This paper presents a feature reasoning-based graph convolution network (FR-GCNet) to improve the classification accuracy of airborne multispectral LiDAR (MS-LiDAR) point clouds. In the FR-GCNet, we directly assign semantic labels to all points by exploring representative features both globally and locally. Based on the graph convolution network (GCN), a global reasoning unit is embedded to obtain the global contextual feature by revealing spatial relationships of points, while a local reasoning unit is integrated to dynamically learn edge features with attention weights in each local graph. Extensive experiments on the Titan MS-LiDAR data showed that the proposed FR-GCNet achieved a promising classification performance with an overall accuracy of 93.55%, an average F₁-score of 78.61%, and a mean Intersection over Union (IoU) of 66.78%. Comparative experimental results demonstrated the superiority of the FR-GCNet against other state-of-the-art approaches.

本文提出了一种基于推理特征曲线图卷积网络（FR-GCNet），以提高空气中的分类精度米ULTI小号pectral激光雷达（MS-LIDAR）点云。在 FR-GCNet 中，我们通过探索全局和局部的代表性特征，直接为所有点分配语义标签。基于图卷积网络（GCN），嵌入全局推理单元，通过揭示点的空间关系获得全局上下文特征，同时集成局部推理单元，动态学习每个局部图中具有注意力权重的边缘特征。对 Titan MS-LiDAR 数据的大量实验表明，所提出的 FR-GCNet 取得了有希望的分类性能，总体准确率为 93.55%，平均F₁ -得分为 78.61%，平均交叉路口 (IoU) 为 66.78%。对比实验结果证明了 FR-GCNet 相对于其他最先进方法的优越性。