TY - GEN
T1 - RADIO FREQUENCY INTERFERENCE DETECTION FOR SAR DATA USING SPECTROGRAM-BASED SEMANTIC NETWORK
AU - Tao, Mingliang
AU - Tang, Shuting
AU - Li, Jieshuang
AU - Zhang, Xiang
AU - Fan, Yifei
AU - Su, Jia
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
KW - Neural network
KW - Radio frequency interference
KW - Semantic analysis
KW - Synthetic aperture radar
KW - Time-frequency spectrogram
UR - http://www.scopus.com/inward/record.url?scp=85126022922&partnerID=8YFLogxK
U2 - 10.1109/IGARSS47720.2021.9553478
DO - 10.1109/IGARSS47720.2021.9553478
M3 - 会议稿件
AN - SCOPUS:85126022922
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 1662
EP - 1665
BT - IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Y2 - 12 July 2021 through 16 July 2021
ER -