Semi‑Automatic Identification of Rock Mass Structural Planes in 3D Point Clouds Based on Support Vector Machines

ZHU Tao; SHI Wenbing; LIU Yongzhi; WANG Yong; LIANG Feng

doi:10.13409/j.cnki.jdpme.20240607003

您当前的位置：

首页 >

文章列表页 >

Semi‑Automatic Identification of Rock Mass Structural Planes in 3D Point Clouds Based on Support Vector Machines

更新时间：2025-03-10

- Semi‑Automatic Identification of Rock Mass Structural Planes in 3D Point Clouds Based on Support Vector Machines
- Journal of Disaster Prevention and Mitigation Engineering Vol. 45, Issue 1, Pages: 95-103(2025)
- 作者机构：
  
  1.贵州大学资源与环境工程学院，贵州贵阳 550025
  2.贵州大学贵州省山地地质灾害防治工程技术研究中心，贵州贵阳 550025
  3.喀斯特地质资源与环境教育部重点实验室（贵州大学），贵州贵阳 550025
- 作者简介：
- 基金信息：
- DOI：10.13409/j.cnki.jdpme.20240607003
  CLC： P642
- Received：07 June 2024，
  
  Revised：2024-07-08，
  
  Published：15 February 2025
- 稿件说明：
移动端阅览
朱涛,史文兵,刘永志等.基于支持向量机的三维点云岩体结构面半自动识别方法[J].防灾减灾工程学报,2025,45(01):95-103.

ZHU Tao,SHI Wenbing,LIU Yongzhi,et al.Semi‑Automatic Identification of Rock Mass Structural Planes in 3D Point Clouds Based on Support Vector Machines[J].Journal of Disaster Prevention and Mitigation Engineering,2025,45(01):95-103.
朱涛,史文兵,刘永志等.基于支持向量机的三维点云岩体结构面半自动识别方法[J].防灾减灾工程学报,2025,45(01):95-103. DOI： 10.13409/j.cnki.jdpme.20240607003.

ZHU Tao,SHI Wenbing,LIU Yongzhi,et al.Semi‑Automatic Identification of Rock Mass Structural Planes in 3D Point Clouds Based on Support Vector Machines[J].Journal of Disaster Prevention and Mitigation Engineering,2025,45(01):95-103. DOI： 10.13409/j.cnki.jdpme.20240607003.

摘要

结构面在评价岩体力学性质和边坡稳定性方面起着至关重要的作用，相比于传统测量，一种准确、高效的结构面参数识别方法尤为重要。提出了一种基于支持向量机（SVM）的三维点云岩体结构面提取的新方法，首先获取点云坐标、RGB、法向量、曲率和密度等作为机器学习模型的特征向量作为输入，结合人工和自动挑选学习样本，随后把学习样本分为训练集和测试集用于训练SVM模型并测试模型，将被接受的模型用于点云的预测分类，进而识别结构面和提取信息。将该方法应用于公开边坡数据集和发耳镇某采区边坡结构面调查，结果表明：使用LOF与PCA结合方法有效地提高了法向量估计的准确性，而DetRD‑PCA方法用于估计单个结构面的法向量并计算产状时得到结果更加准确；对公开点云数据集的结构面进行识别，SVM识别881 552个点时间仅需9 s，成功提取了四组结构面，与前人结果对比，倾向平均偏差最大3.12°，倾角平均偏差最大1.54°；将方法应用于发耳镇某采区边坡的结构面调查中，SVM识别1 450 148个点仅需18 s，成功提取了两组结构面，与经典的三点法估算比较，倾向和倾角的偏差为0.7°~3.3°和0.1°~3.3°；该方法对于小样本的训练数据依然能够表现出较高的正确率。

