基于PCPNET的点云特征线提取算法

doi:10.11896/jsjkx.210800017

摘要/Abstract

摘要： 特征线提取是几何模型处理的基础操作,其对三维模型的表达具有重要意义。文中基于PCPNET提出了一种对噪声和非均匀采样具有鲁棒性的曲率值和主曲率方向的计算方法,并在其基础上提出了一种特征线提取算法。该算法利用加权二次曲线拟合局部曲率分布,并通过判定在最大主曲率方向上与二次曲线极值点的距离来实现脊谷特征点的识别;最后,通过建立细化后潜在特征点的最小生成树(MST)实现特征点的连接,完成特征线的提取。实验结果表明,所提算法能够利用PCPNET对点云曲率和主曲率方向信息进行较为准确的估计,并且根据所提出的特征点识别方法可以弥补传统采用简单阈值截断导致平坦区域特征线线无法正常提取的缺陷,最终能准确、完整地从清洁点云和噪声点云中提取特征线。

关键词: 点云, 特征线, PCPNET, 曲率

Abstract: Feature line extraction is the basic operation of geometric model processing,which is of great significance to the expression of 3D model.Based on PCPNET,a calculation method of curvature value and principal curvature direction which is robust to noise and non-uniform sampling is proposed,and a feature line extraction algorithm is proposed.The proposed algorithm uses the weighted quadratic curve to fit the local curvature distribution,and realizes the recognition of ridge and valley feature points by determining the distance from the extreme point of the quadratic curve in the direction of maximum principal curvature.Finally,the minimum spanning tree(MST) of the refined potential feature points is established to connect the feature points and complete the feature line extraction.Experimental results show that the proposed algorithm can use PCPNET to accurately estimate the curvature and principal curvature direction information of point cloud,and according to the proposed feature point recognition method,it can overcome the defect that the traditional simple threshold truncation can not extract the feature lines of flat area normally,and finally extract the feature lines from clean point cloud and noise point cloud accurately and completely.

Key words: Point cloud, Characteristic line, PCPNET, Curvature

中图分类号:

TP391

喻孟娟, 聂建辉. 基于PCPNET的点云特征线提取算法[J]. 计算机科学, 2022, 49(11A): 210800017-6. https://doi.org/10.11896/jsjkx.210800017

YU Meng-juan, NIE Jian-hui. Point Cloud Feature Line Extraction Algorithm Based on PCPNET[J]. Computer Science, 2022, 49(11A): 210800017-6. https://doi.org/10.11896/jsjkx.210800017

