基于多种空间信息的高光谱遥感图像分类方法
|
摘要
在高光谱遥感图像分类方法中,空间特征和光谱特征的融合可以有效地改善分类效果。针对单一空间特征的信息表达不充分问题,提出了一种联合多种空间特征的高光谱图像空谱分类方法。利用超像素信息对分类结果进行后处理去掉椒盐噪声,并创造性地将超像素信息应用于分类前处理,提出了一种利用超像素信息对像素点的特征向量进行线性加权融合的方法。试验结果表明,所提方法的性能优于目前的通常方法。
In the field of hyperspectral remote sensing image classification, spatial and spectral feature fusion can improve the effect of classification. A multi-feature spectral and spatial classification method for hyperspectral images was proposed. In the post-processing procedure, the salt-and-pepper noises were removed by using superpixel information. It was also used in the pre-processing procedure, and the feature vector of pixels was weighted by superpixel information. The experiment results show that the results of proposed method are better than the present methods.
In the field of hyperspectral remote sensing image classification, spatial and spectral feature fusion can improve the effect of classification. A multi-feature spectral and spatial classification method for hyperspectral images was proposed. In the post-processing procedure, the salt-and-pepper noises were removed by using superpixel information. It was also used in the pre-processing procedure, and the feature vector of pixels was weighted by superpixel information. The experiment results show that the results of proposed method are better than the present methods.
引文
[1] XUE Z,DU P,LI J,et al.Sparse graph regularization for hyperspectral remote sensing image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2017,55(9):1-16.
[2] MA A,ZHONG Y,ZHAO B,et al.Semisupervised subspace-based DNA encoding and matching classifier for hyperspectral remote sensing imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(8):4402-4418.
[3] WANG L,ZHANG J,LIU P,et al.Spectral-spatial multi-feature-based deep learning for hyperspectral remote sensing image classification[J].Soft Computing.2017,21(1):213-221.
[4] ZHANG C,ZHENG Y,FENG C.Spectral-spatial classifi-cation of hyperspectral images using probabilistic weighted strategy for multifeature fusion[J].IEEE Geoscience and Remote Sensing Letters,2016,13(10):1562-1566.
[5] LIAO W,MURA M D,CHANUSSOT J,et al.Fusion of spectral and spatial information for classification of hyperspectral remote-sensed imagery by local graph[J].IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing,2016,9(2):583-594.
[6] FANG L,LI S,DUAN W,et al.Classification of hyper-spectral images by exploiting spectral-spatial information of superpixel via multiple kernels[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(12):6663-6674.
[7] LI W,CHEN C,SU H,et al.Local binary patterns and extreme learning machine for hyperspectral imagery classification[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(7):3681-3693.
[8] ROMERO A,GATTA C,CAMPS-VALLS G.Unsupervised deep feature extraction for remote sensing image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(3):1349-1362.
[9] GUO X,HUANG X,ZHANG L,et al.Support tensor machines for classification of hyperspectral remote sensing imagery[J].IEEE Transactions on Geoscience & Remote Sensing,2016,54(6):3248-3264.
[10] DHANDHALYA J K,PARMAR S K.Hyperspectral image classification using spatial spectral features and machine learning approach[C].IEEE International Conference on Recent Trends in Electronics,Information and Communication Technology.IEEE,2017:1161-1165.
[11] HOSSAIN M A,HASIN-E-JANNAT,AHMED B,et al.Feature mining for effective subspace detection and classification of hyperspectral images[C].International Conference on Electrical,Computer and Communication Engineering.IEEE,2017:544-547.
[12] CHEN C,LI W,TRAMEL E W,et al.Spectral-spatial preprocessing using multihypothesis prediction for noise-robust hyperspectral image classification[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(4):1047-1059.
[13] BENEDIKTSSON J A.Spectral-spatial classififcation of hyperspectral remote sensing images[M].[s.l.]:Artech House,Inc.,2015:30-31.
[14] 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.
[15] GHAMISI P,BENEDIKTSSON J A.Feature selection based on hybridization of genetic algorithm and particle swarm optimization[J].IEEE Geoscience and Remote Sensing Letters,2014,12(2):309-313.
[16] GHAMISI P,ALI A R,COUCEIRO M S,et al.A novel evolutionary swarm fuzzy clustering approach for hyperspectral imagery[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2015,8(6):2447-2456.
[17] ZHU Z,JIA S,HE S,et al.Three-dimensional Gabor feature extraction for hyperspectral imagery classification using a memetic framework[J].Information Sciences,2015,298(C):274-287.
[18] 廖建尚,王立国,郝思媛.基于双边滤波和空间邻域信息的高光谱图像分类方法[J].农业机械学报.2017,48(8):140-146.LIAO J S,WANG L G,HAO S Y.Hyperspectral image classification method combined with bilateral filtering and pixel neighborhood information[J].Transaction of the Chinese Society for Agriculture Machinery,2017,48(8):140-146(in Chinese).
