宽带电磁图像卷积神经网络盲恢复方法研究

朱艳菊; 谢树果; 李元豪; 张娴

doi:10.11884/HPLPB201931.190191

宽带电磁图像卷积神经网络盲恢复方法研究

doi: 10.11884/HPLPB201931.190191

北京航空航天大学电子信息工程学院电磁兼容技术研究所, 北京 100191

基金项目:

国家自然科学基金项目 61427803

详细信息

作者简介:
朱艳菊(1985—)，女，博士研究生，从事电磁兼容、电磁图像处理、散射计算方面的研究; zhuyanju1309@163.com

中图分类号: TP391
计量
- 文章访问数: 986
- HTML全文浏览量: 278
- PDF下载量: 31
- 被引次数: 0
出版历程
- 收稿日期: 2019-05-30
- 修回日期: 2019-06-17
- 刊出日期: 2019-10-15

Research on blind recovery method of wideband electromagnetic image convolutional neural network

EMC Research Institute, Electronic Information Engineering College, Beihang University, Beijing 100191, China

摘要

摘要: 在利用抛物反射面对电磁干扰源成像过程中，由于系统衍射受限及成像频带较宽，导致干扰源成像模糊，分辨率低，难以分辨，不同频率不同区域干扰源所成图像分辨率不同，采用已有超分辨算法难以提高分辨率。为了实现宽带电磁图像的盲复原, 应用卷积神经网络的方法。网络训练是直接输入模糊图像，不假设任何特定的模糊和噪声模型情况下，重建出高质量图像。实验和仿真结果证明了卷积神经网络盲恢复方法在宽频带不同成像区域下表现了优于其他盲恢复算法的优势。
- 卷积神经网络 /
- 宽带电磁图像 /
- 盲恢复 /
- 电磁干扰源
Abstract: In the process of electromagnetic interference sources imaging testing using parabolic reflection, the diffraction phenomenon of the system leads to blurred and low resolution images. Interference sources have different resolution capabilities in different areas and frequencies, so it's difficult to enhance image resolution by using existed super-resolution algorithm. In order to realize the blind recovery of wideband electromagnetic images, a method based on convolutional neural network is proposed. Network training is the process which directly inputs a blurred image and reconstructs a high quality image without assuming any particular blur and noise model. Both experiment and simulation results demonstrate that the convolutional neural network blind recovery method outperforms other blind recovery calculations in different imaging regions of wide frequency band.
- convolutional neural network /
- electromagnetic imaging /
- blind recovery /
- electromagnetic interference source

HTML全文

图 1 算法网络结构示意图

Figure 1. Schematic diagram of algorithm network structure

下载: 全尺寸图片幻灯片

图 2 仿真图像三种算法结果对比

Figure 2. Comparison of three algorithms for simulation images

下载: 全尺寸图片幻灯片

图 3 不同噪声下三种算法结果图

Figure 3. Results of three algorithms under different noises

下载: 全尺寸图片幻灯片

图 4 2 GHz两干扰源图像恢复效果图

Figure 4. Diagram of 2 GHz two-interference-source image restoration effect

下载: 全尺寸图片幻灯片

图 5 4 GHz两干扰源图像恢复效果图

Figure 5. Diagram of 4 GHz two-interference-source image restoration effect

下载: 全尺寸图片幻灯片

图 6 6 GHz两干扰源图像恢复效果图

Figure 6. Diagram of 6 GHz two-interference-source image restoration effect

下载: 全尺寸图片幻灯片

参考文献(11)

[1]	李良超, 杨建宇, 郑鑫, 等. 无源毫米波超分辨算法及实时性研究[J]. 电子科技大学学报, 2009, 38(6): 952-956. https://www.cnki.com.cn/Article/CJFDTOTAL-DKDX200906012.htm Li Liangchao, Yang Jianyu, Zheng Xin, et al. Research on passive millimeter wave image super-resolution algorithm and real-time implementation. Journal of University of Electronic Science and Technology of China, 2009, 38(6): 952-956 https://www.cnki.com.cn/Article/CJFDTOTAL-DKDX200906012.htm
[2]	杜鑫, 谢树果, 郝旭春, 等. 一种电磁干扰源成像多分辨率分区算法[J]. 强激光与粒子束, 2015, 27: 103223. doi: 10.11884/HPLPB201527.103223 Du Xin, Xie Shuguo, Hao Xuchun, et al. An electromagnetic interference source imaging algorithm of multi-resolution partitions. High Power Laser and Particle Beams, 2015, 27: 103223 doi: 10.11884/HPLPB201527.103223
[3]	李垣江, 李跃华, 张光锋. 一种改进的毫米波图像超分辨复原方法[J]. 现代雷达, 2011, 33(8): 43-46. https://www.cnki.com.cn/Article/CJFDTOTAL-XDLD201108013.htm Li Yuanjiang, Li Yuehua, Zhang Guangfeng. A modified method of super-resolution restoration for passive millimeter wave images. Modern Radar, 2011, 33(8): 43-46 https://www.cnki.com.cn/Article/CJFDTOTAL-XDLD201108013.htm
[4]	Chan T F, Wong C. Total variation blind deconvolution diffraction[J]. IEEE Trans Image Processing, 1998, 7(3): 370-375. doi: 10.1109/83.661187
[5]	Krishnan D, Tay T, Fergus R. Blind deconvolution using a normalized sparsity measure[C]//IEEE Conference on Computer Vision and Pattern Recognition. 2011: 233-240.
[6]	Levin A, Weiss Y, Durand F, et al. Efficient marginal likelihood optimization in blind deconvolution[C]//IEEE Conference on Computer Vision and Pattern Recognition. 2011: 2657-2664.
[7]	Xu L, Zheng S, Jia J. Unnatural L₀ sparse representation for natural image deblurring[C]//IEEE Conference on Computer Vision and Pattern Recognition. 2013: 1107-1114.
[8]	Comaniciu D, Meer P. Mean shift analysis and applications[C]//Proceedings of IEEE 7^th International Conference on Computer Vision. 1999, 2: 1197-1203.
[9]	Sun L, Cho S, Wang J, et al. Edge-based blur kernel estimation using patch priors[C]//IEEE Conference on Computational Photography. 2013: 1-8.
[10]	Michal H, Jan K, Pavel Z, et al. Convolutional neural networks for direct text deblurring[C]//British Machine Vision Conference. 2015: 1-12.
[11]	Oliver W, Josef S, Andrew Z, et al. Non-uniform deblurring for shaken images[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2010.