参考文献

[1]GERHARD H B,RUWEN S,REINHARD K.Deteting holes in point set surfaces[J].Journal of WSCG,2006,14(1):1213-1220.
[2]ATTENE M,FALCIDIENO B,ROSSIGNAC J,et al.Sharpen-bend:Recovering curved sharp edges in triangle meshs produced by feature-insensitive sampling[J].IEEE Trans.Vis.Comput.Graph,2005,11(2):181-192.
[3]SCHEIDEGGER C E,FLEISHMAN S,SILVAC T.Triangulating point set surfaces with bounded error[C]//Proceedings of Symposium on Geometry Processing.2005:63-72.
[4]ALEX M,BEHR J,COHEN O D,et al.Computing and rende-ring point set surfaces[J].IEEE Trans.Vis.Comput.Graph,2003,9(1):3-15.
[5]FLEISHMAN S,COHEN O D,SILVA C T.Robust movingleast-squares fitting with sharp features[J].ACM Trans.Graph,2005,24(3):544-552.
[6]GARLAND M,HECKBERT P S.Surface simplification usingquadric error metrics[C]//Proceedings of ACM SIGGRAPH.1997:209-216.
[7]JONES T R,DURAND F,DESBRUN M.Non-iterative,feature preserving mesh smoothing[J].ACM Trans.Graph,2003,22(3):943-949.
[8]DESBRUN M,MEYER M,SCHRODER P etal.Implicit fairing of irregular meshes using diffusion and curvature flow[C]//Proceedings of ACM SIGGRAPH.1999:317-324.
[9]HOPPE H.New quadric metric for simplifying meshes with appearance attributes[C]//Proceedings of IEEE Visualization.1999:59-66.
[10]GUMHOLD S,WANG X.Mcleod R:Feature extraction from point clouds[C]//Proceedings of the 10th Inter national Me-shing Roundtable.Los Alamitos:IEEE Computer Society Press,2001,293-305.
[11]DEMARSIN K,VANDERSTRAETEN D,VOLODINE T,et al.Detection of closed sharp edges in point clouds using normal estimation and graph theory[J].Computer Aided Design,2007,39(4):276-283.
[12]PAULY M,KEISER R,GROSS M.Multi-scale feature extraction on point-sampled surfaces[J].Computer Graphic Forum.2003,22(3),281-289.
[13]LI B,SCHNABEL R,KLEIN R,et al.Robust normal estimation for point clouds with sharp features [J].Computers & Gra-phics,2010,34(1):94-106.
[14]WANG X C,LIU X P,LI B J,et al.Feature detection on point cloud via local reconstruct- ion[J].Journal of Computer Aided Design & Computer Graphics,2013,25(5):659-665.
[15]PANG X F,PANG M Y,XIAO C X.An algorithm for extracting and enhancing valley-ridge features from point sets[J].Acta Automatica Sinica,2010,36(8):1073-1083.
[16]KIM S K,KIM C H.Finding ridges and valleys in a discrete surface using a modified MLS projection [J].Computer Aided Design,2005,37(14),1533-1542.
[17]KIM S K.Extraction of ridge and valley lines from unorganized points[J].Multimed.Tools Appl,2013,63(1),265-279.
[18]WEBER C,HAHMANN S,HAGEN H,et al.Sharp featurepreserving MLS surface reconstruction based on local feature line approximations[J].Graphic Models,2012,74(6),335-345.
[19]QUENTIN M,MAKS O,LEONIDAS G.Voronoi-based curvature and feature estimation from point clouds[J].IEEE Trans.on Visualization and Computer Graphics,2011:17(6):743-756.
[20]DANIELS J Ⅱ,HA L K,OCHOTTA T et al.Spline-based feature curves from point-sampled geometry[J].The Visual Computer,2008,24(6),449-462.
[21]ENKHBAYAR A,YUTA M,KATSUTUGU M et al.Feature line extraction from unorganized noisy point clouds using truncated fourier series[J].The Visual Computer,2013,29(6),617-626.
[22]EVANGELOS K,DEREK N,PATRICIO S et al.Extract lines of curvature from noisy point clouds[J].Comoputer-Aided Design,2009,41(4):282-292.
[23]PARK M K,LEE S J,LEE K H.Multi-scale tensor voting for feature extraction from unstructured point clouds[J].Graphical Models,2012,74(4):197-208.
[24]WEBER C,HAHMANN S,HAGEN H.Sharp feature detection in point clouds[C]//Proceedings of the Shape Modeling International Conference.Los Alamitos:IEEE Computer Society Press,2010,175-186.
[25]GUERRERO P,KLEIMAN Y,OVSJANIKOV M.PCPNET:Learning Local Shape Properties from Raw Point Clouds[J].Computer Graphics Forum,2018,2(37):75-85.
[26]PAULY M,GROSS M,KOBBELTL P.Efficient simplificationof point-sampled surfaces[C]//Proceedings of IEEE Visualization.Los Alamitos:IEEE Computer Society Press,2002:163-170.
[27]YAGOU H,OHTAKE Y,BELYAEV A.Mesh smoothing via mean and median filtering applied to face normals[C]//Procee-dings of Geometric Modeling and Processing-Theory and Applications.2002:124-135.
[28]CHARLES R Q,SU H,KAICHUM M,et al.Pointnet:Deeplearning on point sets for 3D classification and segmentation[C]//CVPR.2017:77-85.
[29]NIE J H.Extracting feature lines from point clouds based on smooth shrink and iterative thinning[J].Graphical Models,2016,84:38-49.