[19] 廖建尚,王立国.两类空间信息融合的高光谱图像分类方法.激光与光电子学进展.2017,54(8):107-116.LIAO J S,WANG L G.Hyperspectral image classification method based on fusion with two kinds of spatial information[J].Laser&Optoeletronics Progress,2017,54(8):107-116(in Chinese).
[20] 廖建尚,王立国.空间信息自适应融合的高光谱图像分类方法[J].光子学报.2017,46(4):152-164.LIAO J S,WANG L G.Hyperspectral image classification method based on adaptive fusion of spatial information[J].Acta Photonica Sinica,2017,46(4):152-164(in Chinese).
[21] 孙艳丽.联合丰度信息与空谱特征的高光谱影像分类研究[D].北京:中国科学院大学(中国科学院遥感与数字地球研究所),北京:2017:44.
[2] MA A,ZHONG Y,ZHAO B,et al.Semisupervised subspace-based DNA encoding and matching classifier for hyperspectral remote sensing imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(8):4402-4418.
[3] WANG L,ZHANG J,LIU P,et al.Spectral-spatial multi-feature-based deep learning for hyperspectral remote sensing image classification[J].Soft Computing.2017,21(1):213-221.
[4] ZHANG C,ZHENG Y,FENG C.Spectral-spatial classifi-cation of hyperspectral images using probabilistic weighted strategy for multifeature fusion[J].IEEE Geoscience and Remote Sensing Letters,2016,13(10):1562-1566.
[5] LIAO W,MURA M D,CHANUSSOT J,et al.Fusion of spectral and spatial information for classification of hyperspectral remote-sensed imagery by local graph[J].IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing,2016,9(2):583-594.
[6] FANG L,LI S,DUAN W,et al.Classification of hyper-spectral images by exploiting spectral-spatial information of superpixel via multiple kernels[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(12):6663-6674.
[7] LI W,CHEN C,SU H,et al.Local binary patterns and extreme learning machine for hyperspectral imagery classification[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(7):3681-3693.
[8] ROMERO A,GATTA C,CAMPS-VALLS G.Unsupervised deep feature extraction for remote sensing image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(3):1349-1362.
[9] GUO X,HUANG X,ZHANG L,et al.Support tensor machines for classification of hyperspectral remote sensing imagery[J].IEEE Transactions on Geoscience & Remote Sensing,2016,54(6):3248-3264.
[10] DHANDHALYA J K,PARMAR S K.Hyperspectral image classification using spatial spectral features and machine learning approach[C].IEEE International Conference on Recent Trends in Electronics,Information and Communication Technology.IEEE,2017:1161-1165.
[11] HOSSAIN M A,HASIN-E-JANNAT,AHMED B,et al.Feature mining for effective subspace detection and classification of hyperspectral images[C].International Conference on Electrical,Computer and Communication Engineering.IEEE,2017:544-547.
[12] CHEN C,LI W,TRAMEL E W,et al.Spectral-spatial preprocessing using multihypothesis prediction for noise-robust hyperspectral image classification[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(4):1047-1059.
[13] BENEDIKTSSON J A.Spectral-spatial classififcation of hyperspectral remote sensing images[M].[s.l.]:Artech House,Inc.,2015:30-31.
[14] 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.
[15] GHAMISI P,BENEDIKTSSON J A.Feature selection based on hybridization of genetic algorithm and particle swarm optimization[J].IEEE Geoscience and Remote Sensing Letters,2014,12(2):309-313.
[16] GHAMISI P,ALI A R,COUCEIRO M S,et al.A novel evolutionary swarm fuzzy clustering approach for hyperspectral imagery[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2015,8(6):2447-2456.
[17] ZHU Z,JIA S,HE S,et al.Three-dimensional Gabor feature extraction for hyperspectral imagery classification using a memetic framework[J].Information Sciences,2015,298(C):274-287.
[18] 廖建尚,王立国,郝思媛.基于双边滤波和空间邻域信息的高光谱图像分类方法[J].农业机械学报.2017,48(8):140-146.LIAO J S,WANG L G,HAO S Y.Hyperspectral image classification method combined with bilateral filtering and pixel neighborhood information[J].Transaction of the Chinese Society for Agriculture Machinery,2017,48(8):140-146(in Chinese).
[19] 廖建尚,王立国.两类空间信息融合的高光谱图像分类方法.激光与光电子学进展.2017,54(8):107-116.LIAO J S,WANG L G.Hyperspectral image classification method based on fusion with two kinds of spatial information[J].Laser&Optoeletronics Progress,2017,54(8):107-116(in Chinese).
[20] 廖建尚,王立国.空间信息自适应融合的高光谱图像分类方法[J].光子学报.2017,46(4):152-164.LIAO J S,WANG L G.Hyperspectral image classification method based on adaptive fusion of spatial information[J].Acta Photonica Sinica,2017,46(4):152-164(in Chinese).
[21] 孙艳丽.联合丰度信息与空谱特征的高光谱影像分类研究[D].北京:中国科学院大学(中国科学院遥感与数字地球研究所),北京:2017:44.