Localization of Subsurface Pipes in Radar Images by 3D Convolutional Neural Network and Kirchhoff Migration
Localization of Subsurface Pipes in Radar Images by 3D Convolutional Neural Network and Kirchhoff Migration
复制标题
通过 3D 卷积神经网络和基尔霍夫偏移对雷达图像中的地下管道进行定位
DOI：
10.1109/igarss47720.2021.9554318
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
and T. Mizutani
中科院分区：
文献类型：
--
作者：
T. Yamaguchi;and T. Mizutani
探地雷达（Ground Penetrating Radar，GPR）具有高密度、高速度的三维监测能力，是一种很有前途的地下管线探测工具。然而，由于雷达数据量巨大，判读困难，检查时间和成本是瓶颈。提出了一种结合3D卷积神经网络（3D-CNN）和基尔霍夫偏移的检测算法。所开发的模型估计管道的存在和方向。与2D-CNN相比，3D-CNN利用管道的3D几何形状来实现高分类精度。利用克希霍夫偏移方法，通过提取峰值来定位管道。通过对实测数据的分析，该算法在合理的计算时间内，对管道的三维位置和布置有清晰的认识。
Ground Penetrating Radar (GPR) is a promising tool for subsurface utility pipe detection due to its dense and highspeed 3D monitoring. However, because of enormous amount of radar data and difficulty of interpretation, inspection time and cost are the bottlenecks. In this research, a novel detection algorithm by the combination of 3D Convolutional Neural Network (3D-CNN) and Kirchhoff migration was proposed. The developed model estimated pipes' existences and directions. 3D-CNN utilized the 3D geometries of the pipes to achieve high classification accuracy compared to 2D-CNN. Kirchhoff migration was applied to localize pipes by extracting peaks. From the result of experimental field data, the algorithm provides the clear understandings of pipes' 3D positions and arrangement with reasonable calculation time.