[1]杨学峰,赵冬娥.一种多尺度压缩感知的遥感图像超分辨重建方法[J].应用科技,2020,47(4):20-25.[doi:10.11991/yykj.201912025]
　YANG Xuefeng,ZHAO Donge.A multi-scale copressive sensing based super-resolution reconstruction method for remote sensing images[J].Applied science and technology,2020,47(4):20-25.[doi:10.11991/yykj.201912025]
点击复制

一种多尺度压缩感知的遥感图像超分辨重建方法(/HTML)
分享到：

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
第47卷
期数:
2020年4期
页码:
20-25
栏目:
智能科学与技术
出版日期:
2020-07-05

文章信息/Info

Title:
A multi-scale copressive sensing based super-resolution reconstruction method for remote sensing images
作者:
杨学峰;  赵冬娥
中北大学 信息与通信工程学院，山西 太原 030051
Author(s):
YANG Xuefeng;  ZHAO Dong’e
School of Information and Communication Engineering, North University of China, Taiyuan 030051, China
关键词:
遥感图像; 超分辨; 压缩感知; 多尺度变换; 残余字典; Contourlet变换; 稀疏编码; 字典学习
Keywords:
remote sensing image; super-resolution; compressive sensing; multi-scale transform; residual dictionary; Contourlet transform; sparse coding; dictionary learning
分类号:
TP751
DOI:
10.11991/yykj.201912025
文献标志码:
A
摘要:
针对传统基于压缩感知的单字典超分辨方法难以充分描述复杂的遥感图像纹理的问题，提出了一种多尺度残余字典超分辨重建方法。首先对插值图像的高频子带执行Contourlet变换获得多个子频带；然后在各子频带上建立对应子残余字典，并进行字典学习和超分辨重建；最后对高频和低频部分进行融合得到完整的超分辨图像。实验结果表明：与其他相关方法相比，本文方法的超分辨效果无论主观视觉还是客观评价指标都有很大提高。其中客观评价指标，本文方法的峰值信噪比(peak signal-to-noise ratio, PSNR)和结构相似度(structural similarity, SSIM)平均值分别提高6 dB和0.05。对于纹理复杂的遥感图像的超分辨重建场合，更好地满足重建效果和时效的要求，具有重要的理论和应用意义。
Abstract:
The traditional compressive sensing based single dictionary super-resolution method can not fully describe the complex remote sensing image texture. To resolve this problem, this paper proposes a multiple residual dictionary method. Firstly, the method extracts the high-frequency part from interpolated image to perform Contourlet transform to obtain multiple directional sub-bands; then establishes corresponding residual sub-dictionary in each sub-band, and perform dictionary learning and super-resolution reconstruction; finally, combines the high-frequency part and low-frequency part to obtain the whole super-resolution image. The experimental result shows that comparing with other state-of-art methods, the super resolution effect of the proposed method is improved greatly both in subjective evaluation and objective evaluation indexes. For the objective evaluation indexes, the average values of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) of the proposed method have improved 6 dB and 0.05 respectively. For the super-resolution reconstruction of a remote sensing image with complex texture, it better meets the requirements of good reconstruction effect and fast speed and has important theoretical and practical significance.

参考文献/References:

