Abstract
Synthetic aperture radar (SAR) plays an important role in monitoring the geographical environment with the ability of all-time, all-weather, but it is a challenge to improve the readability of SAR images. Generative adversarial networks are widely used in image translation, and it also helps to enhance the quality of the cross-domain image translation. In this paper, we propose an image translation method based on generative adversarial networks for SAR images quality enhancement, which innovatively fuses U-Net and T-Net as generators and adds perceptual loss and structural loss as objective functions. The features of SAR images extracted from residual networks are input to the T-Net branch for feature compensation and the U-Net branch for deep feature extraction. Experimental results with the SEN1-2 dataset show that the advantage of the proposed UTGAN model both in traditional quality assessment metrics like SSIM (Structural Similarity), PSNR (Peak Signal-to-Noise Ratio), and deep learning-based metrics like FID (Fréchet Inception Distance). The ablation experiments show that perceptual loss and structural similarity loss both have a positive effect on translation quality. From the objective analysis, the proposed model achieves 0.73 in SSIM, 22.31 in PSNR, and 205.75 in FID, which is better than the existing models. From the subjective analysis, the images generated by the proposed model are more consistent with human visual perception, with clearer textures and richer details.
Similar content being viewed by others
References
Alharbi Y, Smith NG, Wonka P (2019) Latent Filter Scaling for Multimodal Unsupervised Image-To-Image Translation. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 1458–1466
Bermudez JD, Happ PN, Oliveira DAB, Feitosa RQ (2018) Sar to Optical Image Synthesis for Cloud Removal with Generative Adversarial Networks. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, pp 5–11
Chen L, Wu L, Hu Z, Wang M (2019) Quality-aware unpaired image-to-image translation. IEEE Trans Multimed 21:2664–2674
Doi K, Sakurada K, Onishi M, Iwasaki A (2020) GAN-Based SAR-to-Optical Image Translation with Region Information. IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, pp 2069–2072
Enomoto K, Sakurada K, Wang W, Kawaguchi N, Matsuoka M, Nakamura R (2018) Image Translation Between Sar and Optical Imagery with Generative Adversarial Nets. IGARSS 2018–2018 IEEE International Geoscience and Remote Sensing Symposium, pp 1752–1755
Heusel M, Ramsauer H, et al (2017) GANs Trained by a Two Time-Scale Update Rule Converge to a Nash Equilibrium. arXiv preprint: arXiv: 1706.0850
Hughes LH, Schmitt M (2019) A semi-supervised approach to SAR-optical image matching. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, pp 71–78
Hwang J, Yu C, Shin Y (2020) SAR-to-Optical Image Translation Using SSIM and Perceptual Loss Based Cycle-Consistent GAN. In: 2020 International Conference on Information and Communication Technology Convergence (ICTC). IEEE, Jeju, Korea (South), pp 191–194
Isola P, Zhu J-Y, Zhou T, Efros AA (2017) Image-to-Image Translation with Conditional Adversarial Networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Honolulu, HI, pp 5967–5976
Jiang X, Liu M, Zhao F et al (2020) A novel super-resolution CT image reconstruction via semi-supervised generative adversarial network. Neural Comput & Applic 32:14563–14578
Karras T, Laine S, Aila T (2019) A Style-Based Generator Architecture for Generative Adversarial Networks. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Long Beach, CA, USA, pp 4396–4405
Kim T, Cha M, Kim H, et al (2017) Learning to Discover Cross-Domain Relations with Generative Adversarial Networks. In: International Conference on Machine Learning, pp 1857–1865
Kuang P, Ma T, Chen Z, Li F (2018) Image super-resolution with densely connected convolutional networks. Appl Intell 49:125–136
