基于生成对抗网络的SAR图像去噪

doi:10.3969/j.issn.1000-1565.2022.03.013

河北大学学报(自然科学版) ›› 2022, Vol. 42 ›› Issue (3): 306-313.DOI: 10.3969/j.issn.1000-1565.2022.03.013

基于生成对抗网络的SAR图像去噪

刘帅奇,雷钰,庞姣,赵淑欢,苏永钢,孙晨阳

收稿日期:2021-03-11 出版日期:2022-05-25 发布日期:2022-06-16
通讯作者: 庞姣(1979—)
作者简介:刘帅奇(1986—),男,河北石家庄人,河北大学副教授,博士,主要从事数字多维信号处理、图像处理研究.
E-mail:shdkj-1918@163.com
基金资助:
国家自然科学基金资助项目(62172139);河北大学研究生创新资助项目(HBU2021ss002);河北省自然科学基金资助项目(F2020201025);河北省高等学校科学技术研究资助项目(BJ2020030);国家重点实验室开放课题基金资助项目(20220007);河北大学校长基金资助项目(XZJJ201909)

SAR image denoising based on generative adversarial networks

LIU Shuaiqi, LEI Yu, PANG Jiao, ZHAO Shuhuan, SU Yonggang, SUN Chenyang

1. Machine Vision Technology Innovation Center of Hebei Province, College of Electronic and Informational Engineering, Hebei University, Baoding 071002, China

Received:2021-03-11 Online:2022-05-25 Published:2022-06-16

摘要/Abstract

摘要： 合成孔径雷达(synthetic aperture radar,SAR)图像是一种能够全天时、全天候产生高分辨率图像的主动式对地观测系统,在农业和军事等方面得到了广泛应用.然而,由于相干成像机制受到相干斑噪声的影响,因此提出了一种基于生成式对抗网络的SAR图像盲去噪算法,构造了基于残差结构的深度卷积神经网络(deep convolutional neural network,DCNN)作为生成网络,可以加速训练过程,提高去噪性能.本文还利用峰值信噪比(peak signal to noise ratio,PSNR)和结构相似指数(structural similarity index measure,SSIM)定义一种新的损失函数,使得去噪后的图像更符合人眼的视觉感知要求.实验结果表明,本文算法可以有效地抑制SAR图像中的相干噪声,获得良好的去噪效果.

关键词: SAR图像去噪, 生成对抗网络, 深度卷积神经网络, 损失函数

Abstract: Synthetic aperture radar(SAR)is a kind of active earth-observation system, which can produce high-resolution image all day and it has been widely used in agriculture and military. However, SAR image is affected by speckle due to the coherent imaging mechanism. In this paper, we propose a SAR image denoising algorithm based on generative adversarial network.We constructed the generated network by the structure of deep convolutional neural network(DCNN)with residual structure. The new generated network can accelerate the training process and improve the denoising performance. We also define a loss function by combining PSNR and SSIM, which makes the denoising result of SAR noisy image more in line with the visual perception requirements of human eyes. The experiment results show that the proposed algorithm can suppress speckle in SAR images and get good denoising result.

Key words: SAR image denoising, generative adversarial networks, deep convolutional neural network, loss function

中图分类号:

TN95

刘帅奇,雷钰,庞姣,赵淑欢,苏永钢,孙晨阳. 基于生成对抗网络的SAR图像去噪[J]. 河北大学学报(自然科学版), 2022, 42(3): 306-313.

LIU Shuaiqi, LEI Yu, PANG Jiao, ZHAO Shuhuan, SU Yonggang, SUN Chenyang. SAR image denoising based on generative adversarial networks[J]. Journal of Hebei University(Natural Science Edition), 2022, 42(3): 306-313.

