基于深度学习的星系图重建方法研究
Research on Galaxy Map Reconstruction Method Based on Deep Learning
DOI: 10.12677/SEA.2022.115118, PDF,    国家自然科学基金支持
作者: 吴康宁, 蔡宇佳：贵州大学大数据与信息工程学院，贵州 贵阳；张 利*：贵州大学大数据与信息工程学院，贵州 贵阳；贵州大学省部共建公共大数据国家重点实验室，贵州 贵阳
关键词: 生成对抗网络；残差特征；特征融合；图像重建；Generative Adversarial Network； Residual Structure； Feature Fusion； Image Reconstruction
摘要: 为了帮助分析早期宇宙中的星系，需要对图像精确建模，由于在观测成像过程中傅里叶域的稀疏采样,导致传统反卷积算法重建成像数据特征的能力有限，并且早先将神经网络模型探索性地应用于天体物理对象重建，其模型的适配性和优化不足，导致重建性能较差。在此，我们利用斯隆数字巡天的数据进行模拟观测成像，并提出了基于特征融合的生成模型对其观测数据进行重建。通过定性定量测试，也证明该模型很好地从脏图中恢复了成像数据特征，其性能远超传统重建算法，从而可以进一步帮助分析早期宇宙中的星系以及未来应用于不同物理性质的望远镜系统中。
Abstract: To help analyze galaxies in the early universe, images need to be accurately modeled, due to the sparse sampling of the Fourier domain in the process of observation and imaging, the ability of traditional deconvolution algorithms to reconstruct the features of imaging data is limited, and applies neural network model of the exploratory earlier astrophysical object reconstruction, the suitability of its model and optimize the shortage, poor performance in reconstruction. Here, we train the generative model based on feature fusion to reconstruct the galaxy map through the data of the Sloan Digital Sky Survey. Qualitative and quantitative tests also prove that the model is good at recovering the image data features from the dirty map, and its performance is far better than the traditional reconstruction algorithm which could further aid in the analysis of galaxies in the early universe and future applications to telescope systems with different physical properties.
文章引用：吴康宁, 张利, 蔡宇佳. 基于深度学习的星系图重建方法研究[J]. 软件工程与应用, 2022, 11(5): 1154-1165. https://doi.org/10.12677/SEA.2022.115118

