基于边缘修正的高光谱图像超像素空谱核分类方法
|
摘要
本文提出了一种边缘修正的超像素空间光谱核分类方法,该方法能够有效解决构建空谱核时超像素方法提取的空间信息完全依赖于同一个超像素特征,边缘处像素空间信息刻画不准确这一缺陷,从而有效提升分类精度.首先本文提出一种固定窗口与超像素结合的同质区域选择方法,对提取的邻域像素进行赋权,将超像素中固定窗口外的像素权值置零,得到修正的空间光谱核;其次,进一步考虑相邻超像素之间的相关性,得到相邻超像素间的空间特征光谱核,并与上一步中的空间光谱核进行凸组合得到修正的超像素空间光谱核,最后采用支持向量机进行分类.真实高光谱数据实验结果表明:本文方法能有效克服超像素空谱核的空间信息不稳定性,分类精度优于现有的最新的分类方法.
In order to alleviate the drawback that the spatial information of any pixel in a superpixel for generating the spatial-spectral kernel is totally determined by the same biased superpixel feature,especially for spatial information of the pixels located at the boundary,we propose an edge-modified superpixel based spatial-spectral kernel method for hyperspectral classification. On one hand,we combine the fixed window and superpixel to determine the homogeneous regions in a weighting strategy, in which the weights for pixels outside the fixed window are set to zero. Then we obtain the modified spectralspatial kernel based on the weighted homogeneous regions. On the other hand,by considering the correlation among adjacent superpixels,we extract the spatial features among those superpixels to generate the inter-superpixel based spectral-spatial kernel.Finally,we combine the two spatial-spectral kernels in a convex way and employ support vector machine( SVM) for classification. Experimental results on two real hyperspectral data sets indicate that the proposed method could overcome the instability caused by superpixel-based spatial information extraction technique,and lead to better classification results than other state-of-the-art classifiers.
In order to alleviate the drawback that the spatial information of any pixel in a superpixel for generating the spatial-spectral kernel is totally determined by the same biased superpixel feature,especially for spatial information of the pixels located at the boundary,we propose an edge-modified superpixel based spatial-spectral kernel method for hyperspectral classification. On one hand,we combine the fixed window and superpixel to determine the homogeneous regions in a weighting strategy, in which the weights for pixels outside the fixed window are set to zero. Then we obtain the modified spectralspatial kernel based on the weighted homogeneous regions. On the other hand,by considering the correlation among adjacent superpixels,we extract the spatial features among those superpixels to generate the inter-superpixel based spectral-spatial kernel.Finally,we combine the two spatial-spectral kernels in a convex way and employ support vector machine( SVM) for classification. Experimental results on two real hyperspectral data sets indicate that the proposed method could overcome the instability caused by superpixel-based spatial information extraction technique,and lead to better classification results than other state-of-the-art classifiers.
引文
[1]PATEL N K,PATNAIK C,DUTTA S,et al. Study of crop grow th parameters using airborne imaging spectrometer data[J]. International Journal of Remote Sensing,2001,22(12):2401-2411.
[2]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&Remote Sensing,2012,50(3):809-823.
[3]HUANG C,DAVIS L S,TOWNSHEND J R G. An assessment of support vector machines for land cover classification[J]. International Journal of Remote Sensing,2002,23(4):725-749.
[4]JIA X,Richards J. Segmented principal components transformation for efficient hyperspectral remote-sensing image display and classification[J]. IEEE Transactions on Geoscience&Remote Sensing,1999,37(1):538-542.
[5] SUMARSONO A,DU Q. Low-rank subspace representation for supervised and unsupervised classification of hyperspectral imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2016,9(9):4188-4195.
[6]CAMPS-VALLS G,BRUZZONE L. Kernel-based methods for hyperspectral image classification[J]. IEEE Transactions on Geoscience&Remote Sensing,2005,43(6):1351-1362.
