Tunnel point cloud adaptive denoising method based on improved MLESAC

QIAN cheng

您当前的位置：

首页 >

文章列表页 >

Tunnel point cloud adaptive denoising method based on improved MLESAC

Optical Image Processing | 更新时间：2026-01-05

- Tunnel point cloud adaptive denoising method based on improved MLESAC
- OPTICAL TECHNIQUE Vol. 51, Issue 6, Pages: 750-755(2025)
- 作者机构：
  
  中铁十四局集团有限公司山东济南 854000
- 作者简介：
- 基金信息：
- DOI：
  CLC： P237
- Received：24 June 2025，
  
  Revised：2025-08-14，
  
  Published：20 November 2025
- 稿件说明：
移动端阅览
钱程.基于改进MLESAC的隧道点云自适应去噪方法研究[J].光学技术,2025,51(06):750-755.

QIAN cheng.Tunnel point cloud adaptive denoising method based on improved MLESAC[J].OPTICAL TECHNIQUE,2025,51(06):750-755.
钱程.基于改进MLESAC的隧道点云自适应去噪方法研究[J].光学技术,2025,51(06):750-755. DOI：

QIAN cheng.Tunnel point cloud adaptive denoising method based on improved MLESAC[J].OPTICAL TECHNIQUE,2025,51(06):750-755. DOI：

摘要

隧道中堆积的设备导致扫描数据中存在着大量噪点，无法直接用于后续分析与处理。针对点云数据的去噪问题，顾及隧道纵向剖面为类圆几何形状，提出一种基于改进MLESAC算法的隧道点云自适应去噪方法。方法首先将隧道切成一个个区域，每个小区域视作无曲率的直线隧道，并结合椭圆几何特征改进MLESAC算法，对各个区域的二维投影进行椭圆拟合，最后基于椭圆拟合参数实现噪点去除。来自西部某工程的数据验证了该方法的准确性和可靠性，能够在无需人工操作的情况下，自动高效地实现去噪。

Abstract

Accurate denoising of tunnel point cloud data is challenging due to noise caused by stacked equipment in scans

which hinders subsequent analysis. To address this

an adaptive denoising method based on an improved MLESAC algorithm is proposed

leveraging the quasi-circular geometry of tunnel longitudinal profiles. First

the tunnel is segmented into small regions

each approximated as a straight section with negligible curvature. The MLESAC algorithm is then enhanced by incorporating elliptic geometric features to perform 2D ellipse fitting on projected points within each region. Finally

noise removal is achieved based on the fitted ellipse parameters. Validation using data from a project in western China demonstrates the method’s accuracy and reliability

enabling fully automated and efficient denoising without manual intervention.

关键词

Keywords

references

余苑航 , 阎波 . 我国超大城市地下空间开发现状及其发展趋势 [J ] . 地下空间与工程学报 , 2021 , 17 ( S1 ): 1 — 7 .

Yu Yuanhang , Yan Bo . Present situation and development trend of underground space in megacity in China [J ] . Chinese Journal of Underground Space and Engineering , 2021 , 17 ( Suppl 1 ): 1 — 7 .

李喆 , 江媛 , 姜礼杰 , 等 . 我国隧道和地下工程施工技术与装备发展战略研究 [J ] . 隧道建设 , 2021 , 41 ( 10 ): 1717 — 1732 .

Li Zhe , Jiang Yuan , Jiang Lijie . Research on development strategy of tunnel and underground construction technology and equipment in china [J ] . Tunnel Construction , 2021 , 41 ( 10 ): 1717 — 1732 .

黄哲 , 王永才 , 李德英 . 3D目标检测方法研究综述 [J ] . 智能科学与技术学报 , 2023 , 5 ( 01 ): 7 — 31 .

Huang Zhe , Wang Yongcai , Li Deying . A survey of 3D object detection algorithms [J ] . Chinese Journal of Intelligent Science and Technology , 2023 , 5 ( 1 ): 7 — 31 .

秦静 , 王伟滨 , 邹启杰 , 等 . 基于激光雷达点云的3D目标检测方法综述 [J ] . 计算机科学 , 2023 , 50 ( S1 ): 259 — 265 .

Qin Jing , Wang Weibing , Zou Qijie , et al . Review of 3D target detection methods based on LiDAR point clouds [J ] . Computer Science , 2023 , 50 ( 6A ): 259 — 265 .

肖俊 , 石光田 . 三维点云去噪技术 [J ] . 中国科学院大学学报 , 2023 , 40 ( 05 ): 577 — 595 .

Xiao Jun , Shi Guangtian . Three-dimensional point cloud denoising [J ] . Journal of University of Chinese Academy of Sciences , 2023 , 40 ( 5 ): 577 .

贾朝阳 , 陈岳坪 , 苏宇 . 基于距离阈值和密度区分改进的点云去噪算法 [J ] . 工具技术 , 2024 , 58 ( 10 ): 147 — 154 .

Jia Zhaoyang, Chen Yueping, Su Yu, Point cloud denoising algorithm based on distance threshold and density distinction [J ] . Tool Engineering , 2024 , 58 ( 10 ): 147 — 154 .

