Local Scanning Point Cloud Localization of Aircraft Skins Based on Multi-descriptor Voting

doi:10.3969/j.issn.1004-132X.2021.22.009

China Mechanical Engineering ›› 2021, Vol. 32 ›› Issue (22): 2724-2730,2771.DOI: 10.3969/j.issn.1004-132X.2021.22.009

Previous Articles Next Articles

Local Scanning Point Cloud Localization of Aircraft Skins Based on Multi-descriptor Voting

ZHANG Yiming1;LI Hongwei2;ZHAO An'an2X;IE Qian3;WANG Jun3

1.College of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing,210016
2.AVIC Xi'an Aircraft Industry（Group） Company Ltd.,Xi'an,210016
3.College of Mechanical & Electrical Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing,210016

Online:2021-11-25 Published:2021-12-10

基于多描述子投票的飞机蒙皮局部扫描点云定位

张一鸣1;李红卫2;赵安安2;谢乾3;汪俊3

1.南京航空航天大学计算机科学与技术学院，南京，210016
2.航空工业西安飞机工业（集团）有限责任公司，西安，710089
3.南京航空航天大学机电学院，南京，210016

通讯作者: 汪俊（通信作者），男，1981年生，教授、博士研究生导师。E-mail:wjun@nuaa.edu.cn。
作者简介:张一鸣，男，1997年生，硕士研究生。研究方向为点云数据处理。
基金资助:
江苏省杰出青年基金(BK20190016)

Abstract

Abstract: In order to improve efficiency of digital aircraft skin detection, aiming at the alignment problems of local aircraft skins and the digital model, a local scanning point cloud localization algorithm was proposed based on multi-descriptor voting. The localization region on the digital model was determined by various 3D point cloud descriptors, since they had discrepancy in recognition ability. A weighted voting point method was proposed to decrease deviation. A well-designed comparision experiment and a concrete example on real data were conducted. The results are as follows: compared with the methods based on single descriptor, the localization accuracy is improved by 37.5% on average. The algorithm is feasible in practical engineering.

Key words: aircraft skin, digital inspection, point cloud data, local point cloud localization, 3D point cloud descriptor

摘要： 为了提高数字化飞机蒙皮检测技术的效率，针对其中局部蒙皮和数字模型的对齐问题，提出了基于多描述子投票的飞机蒙皮局部扫描点云定位算法，采用基于测地距离的蒙皮面片选取方法，综合利用多种三维点云描述子的识别能力差异来确定数字模型上的定位区域，同时提出了投票点加权定位法来提高定位位置精度。根据对比实验结果和工程实例上的实际应用，得出结论如下：所提算法相比于基于单一描述子的定位方法定位准确率平均提高约37.5%；所提算法在实际工程中具有可行性。

关键词: 飞机蒙皮, 数字化测量, 点云数据, 局部点云定位, 三维点云描述子

CLC Number:

V262.7

ZHANG Yiming, LI Hongwei, ZHAO An'anX, IE Qian, WANG Jun. Local Scanning Point Cloud Localization of Aircraft Skins Based on Multi-descriptor Voting[J]. China Mechanical Engineering, 2021, 32(22): 2724-2730,2771.

张一鸣, 李红卫, 赵安安, 谢乾, 汪俊. 基于多描述子投票的飞机蒙皮局部扫描点云定位[J]. 中国机械工程, 2021, 32(22): 2724-2730,2771.