参考文献

[1] Kevin, S., Zhang, C., Zhang, H., et al. (2017) Generative Adversarial Networks Recover Features in Astrophysical Images of Galaxies beyond the Deconvolution Limit. Monthly Notices of the Royal Astronomical Society Letters, 467, L110-L114. [Google Scholar] [CrossRef] 
[2] Xu, L., Sun, W., Yan, Y., et al. (2020) Solar Image Deconvolution by Generative Adversarial Network. Research in Astronomy and Astrophysics, 20, Article No. 170. [Google Scholar] [CrossRef] 
[3] Zhang, L., Bhatnagar, S., Rau, U., et al. (2016) Efficient Implementation of the Adaptive Scale Pixel Decomposition Algorithm. Astronomy and Astrophysics, 592, Article No. A128. [Google Scholar] [CrossRef] 
[4] Courbin, F., Lidman, C., Frye, B.L., et al. (1998) Image Deconvolution of the Radio Ring PKS 1830-211. Astrophysical Journal, 499, L119-L123. [Google Scholar] [CrossRef] 
[5] Courbin, F., Magain, P., Kirkove, M., et al. (1999) A Method for Spatial Deconvolution of Spectra. The Astrophysical Journal, 529, 1136-1144. [Google Scholar] [CrossRef] 
[6] Querre, P. and Starck, J.L. (2002) Analysis of the Galaxy Distribution Using Multiscale Methods. Proceedings of SPIE—The International Society for Optical Engineering, 4847, 285-296. [Google Scholar] [CrossRef] 
[7] Bell, A.J. and Sejnowski, T.J. (1995) An Information-Maximization Approach to Blind Separation and Blind Deconvolution. Neural Computation, 7, 1129-1159. [Google Scholar] [CrossRef] [PubMed]
[8] Zhang, L. (2018) Fused CLEAN Deconvolution for Compact and Diffuse Emission. Astronomy and Astrophysics, 618, Article No. A117. [Google Scholar] [CrossRef] 
[9] Castleman, K.R. (1996) Digital Image Processing. Prentice-Hall, Hoboken.
[10] Zhang, L., et al. (2019) An Adaptive Loop Gain Selection for CLEAN Deconvolution Algorithm. Research in Astronomy and Astrophysics, 19, Article No. 79. [Google Scholar] [CrossRef] 
[11] Zhang, L., Xu, L. and Zhang, M. (2020) Parameterized CLEAN Deconvolution in Radio Synthesis Imaging. Publications of the Astronomical Society of the Pacific, 132, Article ID: 041001. [Google Scholar] [CrossRef] 
[12] Zhang, L., Mi, L.G., Zhang, M., et al. (2021) Parameterized Reconstruction with Random Scales for Radio Synthesis Imaging. Astronomy and Astrophysics, 646, Article No. A44. [Google Scholar] [CrossRef] 
[13] Zhang, L., Mi, L.G., Zhang, M., et al. (2020) Adaptive-Scale Wide-Field Reconstruction for Radio Synthesis Imaging. Astronomy and Astrophysics, 640, Article No. A80. [Google Scholar] [CrossRef] 
[14] Zhang, L., et al. (2021) Adaptive Scale Model Reconstruction for Radio Synthesis Imaging. Research in Astronomy and Astrophysics, 21, Article No. 63.
[15] Joshi, N.S. (2008) Enhancing Photographs Using Content-Specific Image Priors. University of California, San Diego.
[16] Cho, S. and Lee, S. (2009) Fast Motion Deblurring. ACM Transactions on Graphics, 28, 1-8. [Google Scholar] [CrossRef] 
[17] 陈锡明, 黄硕翼. 盲源分离综述——问题、原理和方法[J]. 电子信息对抗技术, 2008, 23(2): 1-5+45.
[18] Isola, P., Zhu, J.Y., Zhou, T., et al. (2016) Image-to-Image Translation with Conditional Adversarial Networks. IEEE Conference on Computer Vision & Pattern Recognition, Honolulu, 21-26 July 2017, 5967-5976. [Google Scholar] [CrossRef] 
[19] Wang, C., Xu, C., Wang, C., et al. (2018) Perceptual Adversarial Networks for Image-to-Image Transformation. IEEE Transactions on Image Processing, 27, 4066-4079. [Google Scholar] [CrossRef] 
[20] Liu, S., Sun, Y., Zhu, D., et al. (2018) Face Aging with Contextual Generative Adversarial Nets. MM’17: Proceedings of the 25th ACM International Conference on Multimedia, Mountain View, 23-27 October 2017, 82-90. [Google Scholar] [CrossRef] 
[21] Hu, D., Wang, L., Jiang, W., et al. (2018) A Novel Image Steganography Method via Deep Convolutional Generative Adversarial Networks. IEEE Access, 6, 38303-38314. [Google Scholar] [CrossRef] 
[22] Odena, A., Olah, C. and Shlens, J. (2016) Conditional Image Synthesis with Auxiliary Classifier GANs.
[23] Zhan, Y., Hu, D., Wang, Y., et al. (2018) Semisupervised Hyperspectral Image Classification Based on Generative Adversarial Networks. IEEE Geoscience and Remote Sensing Letters, 15, 212-216. [Google Scholar] [CrossRef] 
[24] Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., et al. (2014) Generative Adversarial Networks. Proceedings of the 27th International Conference on Neural Information Processing Systems, Volume 2, 2672-2680.
[25] Cao, Y.J., Jia, L.L., Chen, Y.X., et al. (2019) Recent Advances of Generative Adversarial Networks in Computer Vision. IEEE Access, 7, 14985-15006. [Google Scholar] [CrossRef] 
[26] Lecun, Y., Bengio, Y. and Hinton, G. (2015) Deep Learning. Nature, 521, 436-444. [Google Scholar] [CrossRef] [PubMed]
[27] Mirza, M. and Osindero, S. (2014) Conditional Generative Adversarial Nets. arXiv, 1411.1784.
https://arxiv.org/abs/1411.1784
[28] Hendrycks, D. and Gimpel, K. (2016) Gaussian Error Linear Units (GELUs).
[29] Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. Springer International Publishing, Berlin. [Google Scholar] [CrossRef] 
[30] He, K., Zhang, X., Ren, S., et al. (2016) Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 770-778. [Google Scholar] [CrossRef] 
[31] Pathak, D., Krahenbuhl, P., Donahue, J., et al. (2016) Context Encoders: Feature Learning by Inpainting. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 2536-2544. [Google Scholar] [CrossRef] 
[32] Sola, J. and Sevilla, J. (1997) Importance of Input Data Normalization for the Application of Neural Networks to Complex. IEEE Transactions on Nuclear Science, 44, 1464-1464. [Google Scholar] [CrossRef] 
[33] Lucy, B.L. (1974) An Iterative Technique for the Rectification of Observed Distributions. Astronomical Journal, 79, 745-754. [Google Scholar] [CrossRef] 
[34] Richardson, W.H. (2017) Bayesian-Based Iterative Method of Image Restoration. Journal of the Optical Society of America, 62, 55-59.
[35] Horé, A. and Ziou, D. (2010) Image Quality Metrics: PSNR vs. SSIM. 20th International Conference on Pattern Recognition, ICPR 2010, Istanbul, 23-26 August 2010, 2366-2369. [Google Scholar] [CrossRef] 
[36] Zhou, W., Bovik, A.C., Sheikh, H.R., et al. (2004) Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Transactions on Image Processing, 13, 600-612. [Google Scholar] [CrossRef] 
[37] Buta, R. and Combes, F. (1996) Galactic Rings. Fundamentals of Cosmic Physics, 17, 95-281.

为你推荐