ABSTRACT

Research on spatial information is a hot topic in hyperspectral remote-sensing image (HSI) exploitation. This paper defines a spatial correlation filter to study the spatial variation characteristics and intensity of regionalized variables. Unlike existing spatial information expression methods based on theoretical model, the novel filter takes multi-scale and multi-directional spatial structure features into account and visualizes them, which is model-free and more comprehensive. Further, SCFB model constructed by the filter banks is proposed for pixel-wise classification of HSI and performs well when replacing the classifier component with multiple machine-learning algorithms. Accurate classification on two classic hyperspectral datasets with approximately 3% training samples and on one large dataset with 0.544% training samples indicate that the model is promising in small samples learning. In particular, supervised linear discriminant analysis (LDA) used in the feature subspace optimization part of the model significantly outperforms the other two spectral strategies. Most notably, the model is not only superior to the traditional machine-learning methods considering spectral information only, but also has advantages in accuracy, the number of learnable kernel parameters and time-consuming compared with equal-layer convolution neural network.

摘要

空间信息研究是高光谱遥感图像（HSI）开发的热点。本文定义了一个空间相关滤波器来研究区域化变量的空间变化特征和强度。与现有基于理论模型的空间信息表达方法不同，新型过滤器将多尺度、多方向的空间结构特征考虑在内，并将其可视化，无模型，更全面。此外，由滤波器组构建的 SCFB 模型被提出用于 HSI 的逐像素分类，并且在用多种机器学习算法替换分类器组件时表现良好。在两个经典的高光谱数据集上准确分类，训练样本大约为 3%，一个大数据集的训练样本为 0。544% 的训练样本表明该模型在小样本学习中很有前景。特别是，模型的特征子空间优化部分使用的监督线性判别分析（LDA）明显优于其他两种谱策略。最值得注意的是，该模型不仅优于仅考虑光谱信息的传统机器学习方法，而且与等层卷积神经网络相比，在准确性、可学习核参数的数量和耗时方面也具有优势。