Abstract

Structural planes play a crucial role in evaluating the mechanical properties of rock masses and slope stability. Compared to traditional measurement methods

an accurate and efficient method for recognizing structural plane parameters is particularly important. This paper proposes a new method for extracting structural planes of rock masses from 3D point clouds based on Support Vector Machines (SVM). First

point cloud coordinates

RGB values

normal vectors

curvature

and density were used as feature vectors for the machine learning model. By combining manually and automatically selected learning samples

the samples were divided into training and testing sets to train and test the SVM model. The accepted model was then used for point cloud prediction and classification

enabling the identification of structural planes and information extraction. This method was applied to a publicly available slope dataset and a structural plane survey at a mining area in Fa'er Town. The results showed that: the combination of LOF and PCA methods effectively improved the accuracy of normal vector estimation

while the DetRD-PCA method provided more accurate results for estimating normal vectors and calculating orientation for individual planes. When applied to the publicly available point cloud dataset

the SVM identified 881552 points in just 9 seconds

successfully extracting four sets of structural planes. Compared with previous results

the maximum average deviation in the dip direction was 3.12°

and the maximum average deviation in the dip angle was 1.54°. When applied to the structural plane survey in the Fa'er Town mining area slope

the SVM identified 1450148 points in 18 seconds

successfully extracting two sets of structural planes. Compared with the classic three-point method

the deviations in dip direction and dip angle ranged from 0.7° to 3.3° and 0.1° to 3.3°

respectively. The method demonstrated high accuracy even with small training sample sizes.

关键词

Keywords

references

孙广忠 . 论“岩体结构控制论” ［J］. 工程地质学报， 1993 ， 1 （ 1 ）： 14 ‑ 18 .

Sun G Z . On the theory of structure‑controlled rockmass ［J］. Journal of Engineering Geology ， 1993 ， 1 （ 1 ）： 14 ‑ 18 . （in Chinese）

谷德振，黄鼎成 . 岩体结构的分类及其质量系数的确定［J］. 水文地质工程地质， 1979 ， 2 （ 2 ）： 8 ‑ 13 .

Gu D Z ， Huang D C . Classification of rock structures and determination of their quality coefficients ［J］. Hydrogeology and Engineering Geology ， 1979 ， 2 （ 2 ）： 8 ‑ 13 . （in Chinese）

黄国明，黄润秋 . 复杂岩体结构的几何描述［J］. 成都理工学院学报， 1998 ， 25 （ 4 ）： 83 ‑ 89 .

Huang G M ， Huang R Q . Geometric description of complex rock structures ［J］. Journal of Chengdu University of Technology ， 1998 ， 25 （ 4 ）： 83 ‑ 89 . （in Chinese）

董秀军，黄润秋 . 三维激光扫描技术在高陡边坡地质调查中的应用［J］. 岩石力学与工程学报， 2006 ， 25 （增2 ）： 3629 ‑ 3635 .

Dong X J ， Huang R Q . Application of 3D laser scanning technology to geologic survey of high and steep slope ［J］. Chinese Journal of Rock Mechanics and Engineering ， 2006 ， 25 （ Sup2 ）： 3629 ‑ 3635 . （in Chinese）

王凤艳 . 数字近景摄影测量快速获取岩体裂隙信息的工程应用［D］. 长春：吉林大学， 2006 .

Wang F Y . Engineering application of rapid acquiring rock mass fractures information with digital close range photogrammetry ［D］. Changchun ： Jilin University ， 2006 . （in Chinese）

Riquelme J A ， Abellán A ， Tomás R ， et al . A new approach for semi‑automatic rock mass joints recognition from 3D point clouds ［J］. Computers and Geosciences ， 2014 ， 68 ： 38 ‑ 52 .

Chen J Q ， Zhu H H ， Li X J . Automatic extraction of discontinuity orientation from rock mass surface 3D point cloud ［J］. Computers and Geosciences ， 2016 ， 95 ： 18 ‑ 31 .

葛云峰，夏丁，唐辉明，等 . 基于三维激光扫描技术的岩体结构面智能识别与信息提取［J］. 岩石力学与工程学报， 2017 ， 36 （ 12 ）： 3050 ‑ 3061 .

Ge Y F ， Xia D ， Tang H M ， et al . Intelligent identification and extraction of geometric properties of rock discontinuities based on terrestrial laser scanning ［J］. Chinese Journal of Rock Mechanics and Engineering ， 2017 ， 36 （ 12 ）： 3050 ‑ 3061 . （in Chinese）

Kong D H ， Wu F Q ， Saroglou C . Automatic identification and characterization of discontinuities in rock masses from 3D point clouds ［J］. Engineering Geology ， 2022 ， 265 ： 105442 .

