The growing use of drones/unmanned aerial vehicles (UAV’s) has generated in the general public as well as in institutions the awareness of the possible misuse that can be given to these devices. For this reason, the detection of drones has become a necessity that poses in the case of detection using images a great difficulty due to its small size, in addition to the background that can make detection even more difficult. Regarding this work, the aim is not only to detect drones but also to distinguish the type of detected drone. Different networks were trained whereupon an analysis was conducted in which it was found that the YOLOv4tiny network with 416 × 416 input resolution presents the best results considering both the inference performance and the processing speed.
Towards Real-Time Drone Detection Using Deep Neural Networks
Smart Innovation, Systems and Technologies
29.10.2021
11 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Towards Real-Time Image Reconstruction Using Deep Neural Networks
British Library Conference Proceedings | 2020
|Drone-Based Weed Detection Architectures Using Deep Learning Algorithms and Real-Time Analytics
Springer Verlag | 2022
|Practical Study of Recurrent Neural Networks for Efficient Real-Time Drone Sound Detection: A Review
DOAJ | 2022
|