首页 > , Vol. , Issue () : -
针对高光谱图像样本标签量少且空间-光谱信息利用不充分而导致图像分类精度较低的问题，本文提出一种联合超像素降维和后验概率优化的高光谱图像分类方法。该方法首先基于高光谱图像的空间-光谱信息为每个样本构建局部邻域集合，并从局部邻域集合中提取超像素稀疏混合特征来充分表征图像的空谱信息和相关变化信息，然后将全局稀疏混合特征输入支持向量机分类器中生成像素的类别概率向量，最后采用后验概率模型优化类别概率向量，并依据概率最大值得到分类标签图。在三组常用的小规模数据集Indian Pines、Pavia University和Salinas，以及一组大规模数据集HoustonU上的实验结果表明：所提出的分类方法能够自适应地充分提取高光谱图像的高判别性特征信息，且在少量样本标签情形下，该方法在四组实验数据集上分别获得了98.58%、96.88%、98.54%和91.01%的总体分类精度，并优于目前几种先进的分类方法。
Objective: Hyperspectral image (HSI) classification is one of the fundamental tasks in the field of applied remote sensing. As technological advances have increased the spatial and spectral resolutions available for data acquisition, the problem of achieving accurate HSI classification is becoming more challenging, especially for the HSI data with small labeled training samples and the insufficient utilization of spatial-spectral information in the HSI classification models. Aiming at these problems, this paper proposes a new HSI classification method (expressed as SKERW_SVM) by combining the superpixel dimension reduction (SDR) with post-processing optimization. Method: First, we develop a superpixel sparse linear discriminant analysis (SSLDA) method by combining regional clustering (RC) with SLDA. In the SSLDA method, the RC is applied to construct a homogeneous local neighbourhood set with high spatial correlation and spectral similarity for each pixel of the HSI, and the SLDA to extract superpixel sparse mixture features that can fully characterize spatial-spectral information and related change information of the HSI based on the constructed homogeneous regions. Then, the extracted sparse mixture features are inputted into the support vector machine to generate the class probabilities of all pixels. Finally, the original class probabilities are optimized in the post-processing step by the extended random walker that can express the spatial relationship among adjacent pixels quantitatively, and the classification map is gotten according to the maximum probability. Result: In order to assess the performance of the proposed method, a series of experiments are conducted on three small-scale HSI datasets including Indian Pines, University of Pavia, and Salinas, as well as a large-scale HSI dataset HoustonU. The proposed SKERW_SVM obtains overall accuracy of 98.58%, 96.88%, 98.54%, and 91.01%, respectively, on Indian Pines, University of Pavia, Salinas, and HoustonU. Experimental results demonstrate that our SKERW_SVM can fully mine the joint spatial-spectral features of HSI and achieve higher classification accuracy under the case of a small labeled training samples in comparison to several related advanced methods. Moreover, the operation time consuming by the SKERW_SVM is appropriate compared to other methods. Conclusion: Therefore, under the lack of the labeled HSI pixels condition, the proposed HSI classification method by combining the SDR with post-processing optimization can efficiently extract the high discrimination mixture features information of HSI and significantly enhance classification performance. The SDR based on the homogeneous local regions, one of the components of the SKERW_SVM classification model, can greatly reduce the data redundancy and fully extract the information of spatial and spectral signatures in comparison to the pixel-wise dimension reduction methods. Meanwhile, the extended random walker in the post-processing step can fully use spatial information of HSI by constructing relationship graph to optimizing the original class probabilities, which further improves the classification performance.