A Tensor Voting-Based Surface Anomaly Classification Approach by Using 3D Point Cloud Data

被引：13

作者：

Du, Juan ^{[1
,2
]}

Yan, Hao ^{[3
]}

Chang, Tzyy-Shuh ^{[4
]}

Shi, Jianjun ^{[5
]}

机构：

[1] Hong Kong Univ Sci & Technol, Smart Mfg Thrust, Syst Hub, Guangzhou 511458, Peoples R China

[2] Guangzhou HKUST Fok Ying Tung Res Inst, Guangzhou 511458, Peoples R China

[3] Arizona State Univ, Sch Comp Informat & Decis Syst Engn, Tempe, AZ 85281 USA

[4] OG Technol, Ann Arbor, MI 48108 USA

[5] Georgia Inst Technol, H Milton Stewart Sch Ind & Syst Engn, Atlanta, GA 30332 USA

来源：

JOURNAL OF MANUFACTURING SCIENCE AND ENGINEERING-TRANSACTIONS OF THE ASME | 2022年 / 144卷 / 05期

关键词：

surface monitoring; anomaly classification; tensor voting; 3D point cloud data; product surface inspection; inspection and quality control; metrology; sensing; monitoring; and diagnostics; SPARSE;

D O I：

10.1115/1.4052660

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Advanced three-dimensional (3D) scanning technology has been widely used in many industries to collect the massive point cloud data of artifacts for part dimension measurement and shape analysis. Though point cloud data has product surface quality information, it is challenging to conduct effective surface anomaly classification due to the complex data representation, high-dimensionality, and inconsistent size of the 3D point cloud data within each sample. To deal with these challenges, this paper proposes a tensor voting-based approach for anomaly classification of artifact surfaces. A case study based on 3D scanned data obtained from a manufacturing plant shows the effectiveness of the proposed method.

引用

页数：12

共 33 条

[11]

DErrico J, SHAPE LANGUAGE MODEL

[12] Multiple Tensor-on-Tensor Regression: An Approach for Modeling Processes With Heterogeneous Sources of Data [J].

Gahrooei, Mostafa Reisi ;

Yan, Hao ;

Paynabar, Kamran ;

Shi, Jianjun .

TECHNOMETRICS, 2021, 63 (02) :147-159

[13]

GRANLUND GH, 1995, SIGNAL PROCESSING CO

[14] Inference of surfaces, 3D curves, and junctions from sparse, noisy, 3D data [J].

Guy, G ;

Medioni, G .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1997, 19 (11) :1265-1277

[15] Real-Time Object Classification in 3D Point Clouds Using Point Feature Histograms [J].

Himmelsbach, M. ;

Luettel, T. ;

Wuensche, H. -J. .

2009 IEEE-RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, 2009, :994-1000

[16] Detection and monitoring of defects on three-dimensional curved surfaces based on high-density point cloud data [J].

Huang, Delin ;

Du, Shichang ;

Li, Guilong ;

Zhao, Chen ;

Deng, Yafei .

PRECISION ENGINEERING-JOURNAL OF THE INTERNATIONAL SOCIETIES FOR PRECISION ENGINEERING AND NANOTECHNOLOGY, 2018, 53 :79-95

[17] Improved Sparse Multi-Class SVM and Its Application for Gene Selection in Cancer Classification [J].

Huang, Lingkang ;

Zhang, Hao Helen ;

Zeng, Zhao-Bang ;

Bushel, Pierre R. .

CANCER INFORMATICS, 2013, 12 :143-153

[18] Multicategory support vector machines: Theory and application to the classification of microarray data and satellite radiance data [J].

Lee, YK ;

Lin, Y ;

Wahba, G .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2004, 99 (465) :67-81

[19]

Popa E.M., 2011, ACTA Technica Corviniensis, V4, P109

[20]

Qi CR., 2017, NeurIPS, P5099

← 1 2 3 4 →