广西师范大学学报（自然科学版） ›› 2018, Vol. 36 ›› Issue (2): 33-41.doi: 10.16088/j.issn.1001-6600.2018.02.005

• • 上一篇    下一篇

基于卷积神经网络超分辨率重建的遥感图像融合

薛洋,曾庆科,夏海英*,王文涛   

  1. 广西师范大学电子工程学院,广西桂林 541004
  • 收稿日期:2017-07-20 出版日期:2018-05-10 发布日期:2018-07-18
  • 通讯作者: 夏海英(1983—),女,山东聊城人,广西师范大学副教授,博士。E-mail:xhy22@mailbox.gxnu.edu.cn
  • 基金资助:
    国家自然科学基金(61762014),广西研究生教育创新计划项目(XYCSZ2017054)

Remote Sensing Image Fusion Based on Convolutional Neural Network Super-resolution Reconstruction

XUE Yang,ZENG Qingke,XIA Haiying*,WANG Wentao   

  1. College of Electronic Engineering, Guangxi Normal University,Guilin Guangxi 541004, China
  • Received:2017-07-20 Online:2018-05-10 Published:2018-07-18

PDF (PC)

59

摘要： 为了充分利用多光谱图像的空间信息,获得更好的融合结果,本文提出一种基于卷积神经网络(convolutional neural network,CNN)超分辨率重建的遥感图像融合方法。该方法首先对多光谱图像作IHS变换,选取亮度分量I进行基于卷积神经网络的超分辨率重建(super-resolution convolutional neural network,SRCNN),增加扩展后图像的空间细节信息;然后对重建过后的多光谱图像的亮度分量I和全色图像进行基于小波变换的融合,融合规则为绝对值最大,改变传统算法中融合图像的高频分量全部来源于全色图像的情形;最后逆IHS变换得到分辨率较高的多光谱图像。实验结果表明,该算法的融合效果优于其他对比算法,能有效地降低图像融合过程中空间信息和光谱信息的损失。

关键词: 遥感, 图像融合, 超分辨率重建, 卷积神经网络

Abstract: A remote sensing image fusion method based on super-resolution reconstruction with convolutional neural network (CNN) is proposed to make full use of spatial information of multispectral image and obtain better fusion quality. Firstly,the mulispectral image is transformed with IHS transform,the gotten I component is reconstructed by Super-Resolution Convolutional Neural Network(SRCNN), which enhances the spatial information while expanding its size. Then the panchromatic image and the reconstructed I component of mulispectral image are fused with the fusion method based on wavelet transform,the fusion rule is the absolute value and the changed high frequency components of the fusion image are all derived from the panchromatic image in the traditional algorithms. Finally, the fused multispectral image is obtained via inverse IHS transform.The experiment results show that the algorithm outperforms other algorithms, and reduces the loss of spatial information and spectral information in the process of image fusion effectively.

Key words: remote sensing, image fusion, super-resolution reconstruction, convolutional neural network

中图分类号: 

