Classification of tunnel point clouds based on improved cascaded BP neural network

doi:10.13474/j.cnki.11-2246.2024.1130

Abstract

Abstract: Efficient classification of tunnel point cloud data is crucial for safety monitoring and 3D reconstruction in underground transportation and mining operations, as it facilitates the comprehensive exploration and utilization of point cloud data. This study addresses issues in existing tunnel point cloud classification methods, such as noise sensitivity, low processing efficiency, and susceptibility to overfitting, by proposing a cascaded backpropagation (CBP) neural network classification method optimized with an early stopping mechanism and adaptive parameter tuning. Firstly, the Trimble RealWorks software is used to separate tunnel and ground point clouds. Then, local geometric features are extracted using spherical neighborhood space and covariance matrix eigenvalues to construct feature vectors. Finally, an improved CBP network is employed to hierarchically classify internal tunnel lighting equipment, signage, and various pipelines, thereby enhancing classification efficiency and accuracy. Experimental results demonstrate that the improved CBP neural network achieves high accuracy and reliability in tunnel point cloud classification, significantly improving data processing efficiency and providing data support for tunnel maintenance, renovation, and safety management.

Key words: point cloud, roadway, cascaded BP neural network, feature extraction, classification

CLC Number:

P237

DING Penghui, LI Zhiyuan, LIU Yi, WANG Zhenghui. Classification of tunnel point clouds based on improved cascaded BP neural network[J]. Bulletin of Surveying and Mapping, 2024, 0(11): 172-176.

References

[1] 刘峰, 王宏伟, 刘宇.基于多传感融合的巷道三维空间映射研究[J/OL].煤炭学报:1-10[2024-06-25].https://doi.org/10.13225/j.cnki.jccs.2023.0758.
[2] 张继贤, 林祥国, 梁欣廉. 点云信息提取研究进展和展望[J].测绘学报, 2017, 46(10):1460-1469.
[3] 贾庆仁.煤矿三维地质与巷道建模方法研究及应用[J].测绘学报, 2021, 50(9):1275.
[4] 智志洋, 李爱光, 杜志刚, 等.点云密度特征约束下的隧道开挖轴线抗噪提取[J].测绘通报, 2024(1):109-114.
[5] 顾滢, 李霖, 朱海红.基于改进超体素与图割的室内场景点云分割[J].测绘通报, 2024(1):65-71.
[6] CHEN Maolin, PAN Jianping, XU Jingzhong.Classification of terrestrial laser scanning data with density-adaptive geometric features[J].IEEE Geoscience and Remote Sensing Letters, 2018, 15(11):1795-1799.
[7] XIAO Zhihua.Research on multi-level point cloud classification method of underground tunnel[C]//Proceedings of 2022 the 3rd International Conference on Geology, Mapping and Remote Sensing.Zhoushan:IEEE, 2022.
[8] 汤圣君, 张韵婕, 李晓明, 等.超体素随机森林与LSTM神经网络联合优化的室内点云高精度分类方法[J].武汉大学学报(信息科学版), 2023, 48(4):525-533.
[9] 姚萌萌, 李晓明, 王伟玺, 等.几何特征与神经网络联合优化的室内三维点云语义分割方法[J].测绘通报, 2023(5):56-61.
[10] QI C R, YI Li, SU Hao, et al.PointNet++:deep hierarchical feature learning on point sets in a metric space[EB/OL].[2024-07-01].https://arxiv.org/abs/1706.02413v1.
[11] 张清波, 严加栋.融合自适应最优邻域和卷积神经网络的三维点云分类[J].测绘通报, 2023(7):177-182.
[12] GONG Ziyang, KANG Chenfei, WANG Annan, et al.3D point clouds classification and segmentation network based on global features[C]//Proceedings of 2021 China Automation Congress.Beijing:IEEE, 2021.
[13] 连忠文, 任助理, 郝英豪, 等.基于区域生长的非结构巷道点云去噪方法[J].工矿自动化, 2024, 50(3):48-55.
[14] 任助理, 袁瑞甫, 王李管, 等.复杂地下巷道场景三维点云两阶段去噪方法[J/OL].煤炭科学技术, 1-15.[2024-09-25].https://kns.cnki.net/kcms/detail/11.2402.TD.20240323.1416.002.html.
[15] 陶茂枕.基于BP神经网络的三维激光扫描点云数据的滤波方法研究[D].西安:长安大学, 2014.
[16] 许亮, 王亚龙, 刘颖, 等.一种级联式神经网络框架的路标识别方法研究[J].光电子·激光, 2020, 31(3):310-317.
[17] 曹子耕, 严春满, 杨旭辉, 等.基于多级级联BP神经网络的加速器束流轨道预测[J].强激光与粒子束, 2023, 35(12):230109.