Structural Feature Extraction from Point Clouds Based on Multi-scale Tensor Decomposition

China Mechanical Engineering ›› 2012, Vol. 23 ›› Issue (15): 1833-1839.

Previous Articles Next Articles

Structural Feature Extraction from Point Clouds Based on Multi-scale Tensor Decomposition

Lin Hongbin;Liu Bin;Zhang Yucun

Key Laboratory of Measurement Technology and Instrumentation of Hebei Province,Yanshan University,Qinhuangdao,Hebei,066004

Online:2012-08-10 Published:2012-09-05
Supported by:

National Science and Technology Major Project ( No. 2011ZX04002-101);

Hebei Provincial Natural Science Foundation of China（No. E2012203002）;

Hebei Provincial S&T Research and Development Program of China（No. 10212152）;
S&T Research and Development Program of Qinhuangdao（No. 201001A077）;

基于多尺度张量分解的点云结构特征提取

林洪彬;刘彬;张玉存

燕山大学河北省测试计量技术与仪器重点实验室,秦皇岛,066004

基金资助:
国家科技重大专项(2011ZX04002-101)；河北省自然科学基金资助项目(E2012203002)；河北省科学技术研究与发展计划资助项目(10212152)；秦皇岛市科学技术研究与发展计划资助项目(201001A077)；河北省重点实验室开放基金资助项目
National Science and Technology Major Project ( No. 2011ZX04002-101);

Hebei Provincial Natural Science Foundation of China（No. E2012203002）;

Hebei Provincial S&T Research and Development Program of China（No. 10212152）;
S&T Research and Development Program of Qinhuangdao（No. 201001A077）;

Abstract

Abstract:

To solve the conflicts between the ability of weak feature extraction and noise resistency of traditional algorithms, a new feature extraction algorithm was proposed based on multi-scale tensor decomposition. Firstly, feature saliency encoding was defined based on the singular value decomposition of tensor matrix. Secondly, normal(tangential) consistent measure was constructed and used to determine the maxmuim scale combined with Romanovskii criterion. The reliability of the feature reconizing algorithm is improved. Finaly, the feature lines were constructed using minimal spanning forest. Expremental results reveal the weak feature extraction and noise resistency abilities of the method.

Key words: multi-scale analysis;tensor decomposition, point cloud;feature extraction

摘要：

针对传统点云处理算法弱特征提取与抗噪声能力之间的矛盾,提出了一种基于多尺度张量分解的点云结构特征提取算法。首先,利用张量矩阵奇异值分解进行采样点特征显著性编码;然后,将法向(切向)一致性测度与罗曼诺夫斯基准则相结合求取采样点最优邻域,以提高采样点特征识别的可靠性;最后,利用最小生成森林进行特征点遍历,构建点云结构特征曲线。实验结果表明,该算法可以实现复杂点云结构特征的有效识别。

关键词: 多尺度分析, 张量分解, 点云, 特征提取

CLC Number:

TN957.52

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

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.

References

[1]Gross M, Pfister H. Point- based Graphics[M] Burlington : Morgan Kaufmann, 2007.
[2]Kobbelt L, Botsch M. A Survey of Point-based Techniques in Computer Graphics [J]. Computers and Graphics,2004,28(6) :801-814.
[3]Gumhold S, Wang X, McLeod R. Feature Extraction from Point Clouds [C]//Proceedings of 10th International Meshing Roundtable. Newport Beach: John Chawner Pointwise, Inc. , 2001:1-10.
[4]Pauly M,Keiser R, Gross M. Multi-scale Feature Extraction on Point-Sampled Surfaces[J]. Eurographics, 2003,22 (3): 281-289.
[5]Lee I K. Curve Reconstruction from Unorganized Points[J]. Computer Aided Geometric Design, 2000,17(2) : 161-177.
[6]柯映林[1],范树迁[1].基于点云的边界特征直接提取技术[J].机械工程学报,2004,40(9):116-120.
[7]Jenke P,Wand M,Bokeloh M,et al. Bayesian Point Cloud Reconstruction[J]. Computer Graphics Forum,2009,25(3) :379-388.
[8]Joel D II, K H Linh, Tilo Ochotta, et al. Robust Smooth Feature Extraction from Point Clouds[C]//IEEE International Conference on Shape Modeling and Applications. Lyon, 2007 : 1-11.
[9]庞旭芳[1],庞明勇[2],肖春霞[3].点云模型谷脊特征的提取与增强算法[J].自动化学报,2010(8):1073-1083.
[10]Joel D II, Tilo Ochotta. Spline-based Feature Curves from Point-Sampled Geometry[J]. The Visual Computer, 2008, 24(6): 449-462.
[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]Liu Yu,Xiong Youlun. Automatic Segmentation of Unorganized Noisy Point Clouds Based on the Gaussian Map[J]. Computer Aided Design,2008, 40(5) : 576-594.
[13]Oztireli C,Guennebaud G,Gross M. Feature Preserving Point Set Surfaces Based on Non-linear Kernel Regression[J]. Computer Graphics Forum,2009,28(2):493-501.
[14]Guy G, Medioni G. Inference of Surfaces, 3D Curves, and Junctions from Sparse, Noisy, 3D Data [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997,19(11) : 1265-1277.

Structural Feature Extraction from Point Clouds Based on Multi-scale Tensor Decomposition

基于多尺度张量分解的点云结构特征提取

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 1

Recommended Articles

Metrics