High Power Laser and Particle Beams, Volume. 35, Issue 12, 123002(2023)

Research on wideband electromagnetic image striping noise removal method based on BiGRU-CNN

Yanju Zhu1,2, Zihan Zhao1, and Zhiwei Gao1,2、*
Author Affiliations
  • 1School of Information Science and Technology, Shijiazhuang Tiedao University, Shijiazhuang 050043, China
  • 2Hebei Key Laboratory of Electromagnetic Environmental Effects and Information Processing, Shijiazhuang 050043, China
  • show less

    The electromagnetic detection and imaging system enables wide-range, wideband, and fast localization of electromagnetic interference sources. The system primarily consists of a parabolic reflector and a multi-channel ultra-wideband signal acquisition system. Due to variations in device parameters across channels caused by manufacturing processes, it is impossible to achieve complete consistency, resulting in stripe noise in the obtained electromagnetic images that significantly affects localization accuracy. A bidirectional gated recurrent unit (BiGRU)-convolutional neural network (CNN) model was constructed, which constructs a dataset based on the measured data as the input. The BiGRU and the CNN utilize the strong correlation between neighboring rows of the image to extensively collect redundant information from the past and future inputs, to extract the stripe noise and to integrate the spatial information, and to utilize the difference between the data for loop iteration of this process. The model is validated through a large number of experiments and the BiGRU-CNN method outperforms other tested (classical) methods by reducing the vertical gradient energy by 15.2% and the residual nonuniformity by 21.9%.


    Get Citation

    Copy Citation Text

    Yanju Zhu, Zihan Zhao, Zhiwei Gao. Research on wideband electromagnetic image striping noise removal method based on BiGRU-CNN[J]. High Power Laser and Particle Beams, 2023, 35(12): 123002

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information


    Received: Jul. 29, 2023

    Accepted: Oct. 25, 2023

    Published Online: Dec. 27, 2023

    The Author Email: Gao Zhiwei (gao_zhiwei@163.com)