基于最小Hausdorff距离和NSST的遥感图像融合

武晓焱; 柴晶; 刘帆; 陈泽华

doi:doi:10.3788/gzxb20184702.0210002

光子学报, 2018, 47 (2): 0210002, 网络出版: 2018-01-30

基于最小Hausdorff距离和NSST的遥感图像融合

Remote Sensing Image Fusion Based on Minimum Hausdorff Distance and Nonsampled Shearlet Transform

论文大纲

武晓焱 ^1,*柴晶 ¹刘帆 ²陈泽华 ²

作者单位

¹ 太原理工大学信息工程学院, 太原 030024

² 太原理工大学大数据学院, 太原 030024

摘要

为了最大限度地保留多光谱图像的光谱特性和全色图像的空间细节, 提出基于最小Hausdorff距离和非下采样剪切波变换(NSST)的遥感图像融合方法.首先, 将原多光谱图像进行主成分分析(PCA)获得其第一主分量, 选择NSST对第一主分量和全色图像分别进行分解, 得到相应的低频子带系数和高频子带系数.其次, 对低频子带系数采用基于稀疏表示的融合策略, 稀疏系数与区域空间频率相结合, 根据区域空间频率选择权值, 对稀疏系数进行加权; 对于高频子带系数充分考虑其邻域系数相关性, 提出采用最小Hausdorff距离表征相应区域相关性, 根据相关性不同采用不同的融合策略.最后, 对融合系数进行NSST逆变换得到融合后的第一主分量, 再将新的第一主分量与其他高阶主分量进行PCA逆变换得到融合图像.选择三组QuickBird卫星图像和一组SPOT卫星图像进行测试, 与传统的融合策略算法相比, 本文方法获得的融合结果客观评价指标更优, 且主观视觉效果更好.

Abstract

In order to preserve both spectral and spatial information simultaneously in fused image, we introduce the minimum Hausdorff distance and NonSampled Shearlet Transform (NSST) to construct a new method for remote sensing image fusion. Firstly, Principal Component Analysis (PCA) transform is applied in the original multispectral image to obtain the first principal component, this component and the panchromatic image are decomposed by NSST respectively to obtain the corresponding low frequency subband coefficients and high frequency subband coefficients. Then, the low frequency subband coefficients are fused by sparse representation, the sparse coefficients of sparse representation are fused with the region space frequency; for the high frequency subband coefficients, the regional structure similarity is utilized, using the minimum Hausdorff distance to represent the correlation of regions and different fusion strategies are adopted according to the correlation. Finally, the fused coefficients are transformed by inverse NSST to obtain the new principal component, the new component and other higher order principal components are transformed by inverse PCA transform to obtain the fused image. In this paper, three QuickBird satellite images and one SPOT satellite image are selected for testing, the results show that compared with the traditional fusion strategy algorithms, the fusion results obtained by proposed method have better objective evaluation index and subjective visual effect.

参考文献

[1] DEVORE R A, JAWERTH B, LUCIERB J. Image compression through wavelet transform coding［J］. IEEE Transactions on Information Theory, 1992, 38(2): 719746.

[2] 吴一全, 沈毅, 殷骏. 基于改进梯度投影NMF和复Contourlet变换的遥感图像融合［J］. 光子学报, 2014, 43(5): 0510001.

WU Yiquan, SHEN Yi, YIN Jun. Remote sensing image fusion based on improved gradient projection NMF and complex contourlet transform［J］. Acta Photonica Sinca, 2014, 43(5): 0510001.

[3] LIU X, MEI W, DU H, et al. A novel image fusion algorithm based on nonsubsampled shearlet transform and morphological component analysis［J］. Signal Image & Video Processing, 2016, 10(5): 959966.

[4] LUO X, ZHANG Z, WU X. A novel algorithm of remote sensing image fusion based on shiftinvariant Shearlet transform and regional selection［J］. AEU International Journal of Electronics and Communications, 2016, 70(2): 186197.

[5] 陈贞, 邢笑雪. 基于非下采样剪切波变换的医学图像融合算法［J］. 沈阳工业大学学报, 2015, 37(2): 194199.

CHEN Zhen, XING Xiaoxue. Medical image fusion algorithm based on nonsampled shearlet transform［J］. Journal of Shenyang University of Technology, 2015, 37(2): 194199.

