基于体积积分不变量的散乱点云数据特征点提取

赵双玲; 李奇敏; 蒋恒恒; 叶仲泉

基于体积积分不变量的散乱点云数据特征点提取

1.
重庆大学数学与统计学院,重庆 400030;
2.
重庆大学机械工程学院,重庆 400030

基金项目:

国家自然科学基金项目(50905190)资助

详细信息

作者简介:
赵双玲(1987-)，硕士，研究方向为计算机图形学及计算机辅助设计，zhaoshuangling815@163.com;李奇敏(联系人)，副教授，博士，qim-li@163.com

赵双玲(1987-)，硕士，研究方向为计算机图形学及计算机辅助设计，zhaoshuangling815@163.com;李奇敏(联系人)，副教授，博士，qim-li@163.com

计量
- 文章访问数: 286
- HTML全文浏览量: 25
- PDF下载量: 11
- 被引次数: 0
出版历程
- 收稿日期: 2011-05-07
- 刊出日期: 2015-06-10

Extracting Feature Points for Scattered Points Based on Volume Integral Invariant

1.
School of Mathematics and Statistics,Chongqing University,Chongqing 400030;
2.
School of Mechanical Engineering,Chongqing University,Chongqing 400030

摘要

摘要: 针对积分不变量不依赖网格拓扑结构的特性及体积积分不变量与平均曲率的内在联系,提出了一种基于平均曲率及体积积分不变量的散乱点云特征点提取方法。该算法采用4DShepard曲面估算点云曲率获得体积积分不变量,并基于体积积分不变量通过K-Means分类方法提取点云特征点。该算法只与点的个数和位置有关,实验结果表明,该算法不仅可以较快地提取特征点,而且表达点云边界特征点比较精确。
- 特征点提取 /
- 点云曲率 /
- 积分不变量 /
- K-Means
Abstract: Based on the property of the integral invariant irrelevant to the meshes' topology and the inner relationship between the volume integral invariant and the mean-curvature,a method was proposed to extract the feature points from scattered point sets based on the mean-curvature and the volume integral invariant.The algorithm in the present method used the global 4D Shepard surface to estimate the curvature of each point in the point cloud and it was only related to the numbers and the operations of the points cloud.Then the volume integral invariant was calculated by the given formula,and the feature points were extracted through the K-Means clustering algorithm.The experiments show that this algorithm has higher computing efficiency,and can express the boundary feature of the clouds more precisely.
- feature point extraction /
- curvature of point cloud /
- integral invariant /
- K-Means

HTML全文

参考文献(16)

[1]	孟娜. 基于激光扫描点云的数据处理技术研究[D].济南:山东大学,2009.
[2]	Yongtae J,Kuiwon C. Automated feature-based registration for reverse engineering of human models[J].Journal of Mechani cal Science and Technology,2005,(12):2213-2223.
[3]	Rabbani T,Dijkman S. An integrated approach for modeling and global registration of point clouds[J].Journal of Photogram-metry and Remote Sensing,2007,(61):355-370.
[4]	Yang M,Lee E. Segmentation of measured data using a paramet-ric quatric surface approximation[J].Computered Aided De-sign,1999,(07):449-457.
[5]	Woo H,Kang E,Wang Sem-yung. A new segmentation method for point cloud data[J].International Journal of Ma-chine Tools and nanufacture,2002,(02):167-168.
[6]	吕震,柯映林,孙庆. 反求工程中过渡曲面特征提取算法研究[J].计算机集成制造系统-CIMS,2003,(02):154-157.
[7]	Huang J,Menq C H. Automatic data segmentation for geometric feature extraction from unorganized 3-D coordinate points[J].IEEE Transactions on Robotics and Automation,2001,(03):268-279.
[8]	马骊溟,徐毅,李泽湘. 基于高斯曲率极值点的散乱点云数据特征点提取[J].系统仿真学报,2008,(09):2341-2344.
[9]	柯映林,陈曦. 基于4DShepard曲面的点云曲率估算[J].浙江大学学报,2005,(06):761-764.
[10]	Duda R O,Hart P E,Stork D G. Pattern Classification[M].Wiley-interscience,2001.
[11]	Pottmann H,Wallner J,Huang Q X,Yang Y L. Integral invari-ants for robust geometry,processing[J].Computer Aided Geo-metric Design,2009,(01):37-60.
[12]	Manay S,Yezzi A J,Hong B W,Soatto S. Integral invariant sig-natures[A].2004.87-99.
[13]	Gelfand N,Mitra N J,Guibas L J,Pottmann H. Robust global registration[A].2005.197-206.
[14]	Zhe Bian,Ruofeng Tong. Feature-preserving mesh denoising based on verteces classification[J].Computer Aided Geometric Design,2011.50-64.
[15]	Yang Y L,Lai Y K,Hu S M,Pottmann H. Robust principal curva-tures on multiple scales[A].2006.223-226.
[16]	柯映林,范树迁. 基于点云的边界特征直接提取技术[J].机械工程学报,2004,(09):116-120.