散乱点云局部形貌标架量化及特征识别方法

doi:10.3969/j.issn.1004-132X.2020.19.009

摘要/Abstract

摘要： 针对散乱点云特征识别结果存在噪声及特征遗漏的问题，提出一种基于曲面局部形貌标架的点云特征识别方法。基于点云局部中轴对样点的隔离作用，剔除样点欧氏邻域内的非测地邻域点，为曲面构造优化的局部样本模型。析取局部离散样本中的准共法截线点对集合，构造散乱点云的局部形貌标架。基于标架夹角的差异性，对曲面样本形貌进行量化分析，区分平滑、边界、棱边及尖角等特征区域，实现对中心样点属性的稳健判别。实验结果表明，该方法适用于不同采样密度的点云，可显著降低点云特征识别结果中的噪声点规模，且能有效减少特征遗漏现象。

关键词: 特征识别, 散乱点云, Voronoi图, 局部形貌标架

Abstract: A method for identifying the features of point cloud was proposed based on local topography frame of the surfaces to solve the problems of noise points and feature omissions in the recognition results of the existing methods. Based on the isolation effect of local central axis of the point cloud on sample points, the non-geodedic neighborhood points in Euclidean neighborhood of the sample points were eliminated, and the local sample model was optimized for the surface construction. The set of quasi-common normal section line point pairs in the local discrete samples was extracted to construct the local topography frame of scattering point cloud. Based on the differences of the included angles of the frame, the surface sample shape was quantitatively analyzed, and the feature areas such as smoothness, boundary, edge and sharp corner were distinguished, so as to realize the robust judgment of the attributes of the center sample point. Experimental results show that the method applies to point cloud with different sampling densities and may significantly reduce the scale of noise points in the point cloud feature identification results and feature omissions.

Key words: feature recognition, scattering point cloud, Voronoi diagram, local topography frame

中图分类号:

TP391.72

孙殿柱1;沈江华1;贾宗福1;李延瑞2;林伟1. 散乱点云局部形貌标架量化及特征识别方法[J]. 中国机械工程, DOI: 10.3969/j.issn.1004-132X.2020.19.009.

SUN Dianzhu1;SHEN Jianghua1;JIA Zongfu1;LI Yanrui2;LIN Wei1.

Scattering Point Cloud Local Topography Frame Quantization and Feature Recognition Method

[J]. China Mechanical Engineering, DOI: 10.3969/j.issn.1004-132X.2020.19.009.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.cmemo.org.cn/CN/10.3969/j.issn.1004-132X.2020.19.009

http://www.cmemo.org.cn/CN/Y2020/V31/I19/2332

参考文献

［1］林洪彬,刘彬,张玉存.基于多尺度张量分解的点云结构特征提取［J］.中国机械工程,2012,23(15):1833-1839.

LIN Hongbin, LIU Bin, ZHANG Yucun. Structural Feature Extraction from Point Clouds Based on Multi-scale Tensor Decomposition ［J］. China Mechanical Engineering, 2012,23(15):1833-1839.

［2］王丽辉,袁保宗. 三维散乱点云模型的特征点检测［J］.信号处理,2011,27(6):932-938.

WANG Lihui, YUAN Baozong. Feature Point Detection of 3D Scattered Point Cloud Model［J］. Signal Processing, 2011, 27(6):932-938.

［3］庞旭芳,庞明勇,肖春霞.点云模型谷脊特征的提取与增强算法［J］.自动化学报,2010,36(8):1073-1083.

PANG Xufang, PANG Mingyong, XIAO Chunxia. An Algorithm for Extracting and Enhancing Valley-ridge Features from Point Sets［J］. Acta Automatica Sinica, 2010, 36(8):1073-1083.

［4］PAULY M, KEISER R, GROSS M. Multi-scale Feature Extraction on Point-sampled Surfaces［J］. Computer Graphics Forum，2003, 22(3):281-289.

［5］GUMHOLD S, WANG X, MACLEOD R. FeatureExtraction from Point Clouds［C］∥ Proceedings of the 10th International Meshing Roundtable. Newport Beach, 2001:293-305.

［6］李延瑞,孙殿柱,张英杰,等.曲面边界样点逆向均值漂移识别［J］.计算机集成制造系统,2015,21(7):1719-1724.

LI Yanrui, SUN Dianzhu, ZHANG Yingjie, et al. Reverse Mean Shift Detection Algorithm for Boundary Points of Surface［J］. Computer Integrated Manufacturing Systems, 2015, 21(7):1719-1724.

［7］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.

［8］孙殿柱,范志先,李延瑞,等.散乱数据点云型面特征分析算法的研究与应用［J］.机械工程学报,2007,43(6):133-136.

SUN Dianzhu, FAN Zhixian, LI Yanrui, et al. Research and Application of Surface Feature Analysis for Scatter Data Points［J］. Chinese Journal of Mechanical Engineering, 2007, 43(6):133-136.

［9］刘庆,章光,陈西江. 融合改进场力和判定准则的点云特征规则化［J］.中国激光,2019,46(4):200-209.

LIU Qing, ZHANG Guang, CHEN Xijiang. Point Cloud Feature Regularization Based on Fusion of Improved Field Force and Judging Criterion［J］. Chinese Journal of Lasers, 2019,46(4):200-209.

