Restoration of turbulence-degraded images based on deep convolutional network

Xiangyu Bai, Ming Liu, Chuan He, Liquan Dong, Yuejin Zhao, Xiaohua Liu

科研成果: 书/报告/会议事项章节会议稿件同行评审

8 引用 (Scopus)

摘要

Atmospheric turbulence is an irregular form of motion in the atmosphere. Because of turbulence interference, when the optical system through the atmosphere of the target imaging, the observed image will appear point intensity diffusion, image blur, image drift and other turbulence effects. Digital recovery of the turbulence-degraded images technique is a classical ill-conditioned problem by removing the blurring effect and suppressing the noise. Traditional approaches relying on image heuristics suffer from high frequency noise amplification and processing artifacts. In this paper, the image degradation models of the turbulent flow are given, the point spread function of turbulence is simulated by the similar Gaussian function model, and investigated a general framework of neural networks for restoring turbulence-degraded images. The blur and additive noise are considered simultaneously. Two solutions respectively exploiting fully convolutional networks (FCN) and conditional Generative Adversarial Networks (CGAN) are presented. The FCN based on minimizing the mean squared reconstruction error (MSE) in pixel space gets high PSNR. On the other side, the CGAN based on perceptual loss optimization criterion retrieves more textures. We conduct comparison experiments to demonstrate the performance at different degree of turbulence intensity from the training configuration. The results indicate that the proposed networks outperform traditional approaches for restoring high frequency details and suppressing noise effectively.

源语言英语
主期刊名Applications of Machine Learning
编辑Michael E. Zelinski, Tarek M. Taha, Jonathan Howe, Abdul A. S. Awwal, Khan M. Iftekharuddin
出版商SPIE
ISBN(电子版)9781510629714
DOI
出版状态已出版 - 2019
活动Applications of Machine Learning 2019 - San Diego, 美国
期限: 13 8月 201914 8月 2019

出版系列

姓名Proceedings of SPIE - The International Society for Optical Engineering
11139
ISSN(印刷版)0277-786X
ISSN(电子版)1996-756X

会议

会议Applications of Machine Learning 2019
国家/地区美国
San Diego
时期13/08/1914/08/19

指纹

探究 'Restoration of turbulence-degraded images based on deep convolutional network' 的科研主题。它们共同构成独一无二的指纹。

引用此

Bai, X., Liu, M., He, C., Dong, L., Zhao, Y., & Liu, X. (2019). Restoration of turbulence-degraded images based on deep convolutional network. 在 M. E. Zelinski, T. M. Taha, J. Howe, A. A. S. Awwal, & K. M. Iftekharuddin (编辑), Applications of Machine Learning 文章 111390B (Proceedings of SPIE - The International Society for Optical Engineering; 卷 11139). SPIE. https://doi.org/10.1117/12.2527593