基于超像素分割的图注意力网络的高光谱图像分类

Hyperspectral Image Classification Based on Superpixel Segmentation with Graph Attention Networks

针对卷积神经网络(CNN)仅能应用于欧氏数据,无法有效获取像素间的全局关系特征以及长距离上下文信息的问题,构建一个基于超像素分割的图注意力网络SSGAT.该网络将超像素分割后的超像素块视为图结构中的图节点,有效减少了图结构的复杂度,并降低了分类图的噪声.在3个数据集上对SSGAT及对比算法的分类精度进行测试,分别获得了94.11%,95.22%,96.37%的总体分类精度.结果表明该方法性能优异,在处理大尺度区域的分类问题时优势明显.

Aiming at the problem that convolutional neural network(CNN)could only be applied to Euclidean data and could not effectively obtain global relationship features between pixels and long-distance contextual information,we constructed a superpixel segmentation-based graph attention network(SSGAT).The network treated the segmented superpixel blocks as graph nodes in the graph structure,effectively reducing the complexity of the graph structure and reducing the noise of the classification graph.The classification accuracy of SSGAT and the comparison algorithm were tested on three datasets,and overall classification accuracy of 94.11%,95.22%,and 96.37%were obtained,respectively.The results show that the method has excellent performance and significant advantages in dealing with classification problems in large-scale regions.