Multi-scale feature extraction of hyperspectral image with guided filtering

Leiguang WANG; Xiaowang CAO; Yalan ZHENG; Qinling DAI

doi:10.11834/jrs.20186439

Technology and Methodology | Views : 0 下载量: 630 CSCD: 5

PDF
Export
Share
Collection
Album

Multi-scale feature extraction of hyperspectral image with guided filtering
Vol. 22, Issue 2, Pages: 293-303(2018)
Received：19 December 2016，

Accepted：20 September 2017，

Published：2018-03
DOI： 10.11834/jrs.20186439
稿件说明：

移动端阅览

王雷光, 曹小汪, 郑雅兰, 代沁伶. 2018. 高光谱影像的引导滤波多尺度特征提取. 遥感学报, 22(2): 293–303 DOI： 10.11834/jrs.20186439.

Wang L G, Cao X W, Zheng Y L and Dai Q L. 2018. Multi-scale feature extraction of hyperspectral image with guided filtering. Journal of Remote Sensing, 22(2): 293–303 DOI： 10.11834/jrs.20186439.

摘要

为了解决高光谱遥感影像分类中单一尺度特征无法有效表达地物类间差异和区分地物边界的不足，提高影像分类精度和改善分类目视解译效果，提出了采用引导滤波提取多尺度的空间特征的方法。首先，利用主成分分析对高光谱影像进行降维，移除噪声并突出主要特征；然后，将第1主成分作为引导影像，将包含信息量最多的若干主成分分别作为输入影像，应用依次增加的滤波半径分别进行引导滤波处理提取多个尺度的特征，获得影像不同尺度的结构信息；最后，将多尺度特征输入分类器中进行影像监督分类。采用仿真数据和帕维亚大学(Pavia University)、帕维亚城区(Pavia Centre)等3幅高光谱实验数据，提取了基于引导滤波的多尺度特征、多尺度形态特征和多尺度纹理特征，输入到支持向量机、随机森林和K近邻分类器中，进行了实验。实验结果表明：采用支持向量机分类Pavia University数据，相对于采用多尺度形态特征的分类结果，引导滤波特征的总体精度提高了6.5%；Pavia Centre和Salinas两幅影像最高分类精度均由引导滤波特征实现，分别达到98.51%和98.39%。实验证实基于引导滤波提取的多尺度特征能有效地描述地物结构，进而获得更高的分类精度和改善目视解译效果。

Abstract

Features extracted from a single scale cannot effectively express differences among land objects and recognize object boundaries.Thus

hyperspectral image classification suffers from low classification accuracy and the “pepper-and-salt” phenomenon. In this context

we propose a set of multi-scale spatial features that is based on guided filtering to improve the performance of image classification in quantitative accuracy and visual interpretation. The structure-transferring property of the guided filtering is investigated to appropriately represent land objects with different sizes. The proposed feature extraction and classification algorithm consists of three steps. First

Principal Component Analysis (PCA) is used to reduce the dimensionality of hyperspectral images and remove noise. Second

the first several principal components that have the most amount of information are guided by the first principal component to obtain filtered features. Multi-scale features are extracted by guided filtering with increasing radii

which can represent structures of different land cover types. Finally

the feature set is fed into classifiers for image classification. We operated experiments on one synthetic and three hyperspectral datasets

namely

Pavia University

Pavia Center

and Salinas. Multiple multi-scale features

including multi-scale features based on guided filtering

multi-scale morphological

and multi-scale texture features

were extracted. Three advanced classifiers

namely

Support Vector Machine(SVM)

Random Forest(RF)

and K-Nearest Neighbor(KNN)

were considered for comparison. The results of the experiments conducted on the synthetic data set showed that the proposed feature extraction method could better smooth the inner pixels of land objects while preserving object boundaries compared with multi-scale morphological features. Compared with the combination of multi-scale morphological features and SVM

the combination of multi-scale guided filtering features and SVM achieved a 6.5% increment in overall accuracy on the Pavia University dataset. The highest classification accuracies for the Pavia Centre and Salinas images were 98.51% and 98.39%

respectively.These resultswere achieved by the proposed multi-scale guided filtering method. A single scale cannot effectively represent the spatial information of land objects. Thus

multi-scale features are extracted using guided filtering. These features can preserve the spatial structures transferred from the guidance image and smooth the details of the input image due to the structure-transferring property of guided filtering. Land objects with various scales can also be effectively described by these multi-scale filtering features by setting different filtering window sizes. The quantitative results and visual inspection showthat multi-scale filtering features can effectively describe the structures of land objects in comparison with morphological and texture features and thus result in high classification accuracy and better visual quality. The proposed feature is suitable for analyzing land scenes with complicated structures

such as urban areas.