［10］WEBER C, HAHMANN S, HAGEN H, et al. Sharp Feature Preserving MLS Surface Reconstruction Based on Local Feature Line Approximations［J］. Graphical Models, 2012, 74(6):335-345.

［11］BAZAZIAN D, CASAS J, RUIZ-HIDALGO J. Segmentation-based Multi-scale Edge Extraction to Measure the Persistence of Features in Unorganized Point Clouds［C］∥ 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. Porto, 2017:317-325.

［12］史皓良,吴禄慎,余喆琦,等.散乱点云数据特征信息提取算法［J］.计算机工程,2017,43(8):279-283.

SHI Haoliang, WU Lushen, YU Zheqi, et al. Algorithm for Feature Information Extraction from Scattered Point Cloud Data［J］. Computer Engineering, 2017,43(8):279-283.

［13］O’ROURKE J. Computational Geometry in C ［M］.2nd ed. Cambridge:Cambridge University Press, 1998:155-192.

［14］ALIEZ P,COHEN-STEINER D, TONG Y, et al. Voronoi-based Variational Reconstruction of Unoriented Point Sets［C］∥ Eurographics Symposium on Geometry Processing. Barcelona, 2007:39-48.

［15］MRIGOT Q, OVSJANIKOV M, GUIBAS L J.Voronoi-based Curvature and Feature Estimation from Point Clouds［J］. IEEE Transactions on Visualization and Computer Graphics, 2010, 17(6):743-756.

［16］AMENTA N, CHOI S, DEY T K, et al. A Simple Algorithm for Homeomorphic Surface Reconstruction［J］. International Journal of Computational Geometry & Applications, 2002,12(1/2):125-141.

［17］GROSS M, FOSTER H. Point-based Graphics［M］. San Francisco:Morgan Kaufmann, 2007.

［18］刘迎,王朝阳,高楠,等.特征提取的点云自适应精简［J］.光学精密工程,2017,25(1):245-254.

LIU Ying, WANG Chaoyang, GAO Nan, et al. Point Cloud Adaptive Simplification of Feature Extraction［J］. Optics and Precision Engineering, 2017, 25(1):245-254.

[1]	张宇航, 孙玉文, 徐金亭. 航空发动机机匣加工特征的混合式分割识别算法[J]. 中国机械工程, 2023, 34(20): 2475-2481.
[2]	汤永锋, 路平, 刘斌, 江开勇, 颜丙功, 刘嘉伟, 韩伟, . 不同梯度变化方式的不规则多孔结构设计与力学性能分析[J]. 中国机械工程, 2022, 33(23): 2859-2866.
[3]	张生芳, 王国庆, 马付建, 刘宇, 杨大鹏, 沙智华. 基于改进图匹配的角盒类零件型腔加工特征自动识别[J]. 中国机械工程, 2022, 33(08): 921-928.
[4]	张胜文, 周曦, 李滨城, , 程德俊, , 陈文笛. 基于图像深度学习的零件加工特征信息提取方法[J]. 中国机械工程, 2022, 33(03): 348-355.
[5]	汪攀;张见明;韩磊;鞠传明;池宝涛. 基于子域分解的全六面体网格生成方法[J]. 中国机械工程, 2018, 29(03): 295-300.
[6]	董玉德1;米登斌1;陈明龙1;苏芳1;时晓蕾2;杨善文2;陶高周2. 基于三维几何特征的产品报价方法[J]. 中国机械工程, 2017, 28(22): 2738-2746.
[7]	张旭, 郑泽龙. 主动光立体标靶检测及其在工业机器人位姿测量中的应用[J]. 中国机械工程, 2016, 27(19): 2594-2601.
[8]	李庆, 张龙, 黄志高, 周华民. 面向CAD/CAE集成的注塑模冷却系统特征识别[J]. 中国机械工程, 2013, 24(08): 1042-1046.
[9]	陈志杨1, 喻谷鸣1, 张引2. 基于样条链（环）的CAD模型过渡特征识别与抑制 [J]. 中国机械工程, 2011, 22(22): 2707-2711.
[10]	田富君, 田锡天, 耿俊浩, 李洲洋, 张振明. 基于轻量化模型的加工特征识别技术 [J]. 中国机械工程, 2010, 21(18): 2212-2217.
[11]	闫海兵, 李迎光, 韩雄. 飞机结构件拓扑不固定特征的自动识别 [J]. 中国机械工程, 2010, 21(13): 1567-1571.
[12]	梁新合, 梁晋, 郭成, 曹巨明. 基于自适应最优邻域的散乱点云降噪技术研究 [J]. 中国机械工程, 2010, 21(06): 639-643.
[13]	李伟平, 郑琳, 龚志辉. 基于建模过程的加工特征识别 [J]. 中国机械工程, 2010, 21(05): 556-562.
[14]	孙殿柱, 朱昌志, 范志先, 李延瑞. 基于型面特征的三维散乱点云精简算法 [J]. J4, 2009, 20(23): 2840-2843.
[15]	李伟平;谷正气;何忆斌;. 基于中面的注塑产品特征识别[J]. J4, 2009, 20(19): 0-2392.