一种改进的SRGAN红外图像超分辨率重建算法

doi:10.16182/j.issn1004731x.joss.20-0450

系统仿真学报 ›› 2021, Vol. 33 ›› Issue (9): 2109-2118.doi: 10.16182/j.issn1004731x.joss.20-0450

一种改进的SRGAN红外图像超分辨率重建算法

胡蕾¹, 王足根¹, 陈田², 张永梅³

1.江西师范大学计算机信息工程学院,江西南昌 330022;
2.国网江西省电力有限公司电力科学研究院,江西南昌 330096;
3.北方工业大学信息学院,北京 100144

收稿日期:2020-07-07 修回日期:2020-09-23 出版日期:2021-09-18 发布日期:2021-09-17
作者简介:胡蕾(1980-)，女，博士，副教授，研究方向为图像处理与分析、数据智能分析等。E-mail：hulei@jxnu.edu.cn
基金资助:
国家自然科学基金(61662033,61262036)

An Improved SRGAN Infrared Image Super-Resolution Reconstruction Algorithm

Hu Lei¹, Wang Zugen¹, Chen Tian², Zhang Yongmei³

1. School of Computer Information Engineering, Jiangxi Normal University, Nanchang 330022, China;
2. Electric Power Research Institute, State Grid Jiangxi Electric Power Co., Ltd, Nanchang 330096, China;
3. School of Information, North China University of Technology, Beijing 100144, China

Received:2020-07-07 Revised:2020-09-23 Online:2021-09-18 Published:2021-09-17

摘要/Abstract

摘要： 针对红外图像分辨率偏低的问题,设计了一种改进的超分辨率生成对抗网络(Super-Resolution Using a Generative Adversarial Network,SRGAN)算法。在生成网络中,提出应用残差密集网络获取各网络层提取的图像特征以保留图像更多的高频信息,并采用渐进式上采样方式以提升大缩放因子下超分辨率重建效果。在损失函数方面采用更符合人类感官的感知损失,使生成图像在感官和内容上与真实高分辨率图像更加接近。实验结果表明：所提方法重建的超分辨率红外图像质量在主观及客观评价中均要优于当前具有代表性的方法。

关键词: 红外图像, 超分辨率重建, 生成式对抗网络, 残差密集网络

Abstract: Aiming at the low resolution of infrared images, an improved SRGAN super-resolution reconstruction algorithm is designed. In the generative network, the method of applying the residual dense network to obtain the image features extracted from each network layer so as to retain more high-frequency information of the image, and adopting a progressive upsampling method to improve the super-resolution reconstruction effect under a large scaling factor. In terms of the loss function, the perceptual loss that is more in line with human senses is adopted to make the generated image being closer to the real high-resolution image of senses and content. Experimental results show that the quality of reconstructed infrared image is better than that of the current representative methods in the subjective and objective evaluation.

Key words: infrared image, super-resolution reconstruction, generative adversarial network, residual dense network

中图分类号:

TP391.4

胡蕾, 王足根, 陈田, 张永梅. 一种改进的SRGAN红外图像超分辨率重建算法[J]. 系统仿真学报, 2021, 33(9): 2109-2118.

Hu Lei, Wang Zugen, Chen Tian, Zhang Yongmei. An Improved SRGAN Infrared Image Super-Resolution Reconstruction Algorithm[J]. Journal of System Simulation, 2021, 33(9): 2109-2118.

