can raise many security risks. Recent Artificial Intelligence (AI) capabilities for object detection can be very useful for the identification and classification of drones flying in the airspace and, in particular, are a good solution against malicious drones. A number of counter-drone solutions are being developed, but the cost of drone detection ground systems can also be very high, depending on the number of sensors deployed and powerful fusion algorithms. We propose a low-cost counter-drone solution composed uniquely by a guard-drone that should be able to detect, locate and eliminate any malicious drone. In this paper, a state-of-the-art object detection algorithm is used to train the system to detect drones. Three existing object detection models are improved by transfer learning and tested for real-time drone detection. Training is done with a new dataset of drone images, constructed automatically from a very realistic flight simulator. While flying, the guard-drone captures random images of the area, while at the same time, a malicious drone is flying too. The drone images are auto-labelled using the location and attitude information available in the simulator for both drones. The world coordinates for the malicious drone position must then be projected into image pixel coordinates. The training and test results show a minimum accuracy improvement of 22% with respect to state-of-the-art object detection models, representing promising results that enable a step towards the construction of a fully autonomous counter-drone system. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|