Convolutional Neural Networks for Drone Model Classification

H. Dale, M. Antoniou, C. J. Baker, M. Jahangir, A. Catherall

Research output: Chapter in Book/Report/Conference proceedingConference contribution


This work establishes performances for drone group (fixed wing vs rotary wing), drone subgroup (fixed wing vs hexacopter vs quadcopter) and drone model classification using a convolutional neural network (CNN). Data is from an experimental campaign with nine different drone models flying along various trajectories. It is demonstrated that CNNs are very capable of drone recognition, with baseline performances as high as 98%.

Original languageEnglish
Title of host publication2021 18th European Radar Conference (EuRAD)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages4
ISBN (Electronic)9782874870651
ISBN (Print)9781665447232 (PoD)
Publication statusPublished - 2 Jun 2021
Event18th European Radar Conference, EuRAD 2021 - London, United Kingdom
Duration: 5 Apr 20227 Apr 2022

Publication series

NameEuropean Radar Conference (EURAD)


Conference18th European Radar Conference, EuRAD 2021
Country/TerritoryUnited Kingdom

Bibliographical note

Funding Information:
ACKNOWLEDGEMENTS This work was funded by the UK Engineering and Physical Sciences Research Council.

Publisher Copyright:
© 2022 European Microwave Association (EuMA).


  • convolutional neural networks
  • deep learning
  • radar applications
  • staring radar
  • UAVs

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Instrumentation


Dive into the research topics of 'Convolutional Neural Networks for Drone Model Classification'. Together they form a unique fingerprint.

Cite this