Three-dimensional cardiac point cloud registration by improved iterative closest point method

Bin WANG; Lin LIU; Yu-qing HOU; Xiao-wei HE

doi:10.3788/OPE.20202802.0474

您当前的位置：

首页 >

文章列表页 >

Three-dimensional cardiac point cloud registration by improved iterative closest point method

Information Sciences | 更新时间：2020-07-16

- Three-dimensional cardiac point cloud registration by improved iterative closest point method
- Optics and Precision Engineering Vol. 28, Issue 2, Pages: 474-484(2020)
- 作者机构：
  
  西北大学信息科学与技术学院，西安市影像组学与智能感知重点实验室, 陕西西安 710127
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20202802.0474
  CLC： TP391
- Received：16 May 2019，
  
  Revised：06 July 2019，
  
  Accepted：06 July 2019，
  
  Published：25 February 2020
- 稿件说明：
移动端阅览
Bin WANG, Lin LIU, Yu-qing HOU, et al. Three-dimensional cardiac point cloud registration by improved iterative closest point method[J]. Optics and precision engineering, 2020, 28(2): 474-484.
DOI：

Bin WANG, Lin LIU, Yu-qing HOU, et al. Three-dimensional cardiac point cloud registration by improved iterative closest point method[J]. Optics and precision engineering, 2020, 28(2): 474-484. DOI： 10.3788/OPE.20202802.0474.

摘要

在医学多图谱配准中，为了改善因初始位置差异较大、形状复杂和局部残缺导致的配准效率低和精度差的问题，本文采用了先粗配准再精配准的处理策略，在主成分分析法(PCA)实现粗配准的基础上，提出了基于双向距离比例的迭代最近点(ICP)的精配准算法。精配准算法中，首先采用KD-tree进行最近邻搜索以提高对应点对的搜索速度，然后为每个点提出了双向匹配方法并计算其双向距离和比值，为进一步提高配准精度，引入了一个指数函数判断点对正确匹配概率，最后运用奇异值分解法(SVD)计算最终变换矩阵。为了验证算法的可行性和有效性，分别设计了不同缺损程度的斯坦福点云数据实验和两组CT心脏点云数据配准实验，结果表明本文方法较经典ICP算法的平均误差减少约21%，较TrICP算法减少约13%，在心脏点云数据配准实验中，本文方法较TrICP算法的15.5 s加快到1.77 s。因此本文方法在解决三维心脏点云数据的配准问题中具有良好的效率、精度和稳定性。

Abstract

In medical multi-atlas registration

to improve the limitations of low efficiency and poor accuracy caused by large initial position differences

complex shapes

and local residual differences

a fine registration algorithm that used Iterative Closest Point (ICP) was proposed based on the bidirectional distance ratio. The proposed algorithm was based on the coarse registration method followed by fine registration

where the former was processed by principal registration analysis.In the fine registration algorithm

the K-Dimensional tree was initially used to perform a nearest-neighbor search to improve the searching speed of corresponding point pairs. A bidirectional matching method was then proposed for each point

and the bidirectional distance and ratio were calculated. To further improve the accuracy of the registration

an exponential function was introduced to determine the probability that the point pair belongs to the correct match. The final transformation matrix was then obtained using Singular Value Decomposition. To evaluate the feasibility and effectiveness of the algorithm

experiments were designed using Stanford point cloud data and two sets of CT cardiac point cloud data registration. The results show that the average error during registration is reduced by 21% using this method compared to the classical ICP algorithm

which is 13% lower than the error obtained using the trimmed ICP (TrICP)algorithm. In the cardiac point cloud data registration experiment

this method is accelerated to 1.77 s compared to the TrICP algorithm

which has a value of 15.5 s.Therefore

the proposed method has high efficiency

accuracy

and stability in solving the registration problem associated with the three-dimensional cardiac point cloud data.

关键词

Keywords

references

韦盛斌 , 王少卿 , 周常河 , 等 . 用于三维重建的点云单应性迭代最近点配准算法 . 光学学报 , 2015 . 35 ( 05 ): 252 - 258 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxxb201505033 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxxb201505033 .

S B WEI , SH Q WANG , C H ZHOU , 等 . An Iterative closest point algorithm based on biunique correspondence of point clouds for reconstruction . Acta Optica Sinica , 2015 . 35 ( 05 ): 252 - 258 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxxb201505033 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxxb201505033 .

