State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430010, China.
Shenzhen Power Supply Co., Ltd., No. 2018 Cuizhu Road., Shenzhen 430079, China.
Sensors (Basel). 2018 Oct 7;18(10):3347. doi: 10.3390/s18103347.
The classification of point clouds is a basic task in airborne laser scanning (ALS) point cloud processing. It is quite a challenge when facing complex observed scenes and irregular point distributions. In order to reduce the computational burden of the point-based classification method and improve the classification accuracy, we present a segmentation and multi-scale convolutional neural network-based classification method. Firstly, a three-step region-growing segmentation method was proposed to reduce both under-segmentation and over-segmentation. Then, a feature image generation method was used to transform the 3D neighborhood features of a point into a 2D image. Finally, feature images were treated as the input of a multi-scale convolutional neural network for training and testing tasks. In order to obtain performance comparisons with existing approaches, we evaluated our framework using the International Society for Photogrammetry and Remote Sensing Working Groups II/4 (ISPRS WG II/4) 3D labeling benchmark tests. The experiment result, which achieved 84.9% overall accuracy and 69.2% of average F1 scores, has a satisfactory performance over all participating approaches analyzed.
点云分类是机载激光扫描 (ALS) 点云处理中的基本任务。面对复杂的观测场景和不规则的点分布，这是一项极具挑战性的任务。为了降低基于点的分类方法的计算负担并提高分类精度，我们提出了一种基于分割和多尺度卷积神经网络的分类方法。首先，提出了一种三步区域生长分割方法，以减少欠分割和过分割。然后，使用特征图像生成方法将点的三维邻域特征转换为二维图像。最后，将特征图像作为多尺度卷积神经网络的输入进行训练和测试任务。为了与现有方法进行性能比较，我们使用国际摄影测量与遥感学会工作组 II/4（ISPRS WG II/4）3D 标注基准测试评估了我们的框架。实验结果的总体准确率达到 84.9%，平均 F1 分数达到 69.2%，在所有分析的参与方法中表现出令人满意的性能。
