SAR image denoising based on generative adversarial networks

doi:10.3969/j.issn.1000-1565.2022.03.013

Abstract

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

CLC Number:

TN95

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.

References

[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. (