摘要： 针对当前基于张量结构的特征提取方法不能充分利用高光谱影像多种光谱-空间特征的问题,提出一种融合光谱-空间多特征的高光谱影像张量特征提取方法。利用3D Gabor滤波器提取不同频率和方向的纹理特征,采用形态学属性滤波器提取不同属性和尺度的形状特征,将高光谱影像光谱特征、纹理特征和形状特征结合为张量结构特征。在此基础上,利用局部张量判别分析方法增大同类特征张量之间的相似性以及异类张量间的差异性,得到融合多种空谱特征和判别信息的低维特征张量。使用Pavia University和Salinas影像数据集进行对比实验,结果表明,该方法能够有效保留影像空谱信息和类别间的判别信息,不仅可以提高分类精度,而且能够得到空间连续性更好的分类图。

关键词: 高光谱影像, 光谱-空间特征, 多特征, 张量判别分析, 特征提取

Abstract: Aiming at the problem that current hyperspectral image tensor feature extraction methods cannot make full use of the multiple spectral-spatial features of hyperspectral image,a new hyperspectral image tensor feature extraction method based on fusion of multiple spectral-spatial features is proposed in this paper.Firstly,3D Gabor wavelet is used to get multiple texture features with different directions and frequencies,and the multiple shape structural features are got by different morphological attribute filters.The tensor features are constructed by combining the spatial feature,multiple texture features and multiple shape structural features.Then,by using the local tensor discriminant analysis,the proposed method effectively increases the consistency of the same kind tensors and the difference of different kinds of tensors,which can get the lower dimensional tensors consisting of discriminating information and multiple spatial-spectral features.The experiments are performed on the Pavia University and Salinas hyperspectral data sets.Experimental results indicate that the proposed method can maintain the spatial-spectral information and discriminating information,which has higher classification accuracy and better spatial continuity classification map when it is applied to the classification images.

Key words: hyperspectral image, spectral-spatial feature, multiple features, tensor discriminant analysis, feature extraction

中图分类号: 

• TP751