[6] EASLEY G, LABATE D, LIM W Q. Sparse directional image representations using the discrete Shearlets transform［J］. Applied & Computational Harmonic Analysis, 2008, 25(1): 2546.

[7] 刘卫, 殷明, 栾静,等. 基于平移不变剪切波变换域图像融合算法［J］. 光子学报, 2013, 42(4): 496503.

LIU Wei, YIN Ming, LUAN Jing, et al. Image fusion algorithm based on shiftinvariant shearlet transform［J］. Acta Photonica Sinca, 2013, 42(4): 496503.

[8] 陈泽华, 尚晓慧, 柴晶. 基于混合 Hausdorff距离的多示例学习近邻分类器［J］. 山东大学学报, 2016, 46(6): 1522.

CHEN Zehua, SHANG Xiaohui, CHAI Jing.Neighborhood related multipleinstance classifiers based on integrated Hausdorff distance［J］. Journal of Shandong University, 2016, 46(6): 1522.

[9] 徐旭, 张风丽, 王国军,等. 基于Hausdorff距离的城区高分辨率SAR图像配准方法研究［J］. 遥感信息, 2014, 29(3) : 7377.

XU Xu, ZHANG Fengli, WANG Guojun, et al. Registration of high resolution SAR imagery in urban areas based on Hausdorff distance［J］. Remote Sensing Information, 2014, 29 (3): 7377.

[10] 李伟峰, 周金强, 方圣辉. 基于改进Hausdorff距离的图像配准方法［J］. 国土资源遥感, 2014(2): 9398.

LI Weifeng, ZHOU Jinqiang, FANG Shenghui. Image registration method based on improved Hausdorff distance［J］. Remote Sensing for Land & Resources, 2014(2): 9398.

[11] 郭晓蓉, 柴晶. 基于混合Hausdorff距离的多示例分类问题［J］. 科学技术与工程, 2017, 17(5): 6266.

GUO Xiaorong, CHAI Jing. The problem of multipleinstance classification based on the integration Hausdorff distance［J］. Science and Engineering, 2017, 17(5): 6266.

[12] LUO X, ZHANG Z, ZHANG B, et al. Image fusion with contextual statistical similarity and nonsubsampled shearlet transform［J］. IEEE Sensors Journal, 2017, 17(6): 17601771.

[13] ZHU Z, CHAI Y, YIN H, et al. A novel dictionary learning approach for multimodality medical image fusion［J］. Neurocomputing, 2016, 214: 471–482.

[14] LIU H, LIU Y, SUN F, Robust exemplar extraction using structured sparse coding［J］. IEEE Transactions on Neural Networks & Learning Systems, 2015, 26(8): 1816–1821.

[15] LIU H, GUO D, SUN F, Object recognition using tactile measurements: Kernel sparse coding methods［J］. IEEE Transactions on Instrumentation & Measurement, 2016, 65(3): 656–665.

[16] 李英杰, 张俊举, 常本康, 等. 远距离多波段红外图像融合系统及配准方法［J］. 红外与激光工程, 2016, 45(5): 0526002.

LI Yingjie, ZHANG Junju, CHANG Benkang, et al. Remote multiband infrared image fusion system and registration method［J］. Infrared and Laser Engineering, 2016, 45(5): 0526002.

[17] FAN J, WU Y, WANG F, et al. New point matching algorithm using sparse representation of image patch feature for SAR image registration［J］. IEEE Transactions on Geoscience & Remote Sensing, 2017, 55(3): 14981510.

武晓焱, 柴晶, 刘帆, 陈泽华. 基于最小Hausdorff距离和NSST的遥感图像融合[J]. 光子学报, 2018, 47(2): 0210002. WU Xiaoyan, CHAI Jing, LIU Fan, CHEN Zehua. Remote Sensing Image Fusion Based on Minimum Hausdorff Distance and Nonsampled Shearlet Transform[J]. ACTA PHOTONICA SINICA, 2018, 47(2): 0210002.

基于最小Hausdorff距离和NSST的遥感图像融合

关于本站 Cookie 的使用提示

全站搜索

基于最小Hausdorff距离和NSST的遥感图像融合

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索