Drone model classification using convolutional neural network trained on synthetic data

Date published

2022-08-12

Free to read from

Supervisor/s

Journal Title

Journal ISSN

Volume Title

Publisher

MDPI

Department

Type

Article

ISSN

2313-433X

Format

Citation

Wisniewski M, Rana ZA, Petrunin I. (2022) Drone model classification using convolutional neural network trained on synthetic data. Journal of Imaging, Volume 8, Issue 8, August 2022, Article number 218

Abstract

We present a convolutional neural network (CNN) that identifies drone models in real-life videos. The neural network is trained on synthetic images and tested on a real-life dataset of drone videos. To create the training and validation datasets, we show a method of generating synthetic drone images. Domain randomization is used to vary the simulation parameters such as model textures, background images, and orientation. Three common drone models are classified: DJI Phantom, DJI Mavic, and DJI Inspire. To test the performance of the neural network model, Anti-UAV, a real-life dataset of flying drones is used. The proposed method reduces the time-cost associated with manually labelling drones, and we prove that it is transferable to real-life videos. The CNN achieves an overall accuracy of 92.4%, a precision of 88.8%, a recall of 88.6%, and an f1 score of 88.7% when tested on the real-life dataset.

Description

Software Description

Software Language

Github

Keywords

unmanned aerial vehicles, drones, airport security, convolutional neural network, synthetic images, synthetic data, domain randomization, drone detection, drone classification, drone identification, artificial intelligence

DOI

Rights

Attribution 4.0 International

Relationships

Resources

Funder/s