SAR image despeckling using a CNN guided by high-frequency information

被引:2
|
作者
Tao, Shifei [1 ]
Li, Xinyi [1 ]
Ye, Xiaodong [1 ]
Wang, Hao [1 ]
Li, Xiang [2 ]
机构
[1] Nanjing Univ Sci & Technol, Sch Elect & Opt Engn, Nanjing, Peoples R China
[2] Northern Inst Elect Equipment China, Beijing, Peoples R China
关键词
Convolutional neural network (CNN); wavelet transformation; synthetic aperture radar (SAR); despeckling; block-matching and 3D filtering for SAR image despeckling (SAR-BM3D); high-frequency information; SPECKLE SUPPRESSION; TARGET DETECTION; FILTER; REDUCTION;
D O I
10.1080/09205071.2022.2145506
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Preserving image details is a challenging and significant task for synthetic aperture radar (SAR) image despeckling. In this paper, we proposed a high-frequency information extraction module based on block-matching and 3D filtering for SAR image despeckling (SAR-BM3D) and wavelet transformation to guide the denoisers based on a convolutional neural network (CNN). Firstly, SAR-BM3D is employed to conduct the initial speckle removal, and then Haar wavelet transformation takes the task of extracting high-frequency information of the initial despeckled image. The noisy image and the high-frequency information are merged together to be the input of the CNN, which makes it easier for the CNN-based denoisers to restore the textures and details of the SAR image. Extensive experiments on synthetic and real SAR images have been validated, which show that our method can effectively remove the speckle noise and improve the detail-preserving capacity of the CNN-based denoiser.
引用
收藏
页码:441 / 451
页数:11
相关论文
共 50 条
  • [1] SAR image despeckling using deep CNN
    Passah, Alicia
    Amitab, Khwairakpam
    Kandar, Debdatta
    IET IMAGE PROCESSING, 2021, 15 (06) : 1285 - 1297
  • [2] Nonlocal CNN SAR Image Despeckling
    Cozzolino, Davide
    Verdoliva, Luisa
    Scarpa, Giuseppe
    Poggi, Giovanni
    REMOTE SENSING, 2020, 12 (06)
  • [3] Contourlet-CNN for SAR Image Despeckling
    Liu, Gang
    Kang, Hongzhaoning
    Wang, Quan
    Tian, Yumin
    Wan, Bo
    REMOTE SENSING, 2021, 13 (04) : 1 - 19
  • [4] SAR DESPECKLING GUIDED BY AN OPTICAL IMAGE
    Verdoliva, L.
    Amitrano, D.
    Gaetano, R.
    Ruello, G.
    Poggi, G.
    2014 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2014, : 3698 - 3701
  • [5] A CNN-BASED METHOD FOR SAR IMAGE DESPECKLING
    Ma, Dejiao
    Zhang, Xiaoling
    Tang, Xinxin
    Ming, Jing
    Shi, Jun
    2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019), 2019, : 4272 - 4275
  • [6] Statistical based CNN algorithm for SAR image despeckling
    Vitale, Sergio
    Ferraioli, Giampaolo
    Pascazio, Vito
    13TH EUROPEAN CONFERENCE ON SYNTHETIC APERTURE RADAR, EUSAR 2021, 2021, : 996 - 1000
  • [7] Spatial and Transform Domain CNN for SAR Image Despeckling
    Liu, Zesheng
    Lai, Rui
    Guan, Juntao
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [8] A NEW RATIO IMAGE BASED CNN ALGORITHM FOR SAR DESPECKLING
    Vitale, Sergio
    Ferraioli, Giampaolo
    Pascazio, Vito
    2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019), 2019, : 9494 - 9497
  • [9] SAR Image Despeckling Employing a Recursive Deep CNN Prior
    Shen, Huanfeng
    Zhou, Chenxia
    Li, Jie
    Yuan, Qiangqiang
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2021, 59 (01): : 273 - 286
  • [10] A Fractional Total Variational CNN Approach for SAR Image Despeckling
    Bai, Yu-Cai
    Zhang, Sen
    Chen, Miao
    Pu, Yi-Fei
    Zhou, Ji-Liu
    INTELLIGENT COMPUTING METHODOLOGIES, ICIC 2018, PT III, 2018, 10956 : 431 - 442