点云数据去噪的自适应联合滤波方法

曲大义; 韦良帅; 王可栋; 张智; 李文杰

doi:10.11959/j.issn.2096-6652.202534

您当前的位置：

首页 >

文章列表页 >

点云数据去噪的自适应联合滤波方法

学术论文 | 更新时间：2026-03-18

- 点云数据去噪的自适应联合滤波方法
- An adaptive joint filtering method for point cloud denoising
- 智能科学与技术学报 2025年7卷第4期页码：484-492
- 作者机构：
  
  青岛理工大学机械与汽车工程学院，山东青岛 266525
- 作者简介：
  
  [ "曲大义（1973- ），男，博士，青岛理工大学机械与汽车工程学院教授，主要研究方向为车路协同及安全控制。" ]
  [ "韦良帅（1999- ），男，青岛理工大学机械与汽车工程学院硕士生，主要研究方向为车辆感知技术。" ]
  [ "王可栋（1986- ），男，青岛理工大学机械与汽车工程学院博士生，主要研究方向为人机共驾理论及技术。" ]
  [ "张智（1999- ），男，青岛理工大学机械与汽车工程学院硕士生，主要研究方向为运载系统动力学及协同控制。" ]
  [ "李文杰（2000- ），男，青岛理工大学机械与汽车工程学院硕士生，主要研究方向为车辆行为建模。" ]
- 基金信息：
  
  国家自然科学基金项目(52272311)
- DOI：10.11959/j.issn.2096-6652.202534
  中图分类号： TP391
- 收稿：2025-04-25，
  
  修回：2025-08-31，
  
  录用：2025-09-02，
  
  纸质出版：2025-12-15
- 稿件说明：
移动端阅览
曲大义,韦良帅,王可栋等.点云数据去噪的自适应联合滤波方法[J].智能科学与技术学报,2025,07(04):484-492.

QU Dayi,WEI Liangshuai,WANG Kedong,et al.An adaptive joint filtering method for point cloud denoising[J].Chinese Journal of Intelligent Science and Technology,2025,07(04):484-492.
曲大义,韦良帅,王可栋等.点云数据去噪的自适应联合滤波方法[J].智能科学与技术学报,2025,07(04):484-492. DOI： 10.11959/j.issn.2096-6652.202534.

QU Dayi,WEI Liangshuai,WANG Kedong,et al.An adaptive joint filtering method for point cloud denoising[J].Chinese Journal of Intelligent Science and Technology,2025,07(04):484-492. DOI： 10.11959/j.issn.2096-6652.202534.

摘要

针对恶劣天气条件下激光雷达采集的点云数据噪声严重、传统去噪方法精度低的问题，提出一种基于局部特征与空间距离关系的自适应联合滤波方法。首先依据雪花噪声的特征设定强度阈值，用于区分潜在的噪声点与有效点，随后利用对数正态分布对雪花噪声的分布规律进行拟合，将雪花噪声区域分为3种类型，并结合不同区域噪声点云的特征差异，分别设计对应的去噪策略。其中，高密度区域采用改进后的DSOR进行去噪，将点的强度信息引入阈值计算，使算法能够综合考虑空间结构与强度特性；在低密度区域，算法根据点的局部几何特征和邻域密度信息设定动态阈值，对孤立噪声进行筛选与去除，最后将高、低密度区域滤波后的点云与无噪声区域的点云进行融合，得到完整的去噪点云。实验结果表明，自适应联合滤波方法在精确率较DSOR提升5.16%的情况下，召回率提升约3.29%，有效减少了噪声点的漏检情况，与引入反射强度的DDIOR相比，该方法在保持较高精确率的同时进一步增强了噪声点识别能力，能够在不同交通场景中实现更稳定的去噪效果。

Abstract

To address the problem of severe noise in LiDAR point cloud data collected under adverse weather conditions and the low accuracy of traditional denoising methods

an adaptive joint filtering method based on local features and spatial distance relationships is proposed. First

an intensity threshold is set based on the characteristics of snowflake noise to distinguish potential noise points from valid points. Then

the spatial distribution of snowflake noise is modeled using a log-normal distribution

dividing the noise regions into three types. Corresponding denoising strategies are designed according to the characteristics of noise points in different regions. In high-density regions

an improved DSOR algorithm is applied

incorporating the intensity information of points into the threshold calculation

enabling the algorithm to consider both spatial structure and intensity features. In low-density regions

dynamic thresholds are set based on the local geometric features and neighborhood density of points to filter and remove isolated noise points. Finally

the filtered point clouds from high- and low-density regions are merged with the point cloud from noise-free regions to obtain the complete denoised point cloud. Experimental results show that the adaptive joint filtering method improves precision by 5.16% and recall by approximately 3.29% compared to DSOR

thereby effectively reducing the number of missed noise points. Compared with DDIOR

which also incorporates intensity information

the proposed method maintains a high precision while further enhancing the ability to identify noise points

achieving more stable denoising performance across different traffic scenarios.

