基于“滑移”主方向自适应采样的ICP算法优化研究

中国机械工程 ›› 2014, Vol. 25 ›› Issue (4): 497-502.

基于“滑移”主方向自适应采样的ICP算法优化研究

姜晓通1;戴宁1;张长东1;崔海华1;闫国栋1;孙玉春2

1.南京航空航天大学,南京,210016
2.北京大学口腔医学院,北京，100081

出版日期:2014-02-25 发布日期:2014-03-05
基金资助:
“十二五”国家科技支撑计划资助项目(2012BAI07B04);国家自然科学基金资助项目(51205192)

Research on Self-adapting Sampling along “Slide” Direction of ICP Algorithm

Jiang Xiaotong1;Dai Ning2;Zhang Changdong1;Cui Haihua1;Yan Guodong1;Sun Yuchun2

1.Nanjing University of Aeronautics and Astronautics,Nanjing,210016
2.Peking University School of Stomatology College,Beijing,100081

Online:2014-02-25 Published:2014-03-05
Supported by:
The National Key Technology R&D Program（No. 2012BAI07B04）;National Natural Science Foundation of China（No. 51205192）

摘要/Abstract

摘要：

在已有相关理论的基础上,研究了ICP算法中的采样策略及匹配点集的确定。首先确定重叠区域，识别边界点;其次对重叠区域进行采样，在ICP算法的迭代过程中的不同阶段采取不同的采样策略，同时提出一种基于法矢三点插值的方法确定匹配点，保证配准的精度，提高配准的速度;最后通过对点云数据的测试，验证了研究成果的有效性和实用性。

关键词: 精确配准, 采样策略, 协方差矩阵, 匹配点集

Abstract:

On the basis of existing related theory, this paper placed emphasis on sampling strategy and determination of the matching point set of ICP algorithm. Firstly, the overlap area was determined and the point on the boundary was recognized. Secondly, sampling in the overlap area,and took different sampling strategies in different stages of the iteration of ICP algorithm. At the same time, this paper presented a new way to determine the match point set to guarantee the precision and increase the speed of the fine registration. Finally, experiments based on the point data verified the effectiveness and practicability of the algorithm.

Key words: fine registration, sampling strategy, covariance matrix, match point set

中图分类号:

TP391

姜晓通, 戴宁, 张长东, 崔海华, 闫国栋, 孙玉春. 基于“滑移”主方向自适应采样的ICP算法优化研究[J]. 中国机械工程, 2014, 25(4): 497-502.

Jiang Xiaotong, Dai Ning, Zhang Changdong, Cui Haihua, Yan Guodong, Sun Yuchun. Research on Self-adapting Sampling along “Slide” Direction of ICP Algorithm[J]. China Mechanical Engineering, 2014, 25(4): 497-502.

参考文献

[1]谢则晓,张国成,张国雄.线结构光测量数据的自动拼合方法[J].中国机械工程,2005,16(9):775-778.
Xie Zexiao,Zhang Chengguo,Zhang Guoxiong.An Automatic Registration Method for the Data Patches Obtained by Structured-light Sensons[J].China Mechanical Engineering,2005,16(9):775-778.
[2]罗先波,钟约先,李仁举.三维扫描系统中的数据配准技术[J].清华大学学报,2004,44(8):1104-1106.
Luo Xianbo,Zhong Yuexian,Li Renju.Data Registration in 3-D Scanning Systems [J].J. Tsinghua Univ.,2004,44(8):1104-1106.
[3]朱延婿，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,2006,18(4):475-481.
Zhu Yanxu,Zhou Laishui,Zhang Liyan.Registration of Scattered Cloud Data[J].Journal of Computer-aided Design & Computer Graphics,2006,18(4):475- 481．
[4]Besl P J,McKay N D.A Method for Registration of 3-D Shapes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(2):239-256.
[5]Chen Y,Medioni G.Object Modeling by Registration of Multiple Range Images[J].Image and Vision Computing, 1992, 10(3): 145-155.
[6]Johnson A,Hebert M.Surface Registration by Matching Oriented Points[C]//Proceedings of International Conference on Recent Advances in 3-Digital Imaging and Modeling.Ottawa,1997:121-128.
[7]王磊,邢渊.反向工程中数据点云的拼合[J].模具技术,2004(1):47-49.
Wang Lei,Xing Yuan.The Merge of Date Point Could in Reverse Engineering[J].Die and Mould Technology,2004(1):47-49.
[8]Rusinkiewiez S.Levoy M.Efficient Variants of the ICP Algorithm[C]//Proceeding of the 3rd International Conference on 3D Digital Imaging and Modeling.Quebec,2001:145-152.
[9]Masuda T.Generation of Geometric Model by Registration and Integration of Multiple Range Images[C]//Proceedings of the 3rdInternational Conference on 3D Digital Imaging and Modeling.Quebec,2001:254-261.
[10]Masuda T,Yokoya N.A Robust Method for RegIstration and Segmentation of Multiple Range ImaGes[J].Computer Vision and Image Uniderstanding,1995,61(3):295-307.
[11]Gelfand N,Ikemoto L,Rusinkiewicz S,et al.Geometrically Stable Sampling for the ICP Algorithm[C].//Proceedings of the 4th International Conference on 3D Digital Imaging and Modeling.Banff,2003:260-267.
[12]谢则晓,徐尚.三维点云数据拼接中ICP及其改进算法综述[J].中国海洋大学学报,2010,40(1):99-103.
Xie Zexiao,Xu Shang.A Survey on the ICP Algorithm and Its Variants in Registration of 3D Point Clouds[J].Periodical of Ocean University of China,2010,40(1):99-103.
[13]Eggert D W, Lorusso A, Fisher R B. Estimating 3-D Rigid Body Transformations:a Comparison of Four Major Algorithms[J].Machine Vision and Applications,1997,9(5/6):272-290.