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 ( 03 ): 48 — 55 .

Zhongwen L , Zhuli REN , Yinghao HAO , et al . A point cloud denoising method for unstructured roadways based on regional growth [J ] . Journal of Mine Automation , 2024 , 50 ( 3 ): 48 — 55 .

周乐 , 孙傲 , 刘高翔 , 等 . 基于深度学习算法和三维点云的岩体结构面智能识别 [J ] . 工程勘察 , 2024 , 52 ( 09 ): 66 - 76 .

Zhou Le ， Sun Ao ， Liu Gaoxiang , Intelligent identification of rock mass discontinuity based on deep learning algorithm and 3 D point clouds [J ] . Geotechnical Investigation & Surveying ,2024, 52 ( 09 ): 66 — 76 .

郑理科 , 王健 , 李志远 , 等 . 一种局部最优邻域法向量估算的巷道点云去噪方法 [J ] . 测绘科学 , 2023 , 48 ( 04 ): 140 — 148+171 .

Zheng Like , Wang Jian , Li Zhiyuan . A denoising method of roadway point cloud based on local optimal neighborhood normal vector estimation [J ] . Sci Surv Mapp , 2023 , 48 ( 4 ): 140 — 148 .

李先帅 , 武斌 . 基于椭圆拟合的隧道点云数据去噪方法 [J ] . 铁道科学与工程学报 , 2021 , 18 ( 03 ): 703 — 709 .

Li Xishuai , Wu Bin . Denoising method of tunnel point cloud data based on ellipse fitting [J ] . Journal of Railway Science and Engineering , 2021 , 18 ( 3 ): 703 — 709 .

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 ] . 煤炭科学技术 , 2025 , 53 ( S1 ): 327 — 337 .

Ren Zhuli ， Yuan Ruifu ， Wang Liguan ， et al . Two-stage denoising method for complex underground tunnel scene three-dimensional point clouds [J ] . Coal Science and Technology , 20255 ,3(S)327— 337 .

沈长表 , 夏永华 , 刘勇 , 等 . 基于点云空间扩展的盾构隧道整体去噪方法 [J ] . 测绘通报 , 2024 ,( 02 ): 153 — 156 .

Shen Changbiao , Xia Yonghua , Liu Yong , et al . Overall denoising method for shield tunnel based on point cloud spatial expansion [J ] . Bulletin of Surveying and Mapping , 2024 , 0 ( 2 ): 153 — 156 .

郑天洋 , 马斌 . 多尺度点云噪声的平滑去噪方法 [J ] . 应用激光 , 2024 , 44 ( 12 ): 148 — 157 .

Zheng Tianyang , Ma Bin . Smooth denoising method for multi-scale point cloud noise [J ] . Applied Laser , 2024 , 44 ( 12 ): 148 .

傅思思 , 刘闯 , 王劲松 , 等 . 基于Transformer的超欠挖隧道干扰点云分割算法 [J ] . 光学技术 , 2025 , 51 ( 03 ): 316 — 322 .

Fu Sisi , Liu Chuang , Wang Jinsong , et al . Transformer based interference point cloud segmentation algorithm for underexcavated tunnels [J ] . Optical Technique , 2025 , 51 ( 3 ): 316 .

吴志才 , 魏冠军 , 党空雁 , 等 . 基于改进双边滤波的轨道点云去噪算法 [J ] . 应用激光 , 2024 , 44 ( 11 ): 174 — 182 .

Wu Zhicai , Wei Guanjun , Dang Kongyan , et al . Orbital point cloud denoising algorithm based on improved bilateral filtering [J ] . Applied Laser , 2024 , 44 ( 11 ): 174 .

葛程鹏 , 赵东 , 王蕊 , 等 . 基于改进DBSCAN和距离共识评估的分段点云去噪方法 [J ] . 系统仿真学报 , 2024 , 36 ( 08 ): 1800 — 1809 .

Ge Chengpeng , Zhao Dong , Wang Rui , et al . Section point cloud denoising method based on enhanced DBSCAN and distance consensus evaluation [J ] . Journal of System Simulation , 2024 , 36 ( 8 ): 1800 — 1809 .

Bao Y , Wen , Y , Tang C . Three-dimensional point cloud denoising for tunnel data by combining intensity and geometry information [J ] . Sustainability , 2024 , 16 : 2077 .

Zhao F . Point cloud denoising algorithm with geometric feature preserving [J ] . Multimedia Systems , 2022 , 28 : 1679 — 1687 .

Song P , Jin F , Ji M , et al . Denoising algorithm for inclined tunnel point cloud data based on irregular contour features [J ] . Measurement Science and Technology , 2024 , 35 ( 9 ): 095203 .

Guo C L , Xia Z P , Li C C , et al . Point cloud denoising algorithm combined with improved radius filtering and local plane fitting [J ] . Laser & Optoelectronics Progress , 2024 , 61 （ 12 ）: 1215003.2023 : 1 — 11 .

Zhou S , Liu X , Wang C , et al . Non-iterative denoising algorithm based on a dual threshold for a 3D point cloud [J ] . Optics and Lasers in Engineering , 2020 , 126 : 105921 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