  • TP751
[1] 李红,刘芳,杨淑媛,等.基于深度支撑值学习网络的遥感图像融合[J].计算机学报,2016,39(8):1583-1596.
[2] CHAVEZ P S,SIDES S C,ANDERSON J A. Comparison of three different methods to merge multiresolution and multispectral data: Landsat TM & SPOT panchromatic[J].Photogrammetric Engineering and Remote Sensing,1991,57(3): 295-303.
[3] CARPER W J,LILLESAND T M,KIEFER R W. The use of intensity-hue-saturation transformations for merging spot panchromatic and multispectral image data[J].Photogrammetric Engineering and Remote Sensing,1990,56(4): 459-467.
[4] LABEN C A,BROWER B V.Process for enhancing the spatial resolution of multispectral imagery using pan-sharpening:US Patent 6,011,875[P].2000-01-04.
[5] OTAZU X,GONZALEZ-AUDICANA M,FORS O,et al.Introduction of sensor spectral response into image fusion methods.Application to wavelet-based methods[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(10):2376-2385.
[6] SHAH VP,YOUNAN N H,KINGR L. An efficient pan-sharpening method via a combined adaptive PCA approach and contourlets[J].IEEE Transactions on Geoscience and Remote Sensing,2008,46(5):1323-1335.
[7] ZHENG S,SHI W Z,LIU J,et al.Remote sensing image fusion using multiscale mapped LS-SVM[J].IEEE Transactions on Geoscience and Remote Sensing,2008,46(5):1313-1322.
[8] 石智,张卓,岳彦刚.一种基于区域分割的多尺度遥感图像融合算法[J].光子学报,2013,42:115-120.
[9] NUNEZ J,OTAZU X,FORS O,et al.Multiresolution-based image fusion with additive wavelet decomposition[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(3):1204-1211.
[10] LI Shutao,YANG Bin.A new pan-sharpening method using a compressed sensing technique[J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(2):738-746.
[11] ZHONG Jinying,YANG Bin,HUANG Guoyu,et al.Remote sensing imagefusion with convolutional naural network[J].Sensing and Imaging,2016,17(10):1-16.
[12] DONG Chao,LOY Chenchange,HE Kaiming,et al.Learning a deep convolutional network for image super-resolution[C]// Proceedings of the 13th European Conference on Computer Vision.Zurich:Springer-Cham,2014:184-19.
[13] 杨超,杨斌,黄国玉.基于多光谱图像超分辨率处理的遥感图像融合[J].激光与光电子学进展,2016(2):94-101.
[14] ALPARONE L,BARONTI S,GARZELLI A,et al.A global quality measurement of pan-sharpened multispectral imagery[J].IEEE Geoscience and Remote Sensing Letters,2004,1(4):313-317.
[15] Wald L,Rachin T,Mangolini M,et al.Fusion ofsatellite images of different spatial resolutions: asssessing the quality of resulting images[J].Photogrammetric Engineering and Remote Sensing,1997,63(6):691-699.
[1] 严浩, 许洪波, 沈英汉, 程学旗. 开放式中文事件检测研究[J]. 广西师范大学学报（自然科学版）, 2020, 38(2): 64-71.
[2] 范瑞,蒋品群,曾上游,夏海英,廖志贤,李鹏. 多尺度并行融合的轻量级卷积神经网络设计[J]. 广西师范大学学报（自然科学版）, 2019, 37(3): 50-59.
[3] 武文雅, 陈钰枫, 徐金安, 张玉洁. 基于高层语义注意力机制的中文实体关系抽取[J]. 广西师范大学学报（自然科学版）, 2019, 37(1): 32-41.
[4] 张茹, 张蓓, 任鸿瑞. 山西轩岗矿区耕地流失时空特征及其影响因子研究[J]. 广西师范大学学报（自然科学版）, 2018, 36(3): 121-132.
[5] 夏海英, 喻潇琪. 基于对比度金字塔图像融合的自发笑脸识别[J]. 广西师范大学学报（自然科学版）, 2017, 35(3): 45-52.
[6] 张芳. 艾比湖地区生态景观格局空间演变分析[J]. 广西师范大学学报（自然科学版）, 2016, 34(4): 156-164.
[7] 梁保平, 马艺芳, 陈桂南. 桂林市主城区建设用地扩张时空动态特征分析[J]. 广西师范大学学报（自然科学版）, 2015, 33(4): 152-159.
[8] 王小燕, 任国业, 刘卫东, 汪宏. 基于遥感和GIS的洪水灾情快速统计模拟技术[J]. 广西师范大学学报（自然科学版）, 2014, 32(4): 32-38.
[9] 韦春荣, 何楚. 基于改进型互信息的遥感图像配准方法[J]. 广西师范大学学报（自然科学版）, 2014, 32(2): 20-25.
[10] 李晖, 尹辉, 蒋忠诚, 杨奇勇, 王月. 典型岩溶区石漠化和土壤侵蚀遥感解译与关键问题[J]. 广西师范大学学报（自然科学版）, 2013, 31(2): 133-139.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 广西师范大学学报（自然科学版）编辑部
地址：广西桂林市三里店育才路15号　邮编：541004
电话：0773-5857325　E-mail: gxsdzkb@mailbox.gxnu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发