Superpixel and subspace projection-based support vector machines for hyperspectral image classification

Qiong Ran; Haoyang Yu; Lianru Gao; Wei Li; Bing Zhang

doi:10.11834/jig.170201

Remote Sensing Image Processing | Views : 0 下载量: 348 CSCD: 0

PDF
Export
Share
Collection
Album

Superpixel and subspace projection-based support vector machines for hyperspectral image classification
Vol. 23, Issue 1, Pages: 95-105(2018)
Received：05 July 2017，

Revised：2017-9-19，

Published：16 January 2018
DOI： 10.11834/jig.170201
稿件说明：

移动端阅览

DOI：

Qiong Ran, Haoyang Yu, Lianru Gao, Wei Li, Bing Zhang. Superpixel and subspace projection-based support vector machines for hyperspectral image classification[J]. Journal of Image and Graphics, 2018, 23(1): 95-105. DOI： 10.11834/jig.170201.

摘要

目的

高光谱图像包含了丰富的空间、光谱和辐射信息，能够用于精细的地物分类，但是要达到较高的分类精度，需要解决高维数据与有限样本之间存在矛盾的问题，并且降低因噪声和混合像元引起的同物异谱的影响。为有效解决上述问题，提出结合超像元和子空间投影支持向量机的高光谱图像分类方法。

方法

首先采用简单线性迭代聚类算法将高光谱图像分割成许多无重叠的同质性区域，将每一个区域作为一个超像元，以超像元作为图像分类的最小单元，利用子空间投影算法对超像元构成的图像进行降维处理，在低维特征空间中执行支持向量机分类。本文高光谱图像空谱综合分类模型，对几何特征空间下的超像元分割与光谱特征空间下的子空间投影支持向量机（SVMsub），采用分割后进行特征融合的处理方式，将像元级别转换为面向对象的超像元级别，实现高光谱图像空谱综合分类。

结果

在AVIRIS（airbone visible/infrared imaging spectrometer）获取的Indian Pines数据和Reflective ROSIS（optics system spectrographic imaging system）传感器获取的University of Pavia数据实验中，子空间投影算法比对应的非子空间投影算法的分类精度高，特别是在样本数较少的情况下，分类效果提升明显；利用马尔可夫随机场或超像元融合空间信息的算法比对应的没有融合空间信息的算法的分类精度高；在两组数据均使用少于1%的训练样本情况下，同时融合了超像元和子空间投影的支持向量机算法在两组实验中分类精度均为最高，整体分类精度高出其他相关算法4%左右。

结论

利用超像元处理可以有效融合空间信息，降低同物异谱对分类结果的不利影响；采用子空间投影能够将高光谱数据变换到低维空间中，实现有限训练样本条件下的高精度分类；结合超像元和子空间投影支持向量机的算法能够得到较高的高光谱图像分类精度。

Abstract

Objective

Hyperspectral image contains abundant spatial

spectral

and radiant information and can be used for precise earth object classification. The imbalance between high-dimensional data and limited samples should be solved to obtain accurate classification results of ground objects. The influence of "same object with different spectra" caused by noise and mixing pixels should also be reduced. To solve the aforementioned problems effectively

this study proposes a superpixel and subspace projection-based support vector machine (SVM) method (SP-SVMsub) for hyperspectral image classification.

Method

The framework foundation is the object-based image classification (OBIC)

which is a widely used classification method that includes spatial information. OBIC performs classification after segmentation

and each segment can be regarded as the smallest element in the classification process. The result of over-segmentation can be referred to as a superpixel

which represents the local neighborhood information in an adaptive domain. This study proposes to integrate superpixel segmentation with subspace-based SVM (SVMsub) for hyperspectral image classification. The proposed method can be implemented in three steps. First

simple linear iterative clustering is used to segment a hyperspectral image into several nonoverlapping homogeneous regions

and each region can be considered a superpixel. Second

subspace projection is adopted as a dimensionality reduction method for the image composed of superpixels and the original image. Third

SVM is implemented for classification with the obtained low-dimensional feature space. Innovation:A new spectral-spatial hyperspectral image classification approach is presented in this study. In spatial domain

the original hyperspectral image can be integrated with a segmentation map by applying a feature fusion process such that a pixel-level image is represented by superpixel-level data sets. In spectral domain

SVMsub is adopted to obtain final classification maps. v

Result

In the experiments with data sets collected by using an Airborne Visible/Infrared Imaging Spectrometer over the Indian Pines region in America and a Reflective Optics Spectrographic Imaging System over the University of Pavia in Italy

the accuracies of algorithms with subspace projection are higher than those without subjection projection

and remarkable improvements are shown in cases with few samples. Algorithms that integrate spatial information

either by using Markov random field or superpixel

can acquire higher classification accuracy than those without spatial information. In the case in which less than 1% training samples of two data sets are used

SP-SVMsub obtains the highest classification accuracy. The overall accuracy of SP-SVMsub is approximately 4% higher than that of other related methods.

Conclusion

Superpixel can be used to integrate spatial information and effectively reduce the influence of "same object with different spectra" on classification results. Subspace projection can transform hyperspectral data to a low-dimensional space and can achieve high classification accuracy with limited samples. SP-SVMsub can achieve high classification accuracy for hyperspectral images.

