A Novel Cost Function for Despeckling using Convolutional Neural Networks

被引:11
|
作者
Ferraioli, Giampaolo [1 ]
Pascazio, Vito [2 ]
Vitale, Sergio [2 ]
机构
[1] Univ Napoli Parthenope, Dipartimento Sci & Tecnol, Naples, Italy
[2] Univ Napoli Parthenope, Dipartimento Ingn, Naples, Italy
关键词
SAR; speckle; cnn; despeckling; deep learning; NOISE;
D O I
10.1109/jurse.2019.8809042
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
Removing speckle noise from SAR images is still an open issue. It is well know that the interpretation of SAR images is very challenging and despeckling algorithms are necessary to improve the ability of extracting information. An urban environment makes this task more heavy due to different structures and to different objects scale. Following the recent spread of deep learning methods related to several remote sensing applications, in this work a convolutional neural networks based algorithm for despeckling is proposed. The network is trained on simulated SAR data. The paper is mainly focused on the implementation of a cost function that takes account of both spatial consistency of image and statistical properties of noise.
引用
收藏
页数:4
相关论文
共 50 条
  • [1] Polarimetric SAR Despeckling With Convolutional Neural Networks
    Tucker, David
    Potter, Lee C.
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [2] NONLOCAL SAR IMAGE DESPECKLING BY CONVOLUTIONAL NEURAL NETWORKS
    Cozzolino, D.
    Verdoliva, L.
    Scarpa, G.
    Poggi, G.
    [J]. 2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019), 2019, : 5117 - 5120
  • [3] SAR IMAGE DESPECKLING THROUGH CONVOLUTIONAL NEURAL NETWORKS
    Chierchia, G.
    Cozzolino, D.
    Poggi, G.
    Verdoliva, L.
    [J]. 2017 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2017, : 5438 - 5441
  • [4] SAR DESPECKLING USING OVERCOMPLETE CONVOLUTIONAL NETWORKS
    Perera, Malsha V.
    Bandara, Wele Gedara Chaminda
    Valanarasu, Jeya Maria Jose
    Patel, Vishal M.
    [J]. 2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 401 - 404
  • [5] Synthetic aperture radar image despeckling using convolutional neural networks in wavelet domain
    Liu, Jing
    Liu, Runchuan
    [J]. IET IMAGE PROCESSING, 2023, 17 (09) : 2561 - 2574
  • [6] SAR Image Despeckling Using a Convolutional Neural Network
    Wang, Puyang
    Zhang, He
    Patel, Vishal M.
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2017, 24 (12) : 1763 - 1767
  • [7] Self-calibrated dilated convolutional neural networks for SAR image despeckling
    Yuan, Ye
    Wu, Yanxia
    Tang, Chuheng
    Fu, Yan
    Wu, Yulei
    Jiang, Yan
    Zhao, Yize
    [J]. INTERNATIONAL JOURNAL OF REMOTE SENSING, 2022, 43 (17) : 6483 - 6508
  • [8] A Despeckling Method Using Stationary Wavelet Transform and Convolutional Neural Network
    Kim, Moonheum
    Lee, Junghyun
    Jeong, Jechang
    [J]. 2018 INTERNATIONAL WORKSHOP ON ADVANCED IMAGE TECHNOLOGY (IWAIT), 2018,
  • [9] A novel companion objective function for regularization of deep convolutional neural networks
    Sun, Weichen
    Su, Fei
    [J]. IMAGE AND VISION COMPUTING, 2017, 60 : 58 - 63
  • [10] Convolutional Neural Networks at Constrained Time Cost
    He, Kaiming
    Sun, Jian
    [J]. 2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2015, : 5353 - 5360