参考文献

[1] 王杰, 李洪兴, 王加银, 等. 一种图像快速线性插值的实现方案与分析[J]. 电子学报, 2009, 37(7): 1481-1486.
Wang Jie, Li Hongxing, Wang Jiayin, et al.A Scheme and Its Analysis for Fast Line-ar Image Interpolation[J]. Acta Electronica Sinica, 2009, 37(7): 1481-1486.
[2] Zhao Y, Chen Q, Sui X, et al.A Novel Infrared Image Super-Resolution Method Based on Sparse Representation[J]. Infrared Physics & Technology (S1350-4495), 2015, 71: 506-513.
[3] Dong C, Loy C C, He K, et al.Image Super- Resolution Using Deep Convolutional Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence(S0162-8828), 2015, 38(2): 295-307.
[4] Keys R.Cubic Convolution Interpolation for Digital Image Processing[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing (S0096-3518), 1981, 29(6): 1153-1160.
[5] Shi W, Caballero J, Huszár F, et al.Real-time Single Image and Video Super-resolution Using an Efficient Sub-Pixel Convolutional Neural Network[C]//IEEE Conference on Computer Vision And Pattern Recognition. Piscataway, NJ, USA: IEEE, 2016: 1874-1883.
[6] Lim B, Son S, Kim H, et al.Enhanced Deep Residual Networks for Single Image Super-resolution[C]//IEEE Conference on Computer Vision And Pattern Recognition Workshops. Piscataway, NJ, USA: IEEE, 2017: 136-144.
[7] Zhang Y, Tian Y, Kong Y, et al.Residual Dense Network for Image Super-resolution[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2018: 2472-2481.
[8] Ledig C, Theis L, Huszár F, et al.Photo-realistic Single Image Super-resolution Using a Generative Adversarial Network[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2017: 4681-4690.
[9] Zhang Y, Li K, Li K, et al.Image Super-resolution Using Very Deep Residual Channel Attention Networks[C]// European Conference on Computer Vision (ECCV). Berlin, Germany: Springer, 2018: 286-301.
[10] 李方彪, 何昕, 魏仲慧, 等. 生成式对抗神经网络的多帧红外图像超分辨率重建[J]. 红外与激光工程, 2018, 47(2): 17-24.
Li Fangbiao, He Xin, Wei Zhonghui, et al.Multiframe Infrared Image Super-resolution Reconstruction Using Generative Adversarial Networks[J]. Infrared and Laser Engineering, 2018, 47(2): 17-24.
[11] Wang Y, Perazzi F, McWilliams B, et al. A Fully Progressive Approach to Single-image Super- resolution[C]//IEEE Conference on Computer Vision and Pattern Recognition Workshops. Piscataway, NJ, USA: IEEE, 2018: 864-873.
[12] 段友祥, 张含笑, 孙歧峰, 等. 基于拉普拉斯金字塔生成对抗网络的图像超分辨率重建算法[J].计算机应用, 2021, 41(4): 1020-1026.
Duan Youxiang, Zhang Hanxiao, Sun Qifeng, et al.Image Super-resolution Reconstruction Algorithm Based on Laplacian Pyramid Generative Adversarial Network[J]. Journal of Computer Applications, 2021, 41(4): 1020-1026.

一种改进的SRGAN红外图像超分辨率重建算法

An Improved SRGAN Infrared Image Super-Resolution Reconstruction Algorithm

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	曹建芳, 贾一鸣, 闫敏敏, 田晓东. 稳定增强生成对抗网络在壁画的超分辨率重建[J]. 系统仿真学报, 2022, 34(5): 1076-1089.
[2]	李新利, 邹昌铭, 杨国田, 刘禾. 基于生成式对抗网络的发票图像超分辨率研究[J]. 系统仿真学报, 2021, 33(6): 1307-1314.
[3]	王坤, 吉尧, 刘沛伦, 王力. 基于Otsu和改进易经占卜进化算法的红外图像分割[J]. 系统仿真学报, 2021, 33(2): 421-433.
[4]	杜金莲, 李淑飞, 金雪云. 三维烟雾流场超分辨率数据生成网络模型的研究[J]. 系统仿真学报, 2021, 33(10): 2381-2389.
[5]	王坤, 张杨, 宋胜博, 诸葛晶昌. 改进二维OTSU和自适应遗传算法的红外图像分割[J]. 系统仿真学报, 2017, 29(6): 1229-1236.