王佳婧;王晓南;郑顺义;朱锋博;

• 1:武汉大学遥感信息工程学院
• 2:南京中观自动化科技有限公司
• 3:地球空间信息技术协同创新中心

摘要(Abstract)：

针对多种多样的三维点云自动初始配准算法,该文依照配准过程中侧重点的不同将其分为基于局部特征描述、基于全局搜索策略和基于统计学概率3个算法类别,对其中具有代表性的FPFH、4PCS、NDT 3种算法进行了配准效率和数据适应性的比较分析。采用4组数据分别使用这3种算法进行配准实验,提出了算法中相关参数的设置方法,验证了它们用于最近点迭代精配准的适用性,并记录相应的配准耗时。实验结果表明,不同算法适用的数据不同,初始配准时可以依据数据的特点选取合适的方法。

关键词(KeyWords)： 三维重建;点云配准;初始配准;算法比较

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(41171357);; 湖北省科研条件与资源研究开发项目(2015BCE080)

作者(Authors): 王佳婧;王晓南;郑顺义;朱锋博;

DOI: 10.16251/j.cnki.1009-2307.2018.02.004

参考文献(References)：

• [1]周朗明,郑顺义,黄荣永.旋转平台点云数据的配准方法[J].测绘学报,2013,42(1):73-79.(ZHOU Langming,ZHENG Shunyi,HUANG Rongyong.A registration algorithm for point clouds obtained by scanning objects on turntable[J].Acta Geodaetica et Cartographica Sinica,2013,42(1):73-79.)
• [2]BESL P J,MCKAY N D.Method for registration of 3-D shapes[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(2):239-256.
• [3]POTTMANN H,HUANG Q X,YANG Y L,et al.Geometry and convergence analysis of algorithms for registration of 3D shapes[J].International Journal of Computer Vision,2006,67(3):277-296.
• [4]BAE K H.Evaluation of the convergence region of an automated registration method for 3D laser scanner point clouds[J].Sensors,2009,9(1):355-375.
• [5]JOHNSON A E,HEBERT M.Using spin images for efficient object recognition in cluttered 3Dscenes[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,1999,21(5):433-449.
• [6]TOMBARI F,SALTI S,STEFANO L D.Unique signatures of histograms for local surface description[J].Lecture Notes in Computer Science,2010(6313):356-369.
• [7]RUSU R B,BLODOW N,BEETZ M.Fast point feature histograms(FPFH)for 3Dregistration[C]//Proceedings of the 2009IEEE International Conference on Robotics and Automation.Washington DC,USA:IEEE,2009:3212-3217.
• [8]KIM H,HILTON A.Evaluation of 3Dfeature descriptors for multi-modal data registration[C]//International Conference on 3D Vision-3DV 2013.Washington DC,USA:IEEE,2013:119-126.
• [9]CHEN C S,HUNG Y P,CHENG J B.RANSAC-based DARCES:a new approach to fast automatic registration of partially overlapping range images[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,1999,21(11):1229-1234.
• [10]AIGER D,MITRA N J,COHEN-OR D.4-points congruent sets for robust pairwise surface registration[J].ACM Transactions on Graphics,2008,27(3):15-19.
• [11]SANTAMARA J,CORDON O,DAMAS S.A comparative study of state-of-the-art evolutionary image registration methods for 3D modeling[J].Computer Vision&Image Understanding,2011,115(9):1340-1354.
• [12]BIBER P,STRASSER W.The normal distributions transform:a new approach to laser scan matching[C]//Proceedings of the 2003IEEE/RJS International Conference on Intelligent Robots and Systems.Washington DC,USA:IEEE Computer Society,2003:2743-2748.
• [13]BURGUERA A,GONZALEZ Y,OLIVER G.The likelihood field approach to sonar scan matching[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems.Washington DC,USA:IEEE,2008:2977-2982.
• [14]BOUGHORBEL F,KOSCHAN A,ABIDI B,et al.Gaussian fields:a new criterion for 3Drigid registration[J].Pattern Recognition,2004,37(7):1567-1571.
• [15]LAFFERTY J,MCCALLUM A,PEREIRA F C N.Conditional random fields:probabilistic models for segmenting and labeling sequence data[C]//Proceedings of the Eighteenth International Conference on Machine Learning(ICML).[S.l.]:[s.n.],2001:282-289.