[7]CHEN Y,NASRABADI N M,TRAN T D. Hyperspectral image classification via kernel sparse representation[J].IEEE Transactions on Geoscience&Remote Sensing,2013,51(1):217-231.
[8]MELGANI F,BRUZZONE L. Classification of hyperspectral remote sensing images w ith support vector machines[J]. IEEE Transactions on Geoscience&Remote Sensing,2004,42(8):1778-1790.
[9]孙乐,吴泽彬,冯灿,等.一种新的两分类器融合的空谱联合高光谱分类方法[J].电子学报,2015,43(11):2210-2217.SUN L,WU Z B,FENG C,et al. A novel tw o-classifier fusion method for spectral-spatial hyperspectral classification[J]. Acta Electronica Sinica,2015,43(11):2210-2217.(in Chinese)
[10]MOSER G,SERPICO S B. Combining support vector machines and M arkov random fields in an integrated framew ork for contextual image classification[J]. IEEE Transactions on Geoscience&Remote Sensing,2013,51(5):2734-2752.
[11] CHEN Y,NASRABADI N M,Tran T D. Hyperspectral image classification using dictionary-based sparse representation[J]. IEEE Transactions on Geoscience&Remote Sensing,2011,49(10):3973-3985.
[12]SUN L,WU Z,LIU J,XIAO L,WEI Z. Supervised spectral-spatial hyperspectral image classification w ith w eighted M arkov random fields[J]. IEEE Transactions on Geoscience&Remote Sensing,2015,53(3):1490-1503.
[13]BENEDIKTSSON J A,PALMASON J A,SVEINSSON J R. Classification of hyperspectral data from urban areas based on extended morphological profiles[J]. IEEE Transactions on Geoscience&Remote Sensing,2005,43(3):480-491.
[14]CAMPS-VALLS G,GOMEZ-CHOVA L,MUNOZ-MARI J,et al. Composite kernels for hyperspectral image classification[J]. IEEE Geoscience&Remote Sensing Letters,2006,3(1):93-97.
[15]LIU J,WU Z,WEI Z,XIAO L,SUN L. Spatial-spectral kernel sparse representation for hyperspectral image classification[J]. IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2013,6(6):2462-2471.
[16] DUAN W,LI S,FANG L. Superpixel-based composite kernel for hyperspectral image classification[A]. IEEE International Conference on Geoscience and Remote Sensing Symposium[C]. IEEE,2015. 1698-1701.
[17]SUN Z,WANG C,WANG H,et al. Learn multiple-kernel SVM s for domain adaptation in hyperspectral data[J].IEEE Geoscience&Remote Sensing Letters,2013,10(5):1224-1228.
[18] FANG L,LI S,DUAN W,et al. Classification of hyperspectral images by exploiting spectral-spatial information of superpixel via multiple kernels[J]. IEEE Transactions on Geoscience&Remote Sensing,2015,53(12):6663-6674.
[19] COVER T M. Geometrical and statistical properties of systems of linear inequalities w ith applications in pattern recognition[J]. IEEE Transactions on Electronic Computers,1965,EC-14(3):326-334.
[20] JOLLIFFE,Ian. Principal Component Analysis[M].Springer-Verlag,1986.
[21] LIU M Y,TUZEL O,RAMALINGAM S,et al. Entropy rate superpixel segmentation[A]. IEEE Computer Vision and Pattern Recognition[C]. IEEE,2011. 2097-2104.
[22] CHANG C C,LIN C J. LIBSVM:A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology,2011,2(3):1-27.
[2]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&Remote Sensing,2012,50(3):809-823.
[3]HUANG C,DAVIS L S,TOWNSHEND J R G. An assessment of support vector machines for land cover classification[J]. International Journal of Remote Sensing,2002,23(4):725-749.
[4]JIA X,Richards J. Segmented principal components transformation for efficient hyperspectral remote-sensing image display and classification[J]. IEEE Transactions on Geoscience&Remote Sensing,1999,37(1):538-542.
