Recognition of radar in-pulse modulation based on radar de-noising Linknet

  • Chenkai Wang
  • , Lei Kuang*
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Intra-pulse modulation pattern recognition of radar signals is an important aspect of modern electronic reconnaissance warfare. For radar intra-pulse modulated signals with low signal-to-noise ratio (SNR), traditional machine learning and deep learning networks do not preprocess the signals properly, resulting in low recognition accuracy. To solve this problem, this paper proposes a semantic segmentation network-based method to improve the recognition rate of modulation patterns by preprocessing the semantics of signal time-frequency maps. The experimental results show that the method can effectively recognize 12 radar modulation patterns at low SNR, and the pattern recognition accuracy is as high as 98.6% for signals with SNR of -10db.

Original languageEnglish
Title of host publication2022 2nd International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology, CEI 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages233-236
Number of pages4
ISBN (Electronic)9781665476164
DOIs
StatePublished - 2022
Event2nd International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology, CEI 2022 - Virtual, Online, China
Duration: 23 Sep 202225 Sep 2022

Publication series

Name2022 2nd International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology, CEI 2022

Conference

Conference2nd International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology, CEI 2022
Country/TerritoryChina
CityVirtual, Online
Period23/09/2225/09/22

Keywords

  • de-noising
  • high recognition rate
  • intra-pulse modulation recognition
  • low SNR
  • semantic segmentation

Fingerprint

Dive into the research topics of 'Recognition of radar in-pulse modulation based on radar de-noising Linknet'. Together they form a unique fingerprint.

Cite this