关键词

Keywords

references

Tong Q X, Zhang B, Zheng L F. Hyperspectral Remote Sensing——Principle, Technology and Application[M]. Beijing:Higher Education Press, 2006:1-3.

童庆禧, 张兵, 郑兰芬.高光谱遥感——原理、技术与应用[M].北京:高等教育出版社, 2006:1-3.

Zhang B, Gao L R. Hyperspectral Image Classification and Target Detection[M]. Beijing:Science Press, 2011:1-177.

张兵, 高连如.高光谱图像分类与目标探测[M].北京:科学出版社, 2011:1-177.

Kruse F A, Kierein-Young K S, Boardman J W. Mineral mapping at Cuprite, Nevada with a 63-channel imaging spectrometer[J]. Photogrammetric Engineering and Remote Sensing, 1990, 56(1):83-92.

McIver D K, Friedl M A. Using prior probabilities in decision-tree classification of remotely sensed data[J]. Remote Sensing of Environment, 2002, 81(2-3):253-261.[DOI:10.1016/S0034-4257(02)00003-2]

Melgani F, Bruzzone L. Classification of hyperspectral remote sensing images with support vector machines[J]. IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(8):1778-1790.[DOI:10.1109/TGRS.2004.831865]

Tarabalka Y, Fauvel M, Chanussot J, et al. SVM-and MRF-based method for accurate classification of hyperspectral images[J]. IEEE Geoscience and Remote Sensing Letters, 2010, 7(4):736-740.[DOI:10.1109/LGRS.2010.2047711]

Li J, Bioucas-Dias J M, Plaza A. Spectral-spatial hyperspectral image segmentation using subspace multinomial logistic regression and Markov random fields[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(3):809-823.[DOI:10.1109/TGRS.2011.2162649]

Gao L R, Li J, Khodadadzadeh M, et al. Subspace-based support vector machines for hyperspectral image classification[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(2):349-353.[DOI:10.1109/LGRS.2014.2341044]

Fauvel M, Tarabalka Y, Benediktsson J A, et al. Advances in spectral-spatial classification of hyperspectral images[J]. Proceedings of the IEEE, 2013, 101(3):652-675.[DOI:10.1109/JPROC.2012.2197589]

Zhang B, Li S S, Jia X P, et al. Adaptive Markov random field approach for classification of hyperspectral imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2011, 8(5):973-977.[DOI:10.1109/LGRS.2011.2145353]

Li S S, Zhang B, Chen D M, et al. Adaptive support vector machine and Markov random field model for classifying hyperspectral imagery[J]. Journal of Applied Remote Sensing, 2011, 5(1):#053538.[DOI:10.1117/1.3609847]

Li S S. Integrate spatial context into accurate classification of hyperspectral imagery[D]. Beijing:Graduate School of Chinese Academy of Sciences, 2011. http://d.wanfangdata.com.cn/Thesis/Y2036576 .

李山山. 整合空间上下文特征的高光谱图像精细分类[D]. 北京: 中国科学院研究生院, 2011.

Yu H Y, Gao L R, Li J, et al. Spectral-spatial hyperspectral image classification using subspace-based support vector machines and adaptive Markov random fields[J]. Remote Sensing, 2016, 8(4):#355.[DOI:10.3390/rs8040355]

Jia S, Deng B, Jia X P. Superpixel-level sparse representation-based classification for hyperspectral imagery[C]//2016 IEEE International Geoscience and Remote Sensing Symposium. Beijing, China:IEEE, 2016:3302-3305.[ DOI:10.1109/IGARSS.2016.7729854 http://dx.doi.org/10.1109/IGARSS.2016.7729854 ]

Liu B, Hu H, Wang H Y, et al. Superpixel-based classification with an adaptive number of classes for polarimetric SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(2):907-924.[DOI:10.1109/TGRS.2012.2203358]

Wang C Y, Chen J Z, Li W. Review on superpixel segmentation algorithms[J]. Application Research of Computers, 2014, 31(1):6-12.

王春瑶, 陈俊周, 李炜.超像素分割算法研究综述[J].计算机应用研究, 2014, 31(1):6-12. [DOI:10.3969/j.issn.1001-3695.2014.01.002]

Camps-Valls G, Bruzzone L. Kernel-based methods for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(6):1351-1362.[DOI:10.1109/TGRS.2005.846154]

Harsanyi J C, Chang C I. Hyperspectral image classification and dimensionality reduction:an orthogonal subspace projection approach[J]. IEEE Transactions on Geoscience and Remote Sensing, 1994, 32(4):779-785.[DOI:10.1109/36.298007]

Achanta R, Shaji A, Smith K, et al. SLIC superpixels compared to state-of-the-art superpixel methods[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11):2274-2282.[DOI:10.1109/TPAMI.2012.120]

Li S S, Ni L, Jia X P, et al. Multi-scale superpixel spectral-spatial classification of hyperspectral images[J]. International Journal of Remote Sensing, 2016, 37(20):4905-4922.[DOI:10.1080/01431161.2016.1225175]

Alert me when the article has been cited

提交

Hyperspectral image clustering based on density peaks and superpixel segmentation

Classification of hyperspectral image based on double L2 sparse coding

FixMatch++： a method for expanding limited image label data on the basis of semi-supervised learning

Backdoor defense mechanism for computer vision models based on feature blocking

Image classification network with random dilated convolution