关键词

Keywords

references

程川, 宋春华, 王鹏. 车载激光雷达发展研究综述[J]. 装备制造技术, 2022(5): 247-251.

CHENG C, SONG C H, WANG P. Review on the development of vehicle-borne lidar[J]. Equipment Manufacturing Technology, 2022(5): 247-251.

田永林, 沈宇, 李强, 等. 平行点云: 虚实互动的点云生成与三维模型进化方法[J]. 自动化学报, 2020, 46(12): 2572-2582.

TIAN Y L, SHEN Y, LI Q, et al. Parallel point clouds: point clouds generation and 3D model evolution via virtual-real interaction[J ] . Acta Automatica Sinica, 2020, 46(12): 2572-2582.

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(1): 7-31.

HUANG Z, WANG Y C, LI D Y. A survey of 3D object detection algorithms[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(1): 7-31.

BIJELIC M, GRUBER T, MANNAN F, et al. Seeing through fog without seeing fog: deep multimodal sensor fusion in unseen adverse weather[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2020: 11679-11689.

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(5): 577-595.

XIAO J, SHI G T. Three-dimensional point cloud denoising[J]. Journal of University of Chinese Academy of Sciences, 2023, 40(5): 577-595.

李仁忠, 杨曼, 冉媛, 等. 基于方法库的点云去噪与精简算法[J]. 激光与光电子学进展, 2018, 55(1): 251-257.

LI R Z, YANG M, RAN Y, et al. Point cloud denoising and simplification algorithm based on method library[J]. Laser & Optoelectronics Progress, 2018, 55(1): 251-257.

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 Z Y, CHEN Y P, SU Y. Point cloud denoising algorithm based on distance threshold and density distinction[J]. Tool Engineering, 2024, 58(10): 147-154.

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 T Y, MA B. Smooth denoising method for multi-scale point cloud noise[J]. Applied Laser, 2024, 44(12): 148-157.

GE C P, ZHAO D, WANG R, 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.

ZHAO Z, ZHOU W L, LIANG D H, et al. Denoising method based on improved DBSCAN for lidar point cloud[J]. IEEE Access, 2024, 12: 137656-137666.

CATTAI T, DELFINO A, SCARANO G, et al. VIPDA: a visually driven point cloud denoising algorithm based on anisotropic point cloud filtering[J]. Frontiers in Signal Processing, 2022, 2: 842570.

赵涵, 刘永生, 赵德鹏, 等. 基于混合滤波的点云去噪算法研究[J]. 应用激光, 2023, 43(9): 147-155.

ZHAO H, LIU Y S, ZHAO D P, et al. Research on point cloud denoising algorithm based on hybrid filtering[J]. Applied Laser, 2023, 43(9): 147-155.

CHARRON N, PHILLIPS S, WASLANDER S L. De-noising of lidar point clouds corrupted by snowfall[C]//Proceedings of the 2018 15th Conference on Computer and Robot Vision (CRV). Piscataway: IEEE Press, 2018: 254-261.

KURUP A, BOS J. Dsor: a scalable statistical filter for removing falling snow from lidar point clouds in severe winter weather[EB]. arXiv preprint, 2021, arXiv:2109.07078.

PARK J I, PARK J, KIM K S. Fast and accurate desnowing algorithm for LiDAR point clouds[J]. IEEE Access, 2020, 8: 160202-160212.

WANG W Q, YOU X, CHEN L Y, et al. A scalable and accurate de-snowing algorithm for LiDAR point clouds in winter[J]. Remote Sensing, 2022, 14(6): 1468.

武雨田, 李擎, 孙文蔚, 等. 复杂天气下车载激光点云目标检测方法综述[J]. 工程科学学报, 2025, 47(5): 1081-1093.

WU Y T, LI Q, SUN W W, et al. Overview of object detection methods based on LiDAR point cloud under adverse weather conditions[J]. Chinese Journal of Engineering, 2025, 47(5): 1081-1093.

RONNBACK S, WERNERSSON A. On filtering of laser range data in snowfall[C]//Proceedings of the 2008 4th International IEEE Conference Intelligent Systems. Piscataway: IEEE Press, 2008: 17-33-17-39.

SIANO D B. The log-normal distribution function[J]. Journal of Chemical Education, 1972, 49(11): 755.

GRAMACKI A. Kernel density estimation[M]//Nonparametric Kernel Density Estimation and Its Computational Aspects. Cham: Springer International Publishing, 2017: 25-62.

HUANG H, YAN X, YANG J, et al. Lidsor: a filter for removing rain and snow noise points from lidar point clouds in rainy and snowy weather[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2023, XLVIII-1/W2-2023: 733-740.

GEIGER A, LENZ P, URTASUN R. Are we ready for autonomous driving? The KITTI vision benchmark suite[C]//Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2012: 3354-3361.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

Cerberus：基于深度学习的跨站社交网络机器人检测系统