Stagger PRI Radar Signal Deinterleaving based on Image Semantic Segmentation

Yifei Liu, Jian Xie, Mingliang Tao, Shuting Tang, Zhihao Tang, Ling Wang

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

3 Scopus citations

Abstract

Signal deinterleaving is an important prerequisite step for recognizing radar emitters. However, with the advancement of digital emission technology, traditional signal deinterleaving algorithms have difficulty in obtaining accurate results for complex stagger pulse repetition interval (PRI) signals. To solve this issue, a deinterleaving method based on the image semantic segmentation technique is proposed. This method can characterize the frequency features of different PRI types on pixel distribution, estimate the potential PRI of the sequence, and extract the corresponding pulse sequence by using a segmentation network. Experimental results demonstrate that the proposed method could achieve superior results for staggered radar emitters.

Original languageEnglish
Title of host publication2022 IEEE 5th International Conference on Electronic Information and Communication Technology, ICEICT 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages599-602
Number of pages4
ISBN (Electronic)9781665472111
DOIs
StatePublished - 2022
Event5th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2022 - Hefei, China
Duration: 21 Aug 202223 Aug 2022

Publication series

Name2022 IEEE 5th International Conference on Electronic Information and Communication Technology, ICEICT 2022

Conference

Conference5th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2022
Country/TerritoryChina
CityHefei
Period21/08/2223/08/22

Keywords

  • deep learning
  • semantic segmentation
  • Signal deinterleaving
  • staggered pulse repetition interval

Fingerprint

Dive into the research topics of 'Stagger PRI Radar Signal Deinterleaving based on Image Semantic Segmentation'. Together they form a unique fingerprint.

Cite this