基于S^(2)AF-GCN的高光谱遥感图像分类模型

Hyperspectral Remote Sensing Image Classification Model Based on S^(2)AF-GCN

在高光谱图像分类任务中,图卷积网络能够建模像素或区域间的结构关系和相似性关系。针对利用像素原始光谱特征计算节点相似度构造邻接矩阵不准确的问题,提出基于空间-光谱聚合特征的图卷积网络(S^(2)AF-GCN),用于特征提取和像素级分类。以像素的空间位置为中心,聚合像素空间邻域内的其他像素特征,利用聚合后的像素特征动态更新与邻域内其他像素的权重,通过多次聚合,实现区域内像素特征平滑,得到像素的有效特征表示。然后利用聚合特征计算相似度并构图,获得更为准确的邻接矩阵,同时利用聚合特征训练网络,获得更好的分类结果。S^(2)AF-GCN在三个常用高光谱数据集Indian Pines、Pavia University、Kennedy Space Center上利用1%的标记样本取得了85.51%、96.95%、94.92%的总体分类精度。

For hyperspectral image classification tasks,a graph convolutional network can model the structural and similarity relationships between pixels or regions.To solve the problem of inaccurate construction of an adjacency matrix by calculating the node similarity using the original spectral features of pixels,a graph convolutional network based on spatial-spectral aggregation features(S^(2)AF-GCN) is proposed for feature extraction and pixel-level classification.The S^(2)AF-GCN considers the spatial position of the pixel as the center,aggregates other pixel features in the spatial neighborhood of the pixel,and uses the aggregated pixel features to dynamically update the weights of other pixels in the neighborhood.Through multiple aggregations,the pixel features in the region are smoothed,and the effective feature representation of the pixels is obtained.Next,the aggregated features are used to calculate the similarity and construct a more accurate adjacency matrix.Moreover,the aggregated features are simultaneously used to train the S^(2)AF-GCN to obtain better classification results.The S^(2)AF-GCN achieves overall classification accuracies of 85.51%,96.95%,and 94.92% on three commonly used hyperspectral datasets,namely,Indian Pines,Pavia University,and Kennedy Space Center,respectively,using 1% labeled samples.