Ground Background Clutter Recognition Based on Fully Convolutional Neural Network

Chang Liu, Ping Lang, Xiongjun Fu*, Jian Dong, Mingling Li, Xinyue Qi

*Corresponding author for this work

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

Abstract

Accurate and robust recognition of background clutter is essential for radar target detection. Aiming at the problems that existing clutter recognition methods have low accuracy and poor robustness, a background clutter recognition method based on novel Fully Convolutional Neural Network (FCNN) is proposed. FCNN is trained and tested based on the simulated ground clutter Range-Doppler (R-D) spectra. Experimental results demonstrate that FCNN is significantly superior to the existing background clutter recognition models in terms of clutter classification accuracy or time complexity. In addition, FCNN can better adapt to clutter recognition under low clutter-to-noise ratio (CNR) scenarios. Finally, we verify the effectiveness of the CFAR detector based on clutter recognition.

Original languageEnglish
Title of host publication2021 CIE International Conference on Radar, Radar 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1850-1853
Number of pages4
ISBN (Electronic)9781665498142
DOIs
Publication statusPublished - 2021
Event2021 CIE International Conference on Radar, Radar 2021 - Haikou, Hainan, China
Duration: 15 Dec 202119 Dec 2021

Publication series

NameProceedings of the IEEE Radar Conference
Volume2021-December
ISSN (Print)1097-5764
ISSN (Electronic)2375-5318

Conference

Conference2021 CIE International Conference on Radar, Radar 2021
Country/TerritoryChina
CityHaikou, Hainan
Period15/12/2119/12/21

Keywords

  • Range-Doppler
  • background clutter
  • clutter recognition
  • fully convolutional neural network

Fingerprint

Dive into the research topics of 'Ground Background Clutter Recognition Based on Fully Convolutional Neural Network'. Together they form a unique fingerprint.

Cite this