相关文章 15

[1]	杨文坤, 原晓佩, 陈小锋, 郭睿. 三维激光雷达点云空间多特征分割 Spatial Multi-feature Segmentation of 3D Lidar Point Cloud 计算机科学, 2022, 49(8): 143-149. https://doi.org/10.11896/jsjkx.210300275
[2]	李宗民, 张玉鹏, 刘玉杰, 李华. 基于可变形图卷积的点云表征学习 Deformable Graph Convolutional Networks Based Point Cloud Representation Learning 计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023
[3]	黄璞, 沈阳阳, 杜旭然, 杨章静. 基于局部约束特征线表示的人脸识别 Face Recognition Based on Locality Constrained Feature Line Representation 计算机科学, 2022, 49(6A): 429-433. https://doi.org/10.11896/jsjkx.210300169
[4]	封雷, 朱登明, 李兆歆, 王兆其. 一种基于遮罩的稀疏点云滤波算法 Sparse Point Cloud Filtering Algorithm Based on Mask 计算机科学, 2022, 49(5): 25-32. https://doi.org/10.11896/jsjkx.210600129
[5]	任飞, 常青玲, 刘兴林, 杨鑫, 李敏华, 崔岩. 基于点云的室内结构三维重建综述 Overview of 3D Reconstruction of Indoor Structures Based on Point Clouds 计算机科学, 2022, 49(11A): 211000176-11. https://doi.org/10.11896/jsjkx.211000176
[6]	车爱博, 张辉, 李晨, 王耀南. 基于点云数据的交通环境下单阶段三维目标检测方法 Single-stage 3D Object Detector in Traffic Environment Based on Point Cloud Data 计算机科学, 2022, 49(11A): 210900079-6. https://doi.org/10.11896/jsjkx.210900079
[7]	赵新灿, 常寒星, 金仁标. 3D点云形状补全GAN 3D Point Cloud Shape Completion GAN 计算机科学, 2021, 48(4): 192-196. https://doi.org/10.11896/jsjkx.200100048
[8]	徐新黎, 肖云月, 龙海霞, 杨旭华, 毛剑飞. 基于矩阵分解的属性网络嵌入和社区发现算法 Attributed Network Embedding Based on Matrix Factorization and Community Detection 计算机科学, 2021, 48(12): 204-211. https://doi.org/10.11896/jsjkx.210300060
[9]	姚楠, 张征. 基于三维图像的疤痕面积计算 Scar Area Calculation Based on 3D Image 计算机科学, 2021, 48(11A): 308-313. https://doi.org/10.11896/jsjkx.201100044
[10]	朱威, 绳荣金, 汤如, 何德峰. 基于动态图卷积和空间金字塔池化的点云深度学习网络 Point Cloud Deep Learning Network Based on Dynamic Graph Convolution and Spatial Pyramid Pooling 计算机科学, 2020, 47(7): 192-198. https://doi.org/10.11896/jsjkx.190700180
[11]	曾俊飞,杨海清,吴浩. 面向三维重建的自适应列文伯格-马夸尔特点云配准方法 Adaptive Levenberg-Marquardt Cloud Registration Method for 3D Reconstruction 计算机科学, 2020, 47(3): 137-142. https://doi.org/10.11896/jsjkx.190200261
[12]	史文凯, 张昭晨, 喻孟娟, 吴瑞, 聂建辉. 基于特征检测与深度特征描述的点云粗对齐算法 Point Cloud Coarse Alignment Algorithm Based on Feature Detection and Depth FeatureDescription 计算机科学, 2020, 47(12): 252-257. https://doi.org/10.11896/jsjkx.191000069
[13]	李健, 杨祥如, 何斌. 基于深度学习的几何特征匹配方法 Geometric Features Matching with Deep Learning 计算机科学, 2019, 46(7): 274-279. https://doi.org/10.11896/j.issn.1002-137X.2019.07.042
[14]	孟文权, 武利生. 基于深度特征的足底曲面三角剖分重构 Triangulation Reconstruction of Plantar Surface Based on Depth Feature 计算机科学, 2019, 46(6A): 205-207.
[15]	吴飞, 赵新灿, 展鹏磊, 关凌. 自适应邻域选择的FPFH特征提取算法 FPFH Feature Extraction Algorithm Based on Adaptive Neighborhood Selection 计算机科学, 2019, 46(2): 266-270. https://doi.org/10.11896/j.issn.1002-137X.2019.02.041

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed