An initial investigation into using convolutional neural networks for classification of drones

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

External organisations

  • Microwave Integrated Systems Laboratory (MISL)
  • Aveillant Limited Cambridge

Abstract

The use of convolutional neural networks (CNNs) in drone and non-drone classification is investigated in this paper. A classifier is trained on radar spectrograms obtained using an L-band staring radar and the performance is assessed and compared with a machine learning benchmark. Initial results have shown the CNN to achieve a correct classification performance of up to 98.89%.

Details

Original languageEnglish
Title of host publication2020 IEEE International Radar Conference, RADAR 2020
Publication statusPublished - Apr 2020
Event2020 IEEE International Radar Conference, RADAR 2020 - Washington, United States
Duration: 28 Apr 202030 Apr 2020

Publication series

Name2020 IEEE International Radar Conference, RADAR 2020

Conference

Conference2020 IEEE International Radar Conference, RADAR 2020
CountryUnited States
CityWashington
Period28/04/2030/04/20

Keywords

  • Birds, Classification, Deep learning, Machine learning, Signal processing, Staring radar, UAVs