Please wait a minute...
 首页  期刊介绍 期刊订阅 联系我们 横山亮次奖 百年刊庆
 
最新录用  |  预出版  |  当期目录  |  过刊浏览  |  阅读排行  |  下载排行  |  引用排行  |  横山亮次奖  |  百年刊庆
清华大学学报(自然科学版)  2022, Vol. 62 Issue (10): 1691-1696    DOI: 10.16511/j.cnki.qhdxxb.2021.26.038
  核能与新能源技术 本期目录 | 过刊浏览 | 高级检索 |
基于生成对抗网络的车辆辐射图像复原方法
冷智颖1,2, 孙跃文1,2, 童建民1,2, 王振涛1,2
1. 清华大学 核能与新能源技术研究院, 北京 100084;
2. 核检测技术北京市重点实验室, 北京 100084
Vehicle radiation image restoration based on a generative adversarial network
LENG Zhiying1,2, SUN Yuewen1,2, TONG Jianmin1,2, WANG Zhentao1,2
1. Institute of Nuclear and New Energy Technology, Tsinghua University, Beijing 100084, China;
2. Beijing Key Laboratory on Nuclear Detection & Measurement Technology, Beijing 100084, China
全文: PDF(5396 KB)   HTML
输出: BibTeX | EndNote (RIS)      
摘要 在车辆辐射成像过程中,受到射线源的几何尺寸、探测器及信号放大电路响应时间、统计涨落等降质因素的影响,图像产生退化,表现为模糊与噪声增加。针对车辆辐射图像的退化问题,该文研究了辐射成像系统的退化模型,提出了利用生成对抗网络DeblurGAN的辐射图像复原方法。通过辐射图像的退化机制构造了辐射图像的特定数据集,用于训练DeblurGAN模型,利用训练好的模型去复原系统实际采集的车辆辐射图像。实验结果表明:该方法能够有效去除辐射图像的模糊与噪声,改善系统的成像质量。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
冷智颖
孙跃文
童建民
王振涛
关键词 辐射图像退化模型生成对抗网络图像复原    
Abstract:In vehicle radiation imaging,the size of the gamma ray source,the response time of detector and signal amplification circuits,statistical fluctuations and other factors degrade the image with blurring and noise.A model was developed to predict the image degradation in a radiation imaging system to support a radiation image restoration method based on DeblurGAN.A set of radiation images with simulated blurring was used to train the DeblurGAN model that was then used to restore the images.The results show that this method effectively eliminates blurring and noise in radiation images to improve imaging quality.
Key wordsradiation image    degradation model    generative adversarial network    image restoration
收稿日期: 2021-06-17      出版日期: 2022-09-03
基金资助:王振涛,副研究员,E-mail:wangzt@tsinghua.edu.cn
引用本文:   
冷智颖, 孙跃文, 童建民, 王振涛. 基于生成对抗网络的车辆辐射图像复原方法[J]. 清华大学学报(自然科学版), 2022, 62(10): 1691-1696.
LENG Zhiying, SUN Yuewen, TONG Jianmin, WANG Zhentao. Vehicle radiation image restoration based on a generative adversarial network. Journal of Tsinghua University(Science and Technology), 2022, 62(10): 1691-1696.
链接本文:  
http://jst.tsinghuajournals.com/CN/10.16511/j.cnki.qhdxxb.2021.26.038  或          http://jst.tsinghuajournals.com/CN/Y2022/V62/I10/1691
  
  
  
  
  
  
  
  
  
  
  
[1] KUPYN O, BUDZAN V, MYKHAILYCH M, et al. DeblurGAN:Blind motion deblurring using conditional adversarial networks[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA:IEEE, 2018:8183-8192.
[2] 顾伯华,周立业,安继刚.辐射成像无损检测技术中辐射源几何尺寸引起图像模糊的恢复[J].核电子学与探测技术, 2002, 22(1):17-19.GU B H, ZHOU L Y, AN J G. Restoration of blurred image caused by the size of radiation source in NDT digital radiography[J]. Nuclear Electronics and Detection Technology, 2002, 22(1):17-19.(in Chinese)
[3] 刘锡明,吴志芳,安继刚,等. 60Co集装箱检测系统直流模式下图像模糊问题的研究[J].核电子学与探测技术, 2000, 20(5):332-335. LIU X M, WU Z F, AN J G, et al. Restoration from the blurred image caused by the continuous characteristic of the 60Co container inspection system[J]. Nuclear Electronics and Detection Technology, 2000, 20(5):332-335.(in Chinese)
[4] 吴志芳,刘锡明,苗积臣.钴-60集装箱检测系统的冲激响应和图像时域反卷积算法[J].原子能科学技术, 2002, 36(3):235-237. WU Z F, LIU X M, MIAO J C. Impulse response function and time-field anti-convolution method of 60Co container inspection system[J]. Atomic Energy Science and Technology, 2002, 36(3):235-237.(in Chinese)
[5] 夏雄军.辐射图像噪声及CT环形伪影消除[D].北京:清华大学, 2007. XIA X J. Reduction of radiation image noise and CT ring artifacts[D]. Beijing:Tsinghua University, 2007.(in Chinese)
[6] 江孝国,王婉丽,王伟,等.台阶法测量辐射成像系统扩展函数的误差分析[J].强激光与粒子束, 2004, 16(6):693-696. JIANG X G, WANG W L, WANG W, et al. Error analysis on the measurement of spread function of radiography system by step method[J]. High Power Laser and Particle Beams, 2004, 16(6):693-696.(in Chinese)
[7] ISOLA P, ZHU J Y, ZHOU T H, et al. Image-to-image translation with conditional adversarial networks[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA:IEEE, 2017:5967-5976.
[8] ARJOVSKY M, CHINTALA S, BOTTOU L. Wasserstein GAN[J]. arXiv preprint arXiv, 2017:1701.07875.
[9] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv, 2014:1409.1556.
[10] JOHNSON J, ALAHI A, FEI-FEI L. Perceptual losses for real-time style transfer and super-resolution[C]//Proceedings of the 14th European Conference on Computer Vision. Amsterdam, Netherlands:Springer, 2016:694-711.
[11] KINGMA D P, BA J. Adam:A method for stochastic optimization[J]. arXiv preprint arXiv, 2014:1412.6980.
[12] DEY N, BLANC-FERAUD L, ZIMMER C, et al. Richardson-Lucy algorithm with total variation regularization for 3D confocal microscope deconvolution[J]. Microscopy Research and Technique, 2006, 69(4):260-266.
[1] 刘元鑫, 廖文杰, 林元庆, 解琳琳, 陆新征. 数据特征对剪力墙结构生成式智能设计的影响[J]. 清华大学学报(自然科学版), 2023, 63(12): 2005-2018.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 《清华大学学报(自然科学版)》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn