[1]毕晓君,潘梦迪.基于生成对抗网络的机载遥感图像超分辨率重建[J].智能系统学报,2020,15(1):74-83.[doi:10.11992/tis.202002002]
 BI Xiaojun,PAN Mengdi.Super-resolution reconstruction of airborne remote sensing images based on the generative adversarial networks[J].CAAI Transactions on Intelligent Systems,2020,15(1):74-83.[doi:10.11992/tis.202002002]
点击复制

基于生成对抗网络的机载遥感图像超分辨率重建(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第15卷
期数:
2020年1期
页码:
74-83
栏目:
学术论文—机器感知与模式识别
出版日期:
2020-01-01

文章信息/Info

Title:
Super-resolution reconstruction of airborne remote sensing images based on the generative adversarial networks
作者:
毕晓君1 潘梦迪2
1. 中央民族大学 信息工程学院, 北京 100081;
2. 哈尔滨工程大学 信息与通信工程学院, 黑龙江 哈尔滨 150001
Author(s):
BI Xiaojun1 PAN Mengdi2
1. School of Information Engineering, Minzu University of China, Beijing 100081, China;
2. Department of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China
关键词:
机载遥感超分辨率重建深度学习密集剩余残差块特征提取跳跃链接沃瑟斯坦生成对抗网络
Keywords:
airborne remote sensingsuper-resolution reconstructiondeep learningresidual in residual dense blockfeature extractionjump connectionWassersteingenerative adversarial network
分类号:
TP751.1
DOI:
10.11992/tis.202002002
摘要:
为解决机载遥感图像质量易受环境影响的问题,对其进行超分辨率重建,对现有深度学习机载遥感图像超分辨率重建方法存在的特征提取能力差、重建图像边缘平滑、模型训练困难的问题进行改进,增强图像重建效果。将生成对抗网络作为模型的整体框架,使用密集剩余残差块增强模型特征提取能力,增加跳跃连接,有效提取机载遥感图像的浅层和深层特征,引入沃瑟斯坦式生成对抗网络优化模型训练。该方法能够有效对机载遥感图像进行4倍重建,在峰值信噪比评价上较对比方法约有2 dB增益,重建出的机载遥感图像在视觉上更清晰、细节更丰富、边缘更锐利。实验结果表明,该方法有效提升了模型特征提取能力,优化了训练过程,重建的机载遥感图像效果较好。
Abstract:
To solve the problem that the quality of airborne remote sensing images is susceptible to environmental impacts, super-resolution reconstruction is carried out. The existing super-resolution reconstruction methods for deep learning airborne remote sensing images has the problems of poor feature extraction capability, smooth edges of reconstructed images and difficulty in model training, the image reconstruction effect is enhanced to solve the above problems. The generative adversarial network is taken as the overall framework of the model. The dense residual block is used to enhance the feature extraction capability of the model, and jump connection is added to effectively extract the shallow and deep features of airborne remote sensing images. The Wasserstein-type generative adversarial network optimization model training is introduced. The method can effectively reconstruct airborne remote sensing images by 4 times, and has a gain of 2 dB or so in peak signal-to-noise ratio evaluation compared with other methods for comparison. The reconstructed airborne remote sensing images are clearer in vision, richer in details and sharper in edges. The experimental results show that the method effectively improves the model feature extraction ability, optimizes the training process, and the reconstructed airborne remote sensing image has better effect.

参考文献/References:

[1] 赵英时. 遥感应用分析原理与方法[M]. 北京: 科学出版社, 2013.
[2] 罗小波. 遥感图像智能分类及其应用[M]. 北京: 电子工业出版社, 2011.
[3] 石爱业, 徐枫, 徐梦溪. 图像超分辨率重建方法及应用[M]. 北京: 科学出版社, 2016.
[4] DONG Chao, LOY C C, HE Kaiming, et al. Learning a deep convolutional network for image super-resolution[M]. FLEET D, PAJDLA T, SCHIELE B, et al. Computer Vision- ECCV 2014. Cham: Springer, 2014: 184-199.
[5] DONG Chao, LOY C C, TANG Xiaoou. Accelerating the super-resolution convolutional neural network[M]. LEIBE B, MATAS J, SEBE N, et al. Computer Vision- ECCV 2016. Cham: Springer, 2016: 391-407.
[6] KIM J, LEE J K, LEE K M. Accurate image super-resolution using very deep convolutional networks[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016: 1646-1654.
[7] LEDIG C, THEIS L, HUSZáR F, et al. Photo-realistic single image super-resolution using a generative adversarial network[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA, 2017: 105-114.
[8] ARJOVSKY M, CHINTALA S, BOTTOU L. Wasserstein GAN[J/OL]. (2017-01-26). https://arxiv.org/abs/1701.07875.
[9] 石爱业, 徐枫, 徐梦溪. 图像超分辨率重建方法及应用[M]. 北京: 科学出版社, 2016.
[10] TSAI R Y, HUANG T S. Multiframe image restoration and registration. Advances in Computer Vision and Image Pro-cessing: JAI Press Inc., 1984, 317-339.
[11] 高春波. 生成对抗网络的图像超分辨率重建[D]. 杭州: 浙江理工大学, 2019.
GAO Chunbo. Image super-resolution using a generative adversarial network[D]. Hangzhou: Zhejiang Sci-Tech University, 2019.
[12] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal, Canada, 2014: 2672-2680.
[13] IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on Machine Learning. Lille, France, 2015: 448-456.
[14] MASS A L, HANNUN A Y, NG A Y. Rectifier nonlinearities improve neural network acoustic models[C]//Proceedings of the 30th International Conference on Machine Learning. Atlanta, GA, USA, 2013.
[15] LIM B, SON S, KIM H, et al. Enhanced deep residual networks for single image super-resolution[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Honolulu, HI, USA, 2017: 1132-1140.
[16] CHENG Gong, HAN Junwei, LU Xiaoqiang. Remote sensing image scene classification: benchmark and state of the art[J]. Proceedings of the IEEE, 2017, 105(10): 1865–1883.
[17] YANG Yi, NEWSAM S. Bag-of-visual-words and spatial extensions for land-use classification[C]//Proceedings of the 18th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. New York, USA, 2010: 270-279.

相似文献/References:

[1]刘 琚,乔建苹.基于学习的超分辨率重建技术[J].智能系统学报,2009,4(03):199.
 LIU Ju,QIAO Jian-ping.Learningbased superresolution reconstruction[J].CAAI Transactions on Intelligent Systems,2009,4(1):199.

备注/Memo

备注/Memo:
收稿日期:2020-02-04。
基金项目:国家自然科学基金项目(51779050)
作者简介:毕晓君,女,1964年生,教授,博士生导师,主要研究方向为智能信息处理、数字图像处理、智能优化算法及机器学习。主持国家自然科学基金面上项目2项,科技部国际合作项目面上项目1项,教育部博士点基金1项,工业与信息化部海洋工程装备科研项目子项目1项,民品横向课题1项,获国家专利8项。出版学术专著3部,发表学术论文160余篇;潘梦迪,女,1994年生,硕士研究生,主要研究方向为深度学习、图像处理
通讯作者:毕晓君.E-mail:bixiaojun@hrbeu.edu.cn
更新日期/Last Update: 1900-01-01