Ledig C, Theis L, Huszar F, et al (2017) Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Honolulu, HI, pp 105–114
Li X, Du Z, Huang Y, Tan Z (2021) A deep translation (GAN) based change detection network for optical and SAR remote sensing images. ISPRS J Photogramm Remote Sens 179:14–34
Lin T-Y, Dollar P, Girshick R, et al. (2017) Feature Pyramid Networks for Object Detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Honolulu, HI, pp 936–944
Ma J, Yu W, Chen C, Liang P, Guo X, Jiang J (2020) Pan-GAN: An unsupervised pan-sharpening method for remote sensing image fusion. Inf Fusion 62:110–120
Merkle N, Auer S, Muller R, Reinartz P (2018) Exploring the potential of conditional adversarial networks for optical and SAR image matching. IEEE J Sel Top Appl Earth Observ Remote Sens 11:1811–1820
Moreira A, Prats-Iraola P, Younis M et al (2013) A tutorial on synthetic aperture radar. IEEE Geosci Remote Sens Mag 1:6–43
Richardson E, Alaluf Y, Patashnik O, et al (2020) Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation. arXiv preprint: arXiv:2008.00951
Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention, pp 234–241
Sara U, Akter M, Uddin MS (2019) Image quality assessment through FSIM, SSIM, MSE and PSNR—a comparative study. J Comput Chem 7:8–18
Schmitt M, Hughes LH, Zhu XX (2018) THE SEN1–2 DATASET FOR DEEP LEARNING IN SAR-OPTICAL DATA FUSION. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, pp 141–146
Sheikh HR, Bovik AC (2006) Image information and visual quality. IEEE Trans Image Process 15:430–444. https://doi.org/10.1109/TIP.2005.859378
Wang Z, Bovik AC (2002) A universal image quality index. IEEE Signal Process Lett 9:81–84. https://doi.org/10.1109/97.995823
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13:600–612
Wang C, Xu C, Wang C, Tao D (2018a) Perceptual adversarial networks for image-to-image transformation. IEEE Trans Image Process 27:4066–4079
Wang P, Patel VM (2018b) Generating high quality visible images from SAR images using CNNs. In: 2018 IEEE Radar Conference (RadarConf18). IEEE, Oklahoma City, OK, pp 0570–0575
Wang T-C, Liu M-Y, Zhu J-Y et al (2018c) High-resolution image synthesis and semantic manipulation with conditional GANs. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, Salt Lake City, UT, USA, pp 8798–8807
Wang P, Li Y, Vasconcelos N (2021) Rethinking and Improving the Robustness of Image Style Transfer. arXiv preprint: arXiv: 2104.05623
Yi Z, Zhang H, Tan P, Gong M (2017) DualGAN: Unsupervised Dual Learning for Image-to-Image Translation. In: 2017 IEEE International Conference on Computer Vision (ICCV). IEEE, Venice, pp 2868–2876
Yim C, Bovik AC (2011) Quality assessment of deblocked images. IEEE Trans Image Process 20:88–98. https://doi.org/10.1109/TIP.2010.2061859
Yu T, Zhang J, Zhou J (2021) Conditional GAN with Effective Attention for SAR-to-Optical Image Translation. In: 2021 3rd International Conference on Advances in Computer Technology, Information Science and Communication (CTISC), pp 7–11
Zhang L, Zhang L, Mou X, Zhang D (2011) FSIM: a feature similarity index for image quality assessment. IEEE Trans on Image Process 20:2378–2386
Zhang R, Isola P, Efros AA, et al (2018) The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, Salt Lake City, UT, pp 586–595
Zhu J-Y, Park T, Isola P, Efros AA (2017) Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In: 2017 IEEE International Conference on Computer Vision (ICCV). IEEE, Venice, pp 2242–2251
Zuo Z, Li Y (2021) A SAR-to-optical image translation method based on PIX2PIX. In: 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, pp 3026–3029
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interest with any person(s) or Organization(s).
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Luo, Y., Pi, D. SAR-to-optical image translation for quality enhancement. J Ambient Intell Human Comput 14, 9985–10000 (2023). https://doi.org/10.1007/s12652-021-03665-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-021-03665-0