J C ZHANG , C H YAN , C K CHUI , 等 . Multimodal image registration system for image-guided or thopaedic surgery . Machine Vision & Applications , 2011 . 22 ( 5 ): 851 - 863 .

LEMESZENSKI D D, NAKAMURA R. A Marker-Free calibration and registration process for multiple depth maps from structured light sensors and its application in video avatar systems[C]. 15th Symposium on Virtual and Augmented Reality, Cuiaba, Brazil, May 28-31 2013. Washington DC, USA: IEEE , 2013: 73-82.

I MARIANO , X X LI . Automatic registration of 3D point clouds for reverse engineering . Journal of Computational& Theoretical Nanoscience , 2011 . 4 ( 6 ): 2431 - 2432 . http://cn.bing.com/academic/profile?id=a11b9876183b24a0d0df6221b1100ca7&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=a11b9876183b24a0d0df6221b1100ca7&encoded=0&v=paper_preview&mkt=zh-cn .

F J ZHAO , P GAO , H W HU , 等 . Efficient kidney segmentation in micro-CT based on multi-atlas registration and random forests . IEEE Access , 2018 . 6 43712 - 43723 . http://cn.bing.com/academic/profile?id=64dfe1958af2793f09a1622db46d3aac&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=64dfe1958af2793f09a1622db46d3aac&encoded=0&v=paper_preview&mkt=zh-cn .

YANG G Y, SUN C C, CHEN Y, et al .. Automatic kindey segmentation in CT images based on multi-atlas image registration[C]. ACDC and MMWHS Challenges. STACOM 2017: 10663.

刘江 , 张旭 , 朱继文 . 一种基于K-D树优化的ICP三维点云配准方法 . 测绘工程 , 2016 . 25 ( 6 ): 15 - 18 . http://d.old.wanfangdata.com.cn/Periodical/chgc201606004 http://d.old.wanfangdata.com.cn/Periodical/chgc201606004 .

J LIU , X ZHANG , J W ZHU . ICP 3D point cloud registration method based on K-D tree optimization . Engineering of Surveying and Mapping , 2016 . 25 ( 6 ): 15 - 18 . http://d.old.wanfangdata.com.cn/Periodical/chgc201606004 http://d.old.wanfangdata.com.cn/Periodical/chgc201606004 .

C MENG , J ZHANG , F G ZHOU , 等 . New method for geometric calibration and distortion correction of conventional C-arm . Computers in Biology & Medicine , 2014 . 52 ( 3 ): 49 - 56 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=ec3b6afc6b8f4f845d1fbfec4d70cd03 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=ec3b6afc6b8f4f845d1fbfec4d70cd03 .

B W HE , Z M LIN , Y F LI . An automatic registration algorithm for the scattered point clouds based on the curvature feature . Optics & Laser Technology , 2013 . 46 ( 1 ): 53 - 60 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=39a345726cb1b4a77fc004395259c622 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=39a345726cb1b4a77fc004395259c622 .

P J BESL , N D MCKAY . A method for registration of 3D shapes . IEEE Transactions on Pattern Analysis& Machine Intelligence , 1992 . 14 ( 3 ): 239 - 256 . http://d.old.wanfangdata.com.cn/OAPaper/oai_doaj-articles_408530e55fe9079ac27a3a0351866619 http://d.old.wanfangdata.com.cn/OAPaper/oai_doaj-articles_408530e55fe9079ac27a3a0351866619 .

J L YANG , H D LI , C DYLAN , 等 . Go-ICP: A globally optimal solution to 3D ICP point-set registration . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2016 . 38 ( 11 ): 2241 - 2253 . http://d.old.wanfangdata.com.cn/NSTLHY/NSTL_HYCC0213983376/ http://d.old.wanfangdata.com.cn/NSTLHY/NSTL_HYCC0213983376/ .

赵夫群 , 周明全 . 颅骨点云模型的优化配准 . 光学精密工程 , 2017 . 25 ( 7 ): 1927 - 1933 . http://www.eope.net/CN/abstract/abstract17132.shtml http://www.eope.net/CN/abstract/abstract17132.shtml .

F Q ZHAO , M Q ZHOU . Optimization registration of point cloud model of skull . Opt. Precision Eng , 2017 . 25 ( 7 ): 1927 - 1933 . http://www.eope.net/CN/abstract/abstract17132.shtml http://www.eope.net/CN/abstract/abstract17132.shtml .

