基于3D-CNN结合PointSIFT的断裂带提取方法  

Fracture Zone Extraction Method Based on Three-DimensionalConvolutional Neural Network Combined with PointSIFT

作　　者：王浩[1] 宋冬梅[1] 王斌[1] 戴嵩 Wang Hao;Song Dongmei;Wang Bin;Dai Song(College of Ocean and Space Information,China University of Petroleum(East China),Qingdao 266580,Shandong,China)

机构地区：[1]中国石油大学(华东)海洋与空间信息学院,山东青岛266580

出　　处：《激光与光电子学进展》2023年第24期140-150,共11页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(41772350,41701513);山东省自然科学基金(ZR2022MD015)。

摘　　要：为解决面向复杂地形区域的断裂带提取问题,提出了一种基于三维卷积神经网络(3D-CNN)结合PointSIFT的断裂带提取方法。该方法首先通过PointSIFT模块对原始点云数据的空间方位信息进行编码,以实现对点云特征的聚合,从而得到带有不同尺度特征的重构点云数据。其次,以构建的三维卷积模块为核心搭建3D-CNN模型,以此对重构的点云数据进行深层次特征提取。然后,将所提取的点云特征输入到全连接层以完成点云类别的判断,从而解决断裂带提取问题。最后,将所提方法与张量分解方法、深度神经网络方法在两套数据集上进行对比实验,结果表明:所提方法能够获得更低的分类误差,从而证实了该方法在点云断裂带提取方面的优越性。This paper presents a fracture zone extraction method for complex terrain areas using a combination of a threedimensional convolutional neural network(3D-CNN)and PointSIFT.The PointSIFT module encodes spatial orientation information of the original point cloud data to aggregate point cloud features,resulting in reconstructed point cloud data with different scale features.Subsequently,a 3D-CNN model is developed,with a 3D convolutional module serving as the primary component,to extract deep-level features from the reconstructed point cloud data.The extracted point cloud features are then fed into a fully connected layer for the categorization of the point clouds,addressing the challenge associated with fracture zone extraction.Comparative evaluations with the tensor decomposition method and deep neural network method are performed on two datasets.The results demonstrate that the proposed fracture zone extraction method achieves a lower classification error,thus confirming the superiority of the method in effectively extracting fracture zones from point cloud data.

关 键 词：激光雷达 断裂带提取 深度学习 PointSIFT 三维卷积 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]