[5] SUMARSONO A,DU Q. Low-rank subspace representation for supervised and unsupervised classification of hyperspectral imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2016,9(9):4188-4195.
[6]CAMPS-VALLS G,BRUZZONE L. Kernel-based methods for hyperspectral image classification[J]. IEEE Transactions on Geoscience&Remote Sensing,2005,43(6):1351-1362.
[7]CHEN Y,NASRABADI N M,TRAN T D. Hyperspectral image classification via kernel sparse representation[J].IEEE Transactions on Geoscience&Remote Sensing,2013,51(1):217-231.
[8]MELGANI F,BRUZZONE L. Classification of hyperspectral remote sensing images w ith support vector machines[J]. IEEE Transactions on Geoscience&Remote Sensing,2004,42(8):1778-1790.
[9]孙乐,吴泽彬,冯灿,等.一种新的两分类器融合的空谱联合高光谱分类方法[J].电子学报,2015,43(11):2210-2217.SUN L,WU Z B,FENG C,et al. A novel tw o-classifier fusion method for spectral-spatial hyperspectral classification[J]. Acta Electronica Sinica,2015,43(11):2210-2217.(in Chinese)
[10]MOSER G,SERPICO S B. Combining support vector machines and M arkov random fields in an integrated framew ork for contextual image classification[J]. IEEE Transactions on Geoscience&Remote Sensing,2013,51(5):2734-2752.
[11] CHEN Y,NASRABADI N M,Tran T D. Hyperspectral image classification using dictionary-based sparse representation[J]. IEEE Transactions on Geoscience&Remote Sensing,2011,49(10):3973-3985.
[12]SUN L,WU Z,LIU J,XIAO L,WEI Z. Supervised spectral-spatial hyperspectral image classification w ith w eighted M arkov random fields[J]. IEEE Transactions on Geoscience&Remote Sensing,2015,53(3):1490-1503.
[13]BENEDIKTSSON J A,PALMASON J A,SVEINSSON J R. Classification of hyperspectral data from urban areas based on extended morphological profiles[J]. IEEE Transactions on Geoscience&Remote Sensing,2005,43(3):480-491.
[14]CAMPS-VALLS G,GOMEZ-CHOVA L,MUNOZ-MARI J,et al. Composite kernels for hyperspectral image classification[J]. IEEE Geoscience&Remote Sensing Letters,2006,3(1):93-97.
[15]LIU J,WU Z,WEI Z,XIAO L,SUN L. Spatial-spectral kernel sparse representation for hyperspectral image classification[J]. IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2013,6(6):2462-2471.
[16] DUAN W,LI S,FANG L. Superpixel-based composite kernel for hyperspectral image classification[A]. IEEE International Conference on Geoscience and Remote Sensing Symposium[C]. IEEE,2015. 1698-1701.
[17]SUN Z,WANG C,WANG H,et al. Learn multiple-kernel SVM s for domain adaptation in hyperspectral data[J].IEEE Geoscience&Remote Sensing Letters,2013,10(5):1224-1228.
[18] FANG L,LI S,DUAN W,et al. Classification of hyperspectral images by exploiting spectral-spatial information of superpixel via multiple kernels[J]. IEEE Transactions on Geoscience&Remote Sensing,2015,53(12):6663-6674.
[19] COVER T M. Geometrical and statistical properties of systems of linear inequalities w ith applications in pattern recognition[J]. IEEE Transactions on Electronic Computers,1965,EC-14(3):326-334.
[20] JOLLIFFE,Ian. Principal Component Analysis[M].Springer-Verlag,1986.
[21] LIU M Y,TUZEL O,RAMALINGAM S,et al. Entropy rate superpixel segmentation[A]. IEEE Computer Vision and Pattern Recognition[C]. IEEE,2011. 2097-2104.
[22] CHANG C C,LIN C J. LIBSVM:A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology,2011,2(3):1-27.