References

［1］俞芸芸. 飞机机体损伤检测与评估技术分析［J］.科学技术创新，2020，23(25)：21-22.
YU Yunyun. Analysis of Aircraft Body Damage Detection and Evaluation Technology［J］. Scientific and Technological Innovation, 2020, 23(25):21-22.
［2］李栋，李泷杲，李琦，等. 基于激光扫描的飞机蒙皮下陷特征点提取［J］. 航空制造技术，2018，61(9)：96-101.
LI Dong, LI Shuanggao, LI Qi, et al. Feature Points Extraction of Aircraft Skin Sag Based on Laser Scanning［J］. Aeronautical Manufacturing Technology, 2018, 61(9):96-101.
［3］张晓. 民航飞机维修无损检测的主要特点［EB/OL］. ［2020-09-20］.https:∥wenku.baidu.com/view/b47b56de360cba1aa811da10.html.
ZHANG Xiao. Main Features of NDT for Civil Aircraft Maintenance［EB/OL］.［2020-09-20］. https:∥wenku.baidu.com/view/b47b56de360cba1aa811da10.html.
［4］张珂，罗文田. 机器视觉技术在飞机蒙皮损伤检测中的应用［J］. 软件导刊，2019，18(9)：154-157.
ZHANG Ke, LUO Wentian. Application of Machine Vision Technology in Aircraft Skin Damage Detection［J］. Software Guide, 2019, 18(9):154-157.
［5］盛敏. 基于机器视觉的飞机蒙皮损伤检测方法研究［D］. 南京：南京航空航天大学，2011.
SHENG Min. Aircraft Skin Damage Detection Method Based on Machhine Vision［D］. Nanjing:Nanjing University of Aeronautics and Astronautics, 2011.
［6］王昊. 基于机器视觉的飞机蒙皮损伤检测与寿命分析方法［D］. 南京：南京航空航天大学，2013.
WANG Hao. Aircraft Skin Damage Detection and Life Cycle Analysis Method Based on Machine Vision［D］. Nanjing:Nanjing University of Aeronautics and Astronautics, 2013.
［7］JOVANCEVIC I, PHAM H H, ORTEU J J, et al. 3D Pointcloud Analysis for Detection and Characterization of Defects on Airplane Exterior Surface［J］. Journal of Nondestructive Evaluation, 2017, 36(4):1-17.
［8］高瑞. 飞机蒙皮外形自动化激光扫描测量关键技术研究［D］. 南京：南京航空航天大学，2018.
GAO Rui. Reasearch on the Key Technology of Automatic Laser Scanning Measurement for Aircraft Skin Shape［D］. Nanjing:Nanjing University of Aeronautics and Astronautics, 2018.
［9］XIE Qian, LU Dening, DU Kunpeng, et al. Aircraft Skin Rivet Detection Based on 3D Point Cloud via Multiple Structures Fitting［J］. Computer-Aided Design, 2020, 120:1-12.
［10］许龙. 飞机蒙皮外形的自动化检测技术研究［D］. 南京：南京航空航天大学，2015.
XU Long. Research of Aircraft Skin Apperance Automative Inspection Techonlogy［D］. Nanjing:Nanjing University of Aeronautics and Astronautics, 2015.
［11］戴静兰，陈志杨，叶修梓. ICP算法在点云配准中的应用［J］.中国图象图形学报，2007, 7(3)：517-521.
DAI Jinglan, CHEN Zhiyang, YE Xiuzi. The Application of ICP Algorithm in Pointcloud Alignment［J］. Journal of Image and Graphics, 2007, 7(3):517-521 .
［12］JIANG Jun, CHENG Jun, CHEN Xinglin. Registration for 3D Pointcloud Using Angular-invariant Feature［J］. Neurocomputing, 2009, 72(16):3839-3844.
［13］RUSU R B, BLODOW N, BEETZ M. Fast Point Feature Histograms(FPFH) for 3D Registration［C］∥IEEE International Conference on Robotics and Automation. Kobe, 2009:3212-3217.
［14］WOHLKINGER W, VINCZE M. Ensemble of Shape Functions for 3D Object Classification［C］∥IEEE International Conference on Robotics and Biomimetics. Shanghai, 2011:2987-2992.
［15］MARTON Z C, PANGERCIC D, RUSU R B, et al. Hierarchical Object Geometric Categorization and Appearance Classification for Mobile Manipulation［C］∥10th IEEE-RAS International Conference on Humanoid Robots. Nashville, 2010:365-370.
［16］薛耀红, 梁学章, 马婷, 等. 扫描点云的一种自动配准方法［J］. 计算机辅助设计与图形学学报，2011，23(2)：223-231.
XUE Yaohong, LIANG Xuezhang, MA Ting, et al. An Automatic Registration Method of Scanned Point Clouds［J］. Journal of Computer-Aided Design & Computer Graphics, 2011, 23(2):223-231.
［17］朱延娟,周来水,张丽艳.散乱点云数据配准算法［J］.计算机辅助设计与图形学学报，2006, 17(4)：475-481.
ZHU Yanjuan, ZHOU Laishui, ZHANG Liyan. Registration of Scattered Cloud Data［J］. Journal of Computer-Aided Design & Computer Graphics, 2006, 17(4):457-481.
［18］闻战胜. 飞机钣金件数字化检测中的模型配准技术研究［D］. 南京：南京航空航天大学，2016.
WEN Zhansheng. Research on Model Registration in Digital Inspection for Aircraft Sheet Metal Part［D］. Nanjing:Nanjing University of Aeronautics and Astronautics，2016.
［19］UNNIKRISHNAN R, HEBERT M. Multi-scale Interest Regions from Unorganized Pointclouds［C］∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. Anchorage, 2008:1-8.
［20］CHENG Jian, XIANG Zhiyu, CAO Teng, et al. Robust Vehicle Detection Using 3D Lidar under Complex Urban Enviroment［C］∥IEEE International Conference on Robotics and Automation. Hong Kong, 2014:691-696.
［21］RUSU R B, Holzbach A, BEETZ M, et al. Detecting and Segmenting Objects for Mobile Manipulation［C］∥ IEEE 12th International Conference on Computer Vision Workshops. Kyoto, 2009:47-54.
［22］KASAEI S H, TOME A M, LOPES L S, et al. GOOD:a Global Orthographic Object Descriptor for 3D Object Recognition and Manipulation［J］. Pattern Recognition Letters, 2016, 83:312-320.
［23］WU Zhirong, SONG Shuran, KHOSLA A, et al. 3D Shapenets:a Deep Representation for Volumetric Shapes［C］∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, 2015:1912-1920.

[1]	SHI Hongxia, WANG Jianmin. Feature Line Extraction for Point Cloud Based on Normal Vector Region Clustering Segmentation [J]. China Mechanical Engineering, 2021, 32(21): 2552-2561.
[2]	Zheng Hongbo, Zhang Jiangwen, Tan Xiaojun, Qin Xujia, Chen Songhui. Quadric Surface Geometry Measurement Method for Point Clouds [J]. China Mechanical Engineering, 2014, 25(11): 1545-1549.
[3]	HE De-Hua, LI Dong-Sheng, TUN Zhi-Min, LI Xiao-Jiang. Design of Displacement Loading for Aircraft Skin in NC Stretch Forming [J]. China Mechanical Engineering, 2010, 21(02): 137-140.

Local Scanning Point Cloud Localization of Aircraft Skins Based on Multi-descriptor Voting

基于多描述子投票的飞机蒙皮局部扫描点云定位

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 3

Recommended Articles

Metrics