参考文献

[1] 刘帅奇,扈琪,刘彤,等.合成孔径雷达图像去噪算法研究综述[J].兵器装备工程学报, 2018, 39(12): 106-112, 252. DOI:10.11809/bqzbgcxb2018.12.022.
[2] PAINAM R K, MANIKANDAN S. A comprehensive review of SAR image filtering techniques: systematic survey and future directions[J]. Arab J Geosci, 2021, 14(1): 1-15. DOI:10.1007/s12517-020-06416-1.
[3] GUAN D D, XIANG D L, TANG X A, et al. SAR image despeckling based on nonlocal low-rank regularization[J]. IEEE Trans Geosci Remote Sens, 2019, 57(6): 3472-3489. DOI:10.1109/TGRS.2018.2885089.
[4] 林景栋,吴欣怡,柴毅,等.卷积神经网络结构优化综述[J].自动化学报, 2020, 46(1): 24-37. DOI:10.16383/j.aas.c180275.
[5] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[J]. Commun ACM, 2020, 63(11): 139-144. DOI:10.1145/3422622.
[6] CRESWELL A, WHITE T, DUMOULIN V, et al. Generative adversarial networks: an overview[J]. IEEE Signal Process Mag, 2018, 35(1): 53-65. DOI:10.1109/MSP.2017.2765202.
[7] GOODMAN J W. Some fundamental properties of speckle[J]. J Opt Soc Am, 1976, 66(11): 1145. DOI:10.1364/josa.66.001145.
[8] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C] //2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778. DOI:10.1109/CVPR.2016.90.
[9] RAJ V B, HAREESH K.Review on generative adversarial networks[C] //2020 International Conference on Communication and Signal Processing(ICCSP), 2020: 479-482. DOI:10.1109/ICCSP48568.2020.9182058.
[10] THAKKAR V, TEWARY S, CHAKRABORTY C. Batch normalization in convolutional neural networks—a comparative study with CIFAR-10 data[C] //2018 Fifth International Conference on Emerging Applications of Information Technology(EAIT), 2018: 1-5. DOI:10.1109/EAIT.2018.8470438.
[11] LIU S Q, HU Q, LI P F, et al. Speckle suppression based on sparse representation with non-local priors[J]. Remote Sens, 2018, 10(3): 439. DOI:10.3390/rs10030439.
[12] LOPES A, TOUZI R, NEZRY E. Adaptive speckle filters and scene heterogeneity[J]. IEEE Trans Geosci Remote Sens, 1990, 28(6): 992-1000. DOI:10.1109/36.62623.
[13] LIU S Q, HU S H, XIAO Y, et al. Bayesian Shearlet shrinkage for SAR image de-noising via sparse representation[J]. Multidimens Syst Signal Process, 2014, 25(4): 683-701. DOI:10.1007/s11045-013-0225-8.
[14] PARRILLI S, PODERICO M, ANGELINO C V, et al. A nonlocal SAR image denoising algorithm based on LLMMSE wavelet shrinkage[J]. IEEE Trans Geosci Remote Sens, 2012, 50(2): 606-616. DOI:10.1109/TGRS.2011.2161586.
[15] LIU S Q, LIU T, GAO L L, et al. Convolutional neural network and guided filtering for SAR image denoising[J]. Remote Sens, 2019, 11(6): 702. DOI:10.3390/rs11060702.
[16] LIU S Q, HU Q, LI P F, et al. Speckle suppression based on sparse representation with non-local priors[J]. Remote Sens, 2018, 10(3): 439. DOI:10.3390/rs10030439. (

基于生成对抗网络的SAR图像去噪

SAR image denoising based on generative adversarial networks

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

本文评价

[1]	李凯,张辉,崔丽娟,彭锦佳,陈泰熙. 基于双域信息的深度残差网络图像去噪[J]. 河北大学学报(自然科学版), 2023, 43(2): 216-224.
[2]	申瑞彩,翟俊海,侯璎真. 多生成器生成对抗网络[J]. 河北大学学报(自然科学版), 2021, 41(6): 734-744.
[3]	刘蕊,续欣莹,谢珺. 基于多维度特征提取网络的肝脏图像分割[J]. 河北大学学报(自然科学版), 2021, 41(4): 426-435.
[4]	花强,刘轶功,张峰,董春茹. 基于Wasserstein距离的双向学习推理[J]. 河北大学学报(自然科学版), 2020, 40(3): 328-336.
[5]	庞姣,张世琪,刘帅奇. 基于非局部自适应字典的SAR图像迭代去噪算法[J]. 河北大学学报(自然科学版), 2018, 38(3): 309-314.
[6]	徐宝. 基于对称损失函数下Poisson分布变异系数的估计[J]. 河北大学学报(自然科学版), 2011, 31(1): 16-19.