• [16]DEZ Y,ROURE F,LLADX,et al.A qualitative review on 3Dcoarse registration methods[J].ACM Computing Surveys,2015,47(3):1-36.
• [17]张剑清,潘励,王树根.摄影测量学[M].2版.武汉:武汉大学出版,2009:27-28.(ZHANG Jianqing,PAN Li,WANG Shugen.Photogrammetry[M].2nd ed.Wuhan:Wuhan University,2009:27-28.)
• [18]RUSU R B,MARTON Z C,BLODOW N,et al.Learning informative point classes for the acquisition of object model maps[C]//10th International Conference on Control,Automation,Robotics and Vision(ICARCV),2008.Washington DC,USA:IEEE,2008:643-650.
• [19]RUSU R B,MARTON Z C,BLODOW N,et al.Towards 3Dpoint cloud based object maps for household environments[J].Robotics&Autonomous Systems,2008,56(11):927-941.
• [20]RUSU R B,BLODOW N,MARTON Z C,et al.Aligning point cloud views using persistent feature histograms[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS)2008.Washington DC,USA:IEEE,2008:3384-3391.
• [21]RUSU R B,MARTON Z C,BLODOW N,et al.Persistent point feature histograms for 3Dpoint clouds[C]//Proc of the 10th Int Conf on Intelligent Autonomous Systems(IAS-10).[S.l.]:[s.n.],2008.
• [22]GOODRICH M T,MITCHELL J S B,ORLETSKY M W.Practical methods for approximate geometric pattern matching under rigid motions(preliminary version)[C]//Symposium on Computational Geometry.New York,USA:ACM,1994:103-112.
• [23]MAGNUSSON M,DUCKETT T.A comparison of 3D registration algorithms for autonomous underground mining vehicles[C]//2nd Eurpean Conferena on Mobile Robots,ECMR 2005[S.l.]:[s.n.],2005.
• [24]MAGNUSSON M,ELSRUD R,SKAGERLUND L E,et al.3D modelling for underground mining vehicles[C]//Conference on in Simsafe.[S.l.]:[s.n.],2005.
• [25]MAGNUSSON M,ANDREASSON H,NCHTER A,et al.Automatic appearance-based loop detection from 3D laser data using the normal distributions transform[J].Journal of Field Robotics,2009,26(11/12):892-914.
• [26]MAGNUSSON M.The three-dimensional nomal-distributions transform:an efficient representation for registration,surface analysis,and loop detection[D].rebro,Sweden:rebro University,2013.
• [27]RIPPERDA N,BRENNER C.Marker-free registration of terrestrial laser scans using the normal distribution transform[C/OL]//Proceedings of the ISPRS Working Group V/4 Workshop 3D-ARCH,2005.[2016-04-01].https://www.ikg.uni-hannover.de/fileadmin/ikg/staff/publications/Konferenzbeitraege-abstract-review/RipperdaBrenner-isprs2005.pdf.
• [28]TAKEUCHI E,TSUBOUCHI T.A 3-D scan matching using improved 3-D normal distributions transform for mobile robotic mapping[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems.Washington DC,USA:IEEE,2006:3068-3073.
• [29]MORJ J,THUENTE D J.Line search algorithms with guaranteed sufficient decrease[J].ACM Transactions on Mathematical Software,1994,20(3):286-307.
• [30]THEILER P W,WEGNER J D,SCHINDLER K.Keypoint-based 4-points congruent sets:automated marker-less registration of laser scans[J].ISPRS Journal of Photogrammetry&Remote Sensing,2014,96(11):149-163.
• [31]MELLADO N,AIGER D,MITRA N J.Super 4PCS fast global pointcloud registration via smart indexing[J].Computer Graphics Forum,2014,33(5):205-215.
• [32]ULA爦C,TEMELTA爦H.3D multi-layered normal distribution transform for fast and long range scan matching[J].Journal of Intelligent&Robotic Systems,2013,71(1):85-108.