[1] SHEN Huanfeng, LI Peng, YUE Linwei, et al. Adaptive norm selection for regularized image restoration and super-resolution[J]. IEEE transactions on cybernetics, 2016, 46(6): 1388–1399.
[2] ZHANG Tinghua, GAO Kun, NI Guoqiang, et al. Spatio-temporal super-resolution for multi-videos based on belief propagation[J]. Signal processing: image communication, 2018, 68: 1–12.
[3] AMIRI M, AHMADYFARD A, ABOLGHASEMI V. A fast video super resolution for facial image[J]. Signal processing: image communication, 2019, 70: 259–270.
[4] ZHOU Fei, YANG Wenming, LIAO Qingmin. Interpolation-based image super-resolution using multi-surface fitting[J]. IEEE transactions on image processing, 2012, 21(7): 3312–3318.
[5] RASTI P, ORLOVA O, TAMBERG G, et al. Improved interpolation kernels for super resolution algorithms[C]//International Conference on Image Processing Theory Tools and Applications (IPTA), Montreal, Canada, 2017: 1–6.
[6] WEI Deyun. Image super-resolution reconstruction using the high-order derivative interpolation associated with fractional filter functions[J]. IET signal processing, 2016, 10(9): 1052–1061.
[7] ZHANG Zhendong, WANG Xinran, JUNG C. DCSR: dilated convolutions for single image super-resolution[J]. IEEE transactions on image processing, 2019, 28(4): 1625–1635.
[8] DONG Chao, CHEN C L, HE Kaiming, et al. Image uper-resolution using deep convolutional networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2016, 38(2): 295–307.
[9] LI Yue, LIU Dong, LI Houqiang, et al. Learning a convolutional neural network for image compact-resolution[J]. IEEE transactions on image processing, 2019, 28(3): 1092–1107.
[10] SUN Yicheng, GU Guohua, SUI Xiubao. Single image super-resolution using compressive sensing with a redundant dictionary[J]. IEEE photonics journal, 2015, 7(2): 1–11.
[11] YANG Shuyuan, SUN Fenghua, WANG Min, et al. Novel super resolution restoration of remote sensing images based on compressive sensing and example patches-aided dictionary learning[C]//2011 International Workshop on Multi-Platform/Multi-Sensor Remote Sensing and Mapping (M2RSM). Xiamen, China, 2011: 1–6.
[12] 魏士俨, 顾征, 马友青, 等. 基于压缩感知的月球探测器着陆图像超分辨重建[J]. 红外与毫米波学报, 2013, 32(6): 555–558
[13] 潘宗序, 禹晶, 肖创柏, 等. 基于字典学习与结构自相似性的码本映射超分辨率算法[J]. 计算机辅助设计与图形学学报, 2015, 27(6): 1032–1038
[14] CHEN Honggang, HE Xiaohai, QING Linbo, et al. Single image super-resolution via adaptive transform-based nonlocal self-similarity modeling and learning-based gradient regularization[J]. IEEE transactions on multimedia, 2017, 19(8): 1702–1717.
[15] ZHANG Kaibing, TAO Dacheng, GAO Xinbo, et al. Learning multiple linear mappings for efficient single image super-resolution[J]. IEEE transactions on image processing, 2015, 24(3): 846–861.
[16] LU Xuan, WANG Dingwen, SHI Wenxuan, et al. Group-based single image super-resolution with online dictionary learning[J]. EURASIP journal on advances in signal processing, 2016(1): 84.
[17] YEGANLI F, NAZZAL M, OZKARAMANLI H, et al. Image super-resolution via sparse representation over multiple learned dictionaries based on edge sharpness and gradient phase angle[J]. Signal, image and video processing, 2015, 10(3): 535–542.
[18] WU Wei, YANG Xiaomin, LIU Kai, et al. A new framework for remote sensing image super-resolution: sparse representation-based method by processing dictionaries with multi-type features[J]. Journal of systems architecture, 2016, 64: 63.
[19] SURYANARAYANA G, DHULI R. Image resolution enhancement using wavelet domain transformation and sparse signal representation[C]//The 2nd International Conference on Intelligent Computing, Communication and Convergence. Cairo, Egypt, 2016: 311–316.
[20] MINH N D, MARTIN V. The contourlet transform: an efficient directional multiresolution image representation[J]. IEEE transactions on image processing, 2005, 14(12): 2091–2106.
[21] AHARON M, ELAD M, BRUCKTEIN A. K-SVD: An algorithm for designing of overcomplete dictionaries for sparse representation[J]. IEEE transactions on signal process, 2006, 54(11): 4311–4322.
[22] 郭凌飞; 张林波. 通过CWLS-DL优化St-OMP算法的盲信号重构[J]. 应用科技, 2019, 46(3): 40–45,50
[23] ZHANG Saiwen, WU Jingjing, CHEN Danni, et al. Fast frequency-domain compressed sensing analysis for high-density super-resolution imaging using orthogonal matching pursuit[J]. IEEE photonics journal, 2019, 11(1): 1–8.

相似文献/References:

[1]白鹤,郑丽颖.基于SIFT和三角网格的VHR建筑物检测技术[J].应用科技,2017,44(06):48.[doi:10.11991/yykj.201610001]
　BAI He,ZHENG Liying.Building detection from VHR based on SIFT and Delaunay triangulation[J].Applied science and technology,2017,44(4):48.[doi:10.11991/yykj.201610001]

备注/Memo

备注/Memo:
收稿日期:2019-12-25。
基金项目:十三五装备预研基金项目(61404150304)
作者简介:杨学峰，男，讲师，博士;赵冬娥，女，教授，博士
通讯作者:杨学峰，E-mail：yxf768@163.com
更新日期/Last Update: 2020-11-27