丁世飞，齐丙娟，谭红艳 . 支持向量机理论与算法研究综述［J］. 电子科技大学学报， 2011 ， 40 （ 1 ）： 2 ‑ 10 .

Ding S F ， Qi B J ， Tan H Y . An overview on theory and algorithm of support vector machines ［J］. Journal of University of Electronic Science and Technology of China ， 2011 ， 40 （ 1 ）： 2 ‑ 10 . （in Chinese）

黄发明，殷坤龙，蒋水华，等 . 基于聚类分析和支持向量机的滑坡易发性评价［J］. 岩石力学与工程学报， 2018 ， 37 （ 1 ）： 156 ‑ 167 .

Huang F M ， Yin K L ， Jiang S H ， et al . Landslide susceptibility assessment based on clustering analysis and support vector machine ［J］. Chinese Journal of Rock Mechanics and Engineering ， 2018 ， 37 （ 1 ）： 156 ‑ 167 . （in Chinese）

Mitra J N ， Nguyen A ， Guibas L . Estimating surface normals in noisy point cloud data ［J］. International Journal of Computational Geometry & Applications ， 2003 ， 14 （ 4‑5 ）： 322 ‑ 328 .

王敬华，赵新想，张国燕，等 . NLOF：一种新的基于密度的局部离群点检测算法［J］. 计算机科学， 2013 ， 40 （ 8 ）： 181 ‑ 185 .

Wang J H ， Zhao X X ， Zhang G Y ， et al . NLOF： A new density‑based local outlier detecting algorithm ［J］. Computer Science ， 2013 ， 40 （ 8 ）： 181 ‑ 185 . （in Chinese）

刘竞妍，张可，王桂华 . 综合评价中数据标准化方法比较研究［J］. 数字技术与应用， 2018 ， 36 （ 6 ）： 84 ‑ 85 .

Liu J Y ， Zhang K ， Wang G H . Comparative study on data standardization methods in comprehensive evaluation ［J］. Digital Technology & Application ， 2018 ， 36 （ 6 ）： 84 ‑ 85 . （in Chinese）

Battulwar R ， Zare‑Naghadehi M ， Emami E ， et al . A state‑of‑the‑art review of automated extraction of rock mass discontinuity characteristics using three-dimensional surface models ［J］. Journal of Rock Mechanics and Geotechnical Engineering ， 2021 ， 13 （ 4 ）： 920 ‑ 936 .

王述红，魏崴，陈浩，等 . 基于HDBSCAN算法的岩体结构面产状识别及分组方法［J］. 东北大学学报（自然科学版）， 2022 ， 43 （ 6 ）： 888 ‑ 896 .

Wang S H ， Wei W ， Chen H ， et al . Identification and grouping method of strike information of rock mass based on the HDBSCAN algorithm ［J］. Journal of Northeastern University（Natural Science）， 2022 ， 43 （ 6 ）： 888 ‑ 896 .

Nurunnabi A ， Belton D ， West G . Robust statistical approaches for local planar surface fitting in 3D laser scanning data ［J］. ISPRS Journal of Photogrammetry and Remote Sensing ， 2014 ， 96 ： 106 ‑ 122 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Reliability Analysis of Slopes Reinforced with Prestressed Anchor Cables Based on Active Learning Support Vector Machine

Development and Application of Domestic High‑performance Discrete Element Software MatDEM

Research Status and Prospects of Cyclic Shear Apparatus and Shear Mechanical Properties of Rock Mass Structural Planes

Foundation Coefficient Model of Soil‑rock Mixture based on Support Vector Machine and Its Application

Research on the Occlusion of Debris Flow Window-frame Dam based on SVM and RF Methods

Related Author

LU Meng

ZHANG Jie

XIE Xiaochuang

HE Fengqian

LIU Cunfu

DUAN Xiangrui

LIU Chun

YANG Zerong

Related Institution

Yalong River Hydropower Development Company, LTD.

Department of Geotechnical Engineering, Tongji University

School of Earth Sciences and Engineering,Nanjing University

State Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences

University of Chinese Academy of Sciences

⁰