关键词

Keywords

references

Altman N S. 1992. An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician, 46(3): 175–185

Baraldi A and Parmiggiani F. 1995. An investigation of the textural characteristics associated with gray level cooccurrence matrix statistical parameters. IEEE Transactions on Geoscience and Remote Sensing, 33(2): 293–304

Benediktsson J A, Palmason J A and Sveinsson J R. 2005. Classification of hyperspectral data from urban areas based on extended morphological profiles. IEEE Transactions on Geoscience and Remote Sensing, 43(3): 480–491

Benediktsson J A, Pesaresi M and Amason K. 2003. Classification and feature extraction for remote sensing images from urban areas based on morphological transformations. IEEE Transactions on Geoscience and Remote Sensing, 41(9): 1940–1949

Cao X W, Zhao W F and Wang L G. 2015. Evaluation of multiple and multiscale morphological profiles on the classification of hyperspectral image//Proceedings of the SPIE Volume 9811, MIPPR 2015: Multispectral Image Acquisition, Processing, and Analysis. Enshi, China: SPIE: 981112 [DOI: 10.1117/12.2205487]

Chang C C, Chien L J and Lee Y J. 2011. A novel framework for multi-class classification via ternary smooth support vector machine. Pattern Recognition, 44(6): 1235–1244

方匡南, 吴见彬, 朱建平, 谢邦昌. 2011. 随机森林方法研究综述. 统计与信息论坛, 26(3): 32–38

Fang K N, Wu J B, Zhu J P and Xie B C. 2011. A review of technologies on random forests. Statistics and Information Forum, 26(3): 32–38 (

Gamba P, Dell’Acqua F and Landgrebe D. 2016. Hyperspectral Remote Sensing Scenes. http://www.ehu.eus/ccwintco/index.php?title=Hyperspectral_Remote_Sensing_Scenes http://www.ehu.eus/ccwintco/index.php?title=Hyperspectral_Remote_Sensing_Scenes [2016-09-20]

Hastie T, Tibshirani R T and Friedman J. 2009. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. 2nd ed.New York: Springer-Verlag: 61–69

He K M, Sun J and Tang X O. 2013. Guided image filtering. IEEE Transactions on Pattern Analysis And Machine Intelligence, 35(6): 1397–1409

Ho T K. 1998. The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(8): 832–844

Huang X, Zhang L P and Li P X. 2007. An adaptive multiscale information fusion approach for feature extraction and classification of IKONOS multispectral imagery over urban areas. IEEE Geoscience and Remote Sensing Letters, 4(4): 654–658

黄昕, 张良培, 李平湘. 2007. 融合形状和光谱的高空间分辨率遥感影像分类. 遥感学报, 11(2): 193–200

Huang X, Zhang L P and Li P X. 2007. Classification of high spatial resolution remotely sensed imagery based on the fusion of spectral and shape features. Journal of Remote Sensing, 11(2): 193–200 (

季江, 高鹏飞, 贾南南, 杨蕊, 郭汉明, 瑚琦, 庄松林. 2015. 自适应多尺度窗口平均光谱平滑. 光谱学与光谱分析, 35(5): 1445–1449

Ji J, Gao P F, Jia N N, Yang R, Guo H M, Hu Q and Zhuang S L. 2015. Spectral smoothing with adaptive multiscale window average. Spectroscopy and Spectral Analysis, 35(5): 1445–1449 (

Ji R R, Gao Y, Hong R C, Liu Q, Tao D C and Li X L. 2014. Spectral-spatial constraint hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 52(3): 1811–1824

Li S T, Kang XD and Hu J W. 2013. Image fusion with guided filtering. IEEE Transactions on Image Processing, 22(7): 2864–2875

Licciardi G, Marpu P R, Chanussot J and Benediktsson J A. 2012. Linear versus nonlinear PCA for the classification of hyperspectral data based on the extended morphological profiles. IEEE Geoscience and Remote Sensing Letters, 9(3): 447–451