RUSINKIEWICZ S, LEVOY M. Efficient variants of the ICP algorithm[C]. Third International Conference on 3D Digital Imaging and Modeling , 2001: 145-152.

YANG C, MEDIONI G. Object modeling by registration of multiple range images[C] . Proceedings of IEEE International Conference on Robotics and Automation , 1991: 2724-2729.

王欣 , 张明明 , 于晓 , 等 . 应用改进迭代最近点方法的点云数据配准 . 光学精密工程 , 2012 . 20 ( 9 ): 2068 - 2077 . http://www.eope.net/CN/abstract/abstract14353.shtml http://www.eope.net/CN/abstract/abstract14353.shtml .

X WANG , M M ZHANG , X YU , 等 . Point cloud registration based on improved iterative closest point method . Opt. Precision Eng , 0212 . 20 ( 9 ): 2068 - 2077 . http://www.eope.net/CN/abstract/abstract14353.shtml http://www.eope.net/CN/abstract/abstract14353.shtml .

D CHETVERIKOV , D STEPANOV , P KRSEK . Robust euclidean alignment of 3d point sets: the trimmed iterative closest point algorithm . Image and Vision Computing , 2005 . 23 ( 3 ): 299 - 309 . http://cn.bing.com/academic/profile?id=00c1a816325975921840e876943c8c1f&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=00c1a816325975921840e876943c8c1f&encoded=0&v=paper_preview&mkt=zh-cn .

杨华 . 基于稀疏主成分分析的图像噪声估计方法 . 液晶与显示 , 2019 . 34 ( 9 ): 913 - 920 . http://d.old.wanfangdata.com.cn/Periodical/yjyxs201909011 http://d.old.wanfangdata.com.cn/Periodical/yjyxs201909011 .

H YANG . Image noise estimation method based on sparse principal component analysis . Chinese Journal of Liquid Crystals and Displays , 2019 . 34 ( 9 ): 913 - 920 . http://d.old.wanfangdata.com.cn/Periodical/yjyxs201909011 http://d.old.wanfangdata.com.cn/Periodical/yjyxs201909011 .

李宁 , 赵永强 , 潘泉 . 时空自适应的分焦平面偏振视频PCA去噪 . 红外与激光工程 , 2019 . 48 ( 10 ): 270 - 276 . http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201910036 http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201910036 .

N LI , Y Q ZHAO , Q PAN . PCA-based spatial-temporal adaptive denoising of DoFP video for microgrid polarimeters . Infrared and Laser Engineering , 2019 . 48 ( 10 ): 270 - 276 . http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201910036 http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201910036 .

N N QIN , X D LAI , X F MIN , 等 . Registration of spatial data based on principle component analysis . Engineering Journal of Wuhan University , 2012 . 45 ( 4 ): 528 - 530 . http://d.old.wanfangdata.com.cn/Periodical/whsldldxxb201204026 http://d.old.wanfangdata.com.cn/Periodical/whsldldxxb201204026 .

陈华伟 , 袁小翠 , 吴禄慎 , 等 . 基于曲率突变分析的点云特征线自动提取 . 光学精密工程 , 2019 . 27 ( 5 ): 1218 - 1228 . http://www.eope.net/CN/abstract/abstract17901.shtml http://www.eope.net/CN/abstract/abstract17901.shtml .

H W CHEN , X C YUAN , L SH WU , 等 . Automatic point cloud feature line extraction algorithm based on curvature mutation analysi . Opt. Precision Eng , 2019 . 27 ( 5 ): 1218 - 1228 . http://www.eope.net/CN/abstract/abstract17901.shtml http://www.eope.net/CN/abstract/abstract17901.shtml .

沈海平 , 达飞鹏 , 雷家勇 . 基于最小二乘法的点云数据拼接研究 . 中国图象图形学报 , 2005 . 10 ( 9 ): 1112 - 1116 . http://d.old.wanfangdata.com.cn/Periodical/zgtxtxxb-a200509007 http://d.old.wanfangdata.com.cn/Periodical/zgtxtxxb-a200509007 .

H P SHEN , F P DA , J Y LEI . Research of point clouds registration based on least square method . Journal of Image and Graphics , 2005 . 10 ( 9 ): 1112 - 1116 . http://d.old.wanfangdata.com.cn/Periodical/zgtxtxxb-a200509007 http://d.old.wanfangdata.com.cn/Periodical/zgtxtxxb-a200509007 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