星系图像超分辨率重建技术研究
Research on Super Resolution Reconstruction Technique of Galaxy Image
DOI: 10.12677/ORF.2023.136750, PDF,  被引量    国家自然科学基金支持
作者: 彭 嘉, 罗珺茜, 周 娟, 马 帅, 韦焕泽, 张 利*：贵州大学大数据与信息工程学院，贵州 贵阳
关键词: SKA星系图像；超分辨率重建；生成对抗网络；SKA Galaxy Image； Super Resolution Reconstruction； Generative Adversarial Network
摘要: SKA1-low接收到的无线电信号转换为图像数据后，由于各种因素的干扰会导致图像的分辨率模糊不清，使得天文学家难以从中获取清晰完整的星系信息。针对这一现象，本文计划在生成对抗网络SRGAN的基础上，对其基础模块进行调整优化，使之更利于重建SKA星系图像。本文采用改进SRGAN的星系图像超分辨率重建算法在星系图像数据集上进行训练及测试，实验结果在原模型上PSNR值提升了3.02 db，SSIM值提升了0.0551 db；此外，本文另从定性与定量两方面与SRResCCGAN、IMDN、LAPAR、及BebyGAN等主流模型作对比，从定量角度分析，PSNR值分别提升了1.96 DB、1.59 DB、4.88 DB、0.81 DB，SSIM值分别提升了0.1103、0.056、0.0381、0.0141，两种主流评价指标数值均有所提升；从定性角度分析，本文模型相较于其他经典模型，重建所得图像的边缘信息更加清晰，更有效地复原了星系图像的细节信息。
Abstract: After the radio signal received by SKA1-low is converted into image data, the resolution of the image will be blurred due to various factors, making it difficult for astronomers to obtain clear and complete galaxy information. In view of this phenomenon, this paper plans to adjust and optimize the basic module of SRGAN based on the generation of adversarial network, so as to make it more conducive to the reconstruction of SKA galaxy images. In this paper, the galaxy image super-resolution reconstruction algorithm with improved SRGAN is used for training and testing on the galaxy image dataset. The experimental results show that the PSNR value is increased by 3.05 DB and SSIM value is increased by 0.0551 DB on the original model. In addition, this paper also made qualitative and quantitative comparisons with SRResCCGAN, IMDN, LAPAR and BebyGAN models. From a quantitative perspective, the PSNR value increased by 1.96 DB, 1.59 DB, 4.88 DB and 0.81 DB respectively. SSIM values increased by 0.1103, 0.056, 0.0381 and 0.0141 respectively, and the values of the two mainstream evaluation indicators were all improved. From the qualitative point of view, compared with other classical models, the edge information of the reconstructed image is clearer and the details of the galaxy image can be recovered more effectively.
文章引用：彭嘉, 罗珺茜, 周娟, 马帅, 韦焕泽, 张利. 星系图像超分辨率重建技术研究[J]. 运筹与模糊学, 2023, 13(6): 7655-7662. https://doi.org/10.12677/ORF.2023.136750

参考文献

[1] An, T., Wu, X., Lao, B., et al. (2022) Status and Progress of China SKA Regional Centre prototype. Science China (Physics, Mechanics & Astronomy), 65, 76-94. [Google Scholar] [CrossRef] 
[2] Zhang, L., Zhang, M. and Liu, X. (2016) The Adaptive-Loop-Gain Adaptive-Scale CLEAN Deconvolution of Radio Inter-ferometric Images. Astrophysics and Space Science, 361, 1-6. [Google Scholar] [CrossRef] 
[3] Zhang, L., Xu, L., Zhang, M. and Wu, Z.Z. (2019) An Adaptive Loop Gain Selection for CLEAN Deconvolution Algorithm. Research in Astronomy and Astrophysics, 19, 79-1-79-6. [Google Scholar] [CrossRef] 
[4] Zhang, L., Xu, L. and Zhang, M. (2020) Parame-terized CLEAN Deconvolution in Radio Synthesis Imaging. Publications of the Astronomical Society of the Pacific, 132, 1-13. [Google Scholar] [CrossRef] 
[5] Gerchberg, R.W. (1974) Super-Resolution through Error Energy Reduction. Journal of Modern Optics, 21, 709-720. [Google Scholar] [CrossRef] 
[6] Tsai, R. (1984) Multiframe Image Restoration and Registration. Advance Computer Visual and Image Processing, 1, 317-339.
[7] Dong, C., Loy, C.C., He, K.M., et al. (2014) Learning a Deep Convolutional Network for Image Super Resolution. In: Fleet, D., Pajdla, T., Schiele, B. and Tuytelaars, T., Eds., Computer Vision—ECCV 2014, Springer, Cham, 184-199. [Google Scholar] [CrossRef] 
[8] Dong, C., Loy, C.C., He, K.M., et al. (2015) Image Su-per-Resolution Using Deep Convolutional Networks. IEEE Transactions on Pattern Analysis and Mmachine Intel-ligence, 38, 295-307. [Google Scholar] [CrossRef] 
[9] Kim, J., Lee, J.K. and Lee, K.M. (2016) Deeply-Recursive Convolutional Network for Image Super-Resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 1637-1645. [Google Scholar] [CrossRef] 
[10] Kim, J., Lee, J.K. and Lee, K.M. (2016) Accurate Image Su-per-Resolution Using Very Deep Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 1646-1654. [Google Scholar] [CrossRef] 
[11] Ledig, C., Theis, L., Huszár, F., et al. (2017) Photo-Realistic Single Image Superresolution Using a Generative Adversarial Network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 21-26 July 2017, Hawaii, USA, 4681-4690. [Google Scholar] [CrossRef] 
[12] Zhang, Y., Li, K., Li, K., et al. (2018) Image Super-Resolution Using Very Deep Residual Channel Attention Networks. Proceedings of the European Conference on Computer Vision, ECCV 2018, 8-14 September 2018, Munich, 286-301. [Google Scholar] [CrossRef] 
[13] Hu, J., Shen, L. and Sun, G. (2018) Squeeze-and-Excitation Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recogni-tion, Salt Lake City, 18-23 June 2018, 7132-7141. [Google Scholar] [CrossRef] 
[14] Muhammad Umer, R., Luca Foresti, G. and Micheloni, C. (2020) Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-Resolution. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, 14-19 June 2020, 1769-1777. [Google Scholar] [CrossRef] 
[15] Hui, Z., Gao, X., Yang, Y. and Wang, X. (2019) Lightweight Image Super-Resolution with Information Multi-distillation Network. Proceedings of the 27th ACM International Conference on Multimedia, 15-19 October 2019, Beijing, 2024-2032. [Google Scholar] [CrossRef] 
[16] Li, W., Zhou, K., Qi, L., Jiang, N., Lu, J. and Jia, J. (2020) LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond. Neural Information Processing Systems. [Google Scholar] [CrossRef] 
[17] Li, W., Zhou, K., Qi, L., Lu, L. and Lu, J. (2022) Best-Buddy GANs for Highly Detailed Image Super-Resolution. Proceedings of the AAAI Conference on Artificial Intelligence, 36, 1412-1420. [Google Scholar] [CrossRef] 

为你推荐