RADIO FREQUENCY INTERFERENCE DETECTION FOR SAR DATA USING SPECTROGRAM-BASED SEMANTIC NETWORK

Mingliang Tao, Shuting Tang, Jieshuang Li, Xiang Zhang, Yifei Fan, Jia Su

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

11 Scopus citations

Abstract

Radio frequency interference (RFI) has been a pervasive and critical issue for space-borne synthetic aperture radar (SAR). The presence of RFI could lead to incorrect image interpretation and biased parameter retrieval, making the RFI detection a necessity to preserve overall data quality. In this paper, we propose an approach for detecting RFI signals in SAR raw data using time-frequency semantic analysis. Employing the U-Net convolutional neural network enables identification of target echoes and RFI signatures in 2D time-frequency representation with high probability. The detection process is realized without setting predefined thresholds, and could achieve superior performance without requiring large number of training samples.

Original languageEnglish
Title of host publicationIGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1662-1665
Number of pages4
ISBN (Electronic)9781665403696
DOIs
StatePublished - 2021
Event2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 - Brussels, Belgium
Duration: 12 Jul 202116 Jul 2021

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume2021-July

Conference

Conference2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Country/TerritoryBelgium
CityBrussels
Period12/07/2116/07/21

Keywords

  • Neural network
  • Radio frequency interference
  • Semantic analysis
  • Synthetic aperture radar
  • Time-frequency spectrogram

Fingerprint

Dive into the research topics of 'RADIO FREQUENCY INTERFERENCE DETECTION FOR SAR DATA USING SPECTROGRAM-BASED SEMANTIC NETWORK'. Together they form a unique fingerprint.

Cite this