Millimeter Wave Radar Measurements: Distinguishing UAS and Birds Based on 60 GHz micro-Doppler Signatures

Seongjoon Kang, Henrik Forstén, Panagiotis Skrimponis, Martins Ezuma, Marco Mezzavilla, Ismail Guvenc, Sundeep Rangan, Vasilii Semkin

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

Abstract

This work presents the results of measurements conducted on small drones and a bionic bird using a 60 GHz millimeter wave radar, analyzing their micro-Doppler characteristics in both time and frequency domains. In particular, we focus on their distinct nature of movement, i.e., rotating propellers and flapping wings, rather than relying on their materials. The time-series measurements show comparable differences in the phase of the samples as a result of micro-Doppler effects. Utilizing the collected measurement data, we develop neural network models to accurately differentiate between bionic birds and drones, having a significant potential for application in airports where precise object identification is essential. We adopt a convolutional neural network for detecting changes in the amplitude values and a convolutional long- and short-term memory for identifying the phase difference between the drone and bird signatures. The results reveal that distinguishing between small drones and birds can be done based on the phase difference of the scattered radar signals, even with a high noise variance.

Original languageEnglish (US)
Title of host publication2024 IEEE 100th Vehicular Technology Conference, VTC 2024-Fall - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331517786
DOIs
StatePublished - 2024
Event100th IEEE Vehicular Technology Conference, VTC 2024-Fall - Washington, United States
Duration: Oct 7 2024Oct 10 2024

Publication series

NameIEEE Vehicular Technology Conference
ISSN (Print)1550-2252

Conference

Conference100th IEEE Vehicular Technology Conference, VTC 2024-Fall
Country/TerritoryUnited States
CityWashington
Period10/7/2410/10/24

Keywords

  • Classification
  • detection
  • drones
  • micro-Doppler
  • millimeter-wave
  • radar
  • UAS
  • UAV

ASJC Scopus subject areas

  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Millimeter Wave Radar Measurements: Distinguishing UAS and Birds Based on 60 GHz micro-Doppler Signatures'. Together they form a unique fingerprint.

Cite this