| 非均匀分布三维点云自适应参数混合滤波去噪方法 |
| Mixed filter method based on adaptive parameters for inhomogeneous densities point clouds |
| 投稿时间：2025-05-21 修订日期：2025-06-18 |
| HTML 查看/发表评论 下载PDF阅读器 |
| 中文摘要: |
| 智能制造复杂构件材质多样且几何形状复杂导致边角部位获取的三维点云稀疏，使得复杂部件的三维点云密度分布不均匀。为去除复杂构件三维点云的多种噪声，研究了基于点云密度的自适应参数统计滤波和半径滤波混合的去噪方法。首先对分割的三维点云基于密度相似性进行体素合并，基于合并体素规模指数确定半径滤波最小点数，基于邻域平均距离确定搜索半径，基于缩放系数确定统计滤波的标准差。利用所提自适应参数混合滤波方法对经典三维点云模型去噪进行实验验证。结果表明去噪后三维点云边缘保留率远远高于固定参数的滤波结果，有效保留了点云稀疏区域的细节信息，噪声去除率也明显提高。对不同噪声等级三维点云去噪结果表明该方法具有很好的鲁棒性。该方法为智能制造在线检测提供了技术保证。 |
| 英文摘要: |
| The diversity of materials and complex geometric shapes of intelligent manufacturing components lead to sparse three-dimensional (3D) point clouds at edge regions, resulting in non-uniform density distribution across complex mechanical parts. This study proposes a hybrid filtering method integrating density-adaptive statistical outlier removal (SOR) and radius outlier removal (ROR) to address multiple noise types in complex component point clouds. The methodology begins with voxel merging of segmented point clouds based on density similarity, establishes minimum neighborhood points for ROR using merged voxel size exponents, determines search radius through neighborhood average distances, and calculates SOR standard deviations using scaling coefficients. Experimental validation using classical 3D point cloud models demonstrates that the edge retention of post-processed point clouds significantly exceed those achieved by fixed-parameter filtering methods, while effectively preserving detail information in sparse regions and the noise removal rate is also improved. Robustness tests conducted under varying noise levels confirm consistent performance across different noise intensities. This method establishes a technical foundation for online inspection in intelligent manufacturing systems requiring high-fidelity geometric reconstruction. |
|
| 中文关键词: 不均匀三维点云 混合滤波 自适应参数 复杂构件 |
| 英文关键词:inhomogeneous densities point clouds mixed filter adaptive parameters complex component |
| 基金项目:国家重点研发计划项目(2023YFF0722900) |
| DOI： |
| 引用本文： |
| 关闭 |