刘纯, 洪亮, 陈杰, 楚森森, 邓敏. 2015. 融合像素—多尺度区域特征的高分辨率遥感影像分类算法. 遥感学报, 19(2): 228–239

Liu C, Hong L, Chen J, Chu S S and Deng M. 2015. Fusion of pixel-based and multi-scale region-based features for the classification of high-resolution remote sensing image. Journal of Remote Sensing, 19(2): 228–239 (

刘萌萌, 刘亚岚, 孙国庆, 彭立. 2014. 结合纹理特征的SVM样本分层土地覆盖分类. 遥感技术与应用, 29(2): 315–323

Liu M M, Liu Y L, Sun G Q and Peng L. 2014. SVM L and cover classification based on spectral and textural features using stratified samples. Remote Sensing Technology and Application, 29(2): 315–323 (

Mura M D, Villa A, Benediktsson J A, Chanussot J and Bruzzone L. 2011. Classification of hyperspectral images by using extended morphological attribute profiles and independent component analysis. IEEE Geoscience and Remote Sensing Letters, 8(3): 542–546

Quesada-Barriuso P, Arguello F and Heras D B. 2014. Spectral–spatial classification of hyperspectral images using wavelets and extended morphological profiles. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(4): 1177–1185

Shen L L and Jia S. 2011. Three-dimensional Gabor wavelets for pixel-based hyperspectral imagery classification. IEEE Transactions on Geoscience and Remote Sensing, 49(12): 5039–5046

Wang LG, Dai QL, Xu Q Z and Zhang Y. 2015. Constructing hierarchical segmentation tree for feature extraction and land cover classification of high resolution MS imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(5): 1946–1961

尹明, 谭熊, 张鹏强, 徐卫霄. 2015. 一种基于纹理和光谱特征的高光谱影像信息向量机分类方法. 测绘科学技术学报, 32(4): 368–372, 378

Yi M, Tan X, Zhang P Q and Xu W X. 2015. A classification method of informative vector machine for hyperspectral imagery based ontexture and spectral features. Journal of Geomatics Science and Technology, 32(4): 368–372, 378 (

余旭初, 谭熊, 付琼莹, 王蔚涛. 2014. 联合纹理和光谱特征的高光谱影像多核分类方法. 测绘通报(9): 38–42

Yu X C, Tan X, Fu Q Y and Wang W T. 2014. Combined texture-spectral feature for multiple kernel classification of hyperspectral images. Bulletin of Surveying and Mapping(9): 38–42 (

张春森, 郑艺惟, 黄小兵, 崔卫红. 2015. 高光谱影像光谱-空间多特征加权概率融合分类. 测绘学报, 44(8): 909–918

Zhang C S, Zheng Y W, Huang X B and Cui W H. 2015. Hyperspectral image classification based on the weighted probabilistic fusion of multiple spectral-spatial features. Acta Geodaetica et CartographicaSinica, 44(8): 909–918 (

张刚, 马宗民. 2010. 一种采用Gabor小波的纹理特征提取方法. 中国图象图形学报, 15(2): 247–254

Zhang G and Ma Z M. 2010. An approach of using gabor wavelets for texture feature extraction. Journal of Image and Graphics, 15(2): 247–254 (

张学工. 2010. 模式识别. 3版. 北京: 清华大学出版社

Zhang X G. 2010. Pattern Recognition.3rd ed. Beijing: Tsinghua University Press

Zhao W F, Dai QL and Wang L G. 2015. Remote sensing fusion based on guided image filtering//Proceedings of SPIE Volume 9815, MIPPR 2015: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications. Enshi, China: 98150H [DOI: 10.1117/12.2205139]

郑晨, 孙丁茜, 陈晓惠. 2013. 基于多尺度区域粒度分析的遥感图像分割. 光谱学与光谱分析, 33(7): 1912–1916

Zheng C, Sun D Q and Chen X H. 2013. Remote sensing image segmentation based on a multiresolution region granularity analysis method. Spectroscopy and Spectral Analysis, 33(7): 1912–1916 (

Alert me when the article has been cited

提交

A Classification Method Based on Spatial Information

Advances in graph neural network-based hyperspectral remote sensing image classification

Integration of a spatial-spectral structure with improved local density for hyperspectral image band selection

Change detection for high-resolution remote sensing images with multi-scale feature transformer

Information extraction and system construction of digital forest system based on multisource remote sensing data