融合遗传算法和ICP的地面与车载激光点云配准
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Registration of TLS and MLS Point Cloud Combining Genetic Algorithm with ICP
  • 作者:闫利 ; 谭骏祥 ; 刘华 ; 陈长军
  • 英文作者:YAN Li;TAN Junxiang;LIU Hua;CHEN Changjun;School of Geodesy and Geomatics,Wuhan University;
  • 关键词:车载激光扫描 ; 地面激光扫描 ; 点云配准 ; 遗传算法 ; ICP
  • 英文关键词:mobile laser scanning;;terrestrial laser scanning;;point cloud registration;;genetic algorithm;;ICP
  • 中文刊名:CHXB
  • 英文刊名:Acta Geodaetica et Cartographica Sinica
  • 机构:武汉大学测绘学院;
  • 出版日期:2018-04-15
  • 出版单位:测绘学报
  • 年:2018
  • 期:v.47
  • 基金:国家重点研发计划(2016YFC0802500)~~
  • 语种:中文;
  • 页:CHXB201804013
  • 页数:9
  • CN:04
  • ISSN:11-2089/P
  • 分类号:108-116
摘要
车载激光扫描可快速获取大场景点云,由于存在视场限制和遮挡,需地面激光点云作补充。车载与地面点云分别位于大地坐标和局部坐标系统,本文提出结合遗传算法(genetic algorithm,GA)和(iterative closed point,ICP)的自动点云配准方法以统一基准。ICP采用局部优化,效率较高,但依赖初始解;GA为全局优化方法,但效率低。融合策略为当GA配准趋于局部搜索时,采用ICP完成配准。GA配准以地面激光扫描仪内置GPS测量粗略位置限定优化搜索空间。为提高GA配准精度,提出了最大化归一化匹配分数之和(normalized sum of matching scores,NSMS)配准模型。实测数据试验验证了NSMS模型的有效性,GA配准均方根误差(root mean square error,RMSE)为1~5cm;融合配准比GA配准效率高约50%。
        Large scene point cloud can be quickly acquired by mobile laser scanning(MLS)technology,which needs to be supplemented by terrestrial laser scanning(TLS)point cloud because of limited field of view and occlusion.MLS and TLS point cloud are located in geodetic coordinate system and local coordinate system respectively.This paper proposes an automatic registration method combined genetic algorithm(GA)and iterative closed point ICP to achieve a uniform coordinate reference frame.The local optimizer is utilized in ICP.The efficiency of ICP is higher than that of GA registration,but it depends on a initial solution.GA is a global optimizer,but it's inefficient.The combining strategy is that ICP is enabled to complete the registration when the GA tends to local search.The rough position measured by a built-in GPS of a terrestrial laser scanner is used in the GA registration to limit its optimizing search space.To improve the GA registration accuracy,a maximum registration model called normalized sum of matching scores(NSMS)is presented.The results for measured data show that the NSMS model is effective,the root mean square error(RMSE)of GA registration is 1~5 cm and the registration efficiency can be improved by about 50% combining GA with ICP.
引文
[1]WILLIAMS K,OLSEN M J,ROE G V,et al.Synthesis of Transportation Applications of Mobile LiDAR[J].Remote Sensing,2013,5(9):4652-4692.
    [2]方莉娜,杨必胜.车载激光扫描数据的结构化道路自动提取方法[J].测绘学报,2013,42(2):260-267.FANG Li’na,YANG Bisheng.Automated Extracting Structural Roads from Mobile Laser Scanning Point Clouds[J].Acta Geodaetica et Cartographica Sinica,2013,42(2):260-267.
    [3]GUAN Haiyan,LI J,CAO Shuang,et al.Use of Mobile LiDAR in Road Information Inventory:A Review[J].International Journal of Image and Data Fusion,2016,7(3):219-242.
    [4]YANG Bisheng,LIU Yuan,LIANG Fuxun,et al.Using Mobile Laser Scanning Data for Features Extraction of High Accuracy Driving Maps[C]//Proceedings of the International Archives of the Photogrammetry,Remote Sensing and Spatial Information Sciences.Prague,Czech Republic:ISPRS,2016:433-439.
    [5]BARBER D,MILLS J,SMITH-VOYSEY S.Geometric Validation of a Ground-based Mobile Laser Scanning System[J].ISPRS Journal of Photogrammetry and Remote Sensing,2008,63(1):128-141.
    [6]SALVI J,MATABOSCH C,FOFI D,et al.A Review of Recent Range Image Registration Methods with Accuracy Evaluation[J].Image and Vision Computing,2007,25(5):578-596.
    [7]BESL P J,MCKAY N D.A Method for Registration of3DShapes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(2):239-256.
    [8]CHEN Yang,MEDIONI G.Object Modelling by Registration of Multiple Range Images[J].Image and Vision Computing,1992,10(3):145-155.
    [9]RUSINKIEWICZ S,LEVOY M.Efficient Variants of the ICP Algorithm[C]//Proceedings of the Third International Conference on 3-D Digital Imaging and Modeling.Quebec City,Quebec,Canada:IEEE,2001:145-152.
    [10]AKCA D,GRUN A.Least Squares 3DSurface Matching[M].Zürich:Institut für Geodsie und Photogrammetrie,2007.
    [11]SEEGER S,LABOUREUX X.Feature Extraction and Registration:An Overview[M]//GIROD B,GREINER G,NIEMANN H.Principles of 3DImage Analysis and Synthesis.Kluwer:Academic Publishers,2002:153-166.
    [12]JOHNSON A E,HEBERT M.Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(5):433-449.
    [13]RUSU R B,BLODOW N,BEETZ M.Fast Point Feature Histograms(FPFH)for 3DRegistration[C]//Proceedings of2009 IEEE International Conference on Robotics and Automation.Kobe,Japan:IEEE,2009:3212-3217.
    [14]TOMBARI F,SALTI S,DI STEFANO L.Performance Evaluation of 3D Keypoint Detectors[J].International Journal of Computer Vision,2013,102(1-3):198-220.
    [15]HANSCH R,WEBER T,HELLWICH O.Comparison of3DInterest Point Detectors and Descriptors for Point Cloud Fusion[C]//Proceedings of the ISPRS Technical CommissionⅢSymposium.Zurich,Switzerland:ISPRS,2014:57-64.
    [16]THEILER P W,WEGNER J D,SCHINDLER K.Keypointbased 4-points Congruent Sets-automated Marker-less Registration of Laser Scans[J].ISPRS Journal of Photogrammetry and Remote Sensing,2014,96(2):149-163.
    [17]SILVA L,BELLON O R P,BOYER K L.Precision Range Image Registration Using a Robust Surface Interpenetration Measure and Enhanced Genetic Algorithms[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(5):762-776.
    [18]朱灿.实数编码遗传算法机理分析及算法改进研究[D].长沙:中南大学,2009.ZHU Can.The Study on Mechanism and Improvement of Real-coded Genetic Algorithms[D].Changsha:Central South University,2009.
    [19]JACQ J J,ROUX C.Registration of 3-D Images by Genetic Optimization[J].Pattern Recognition Letters,1995,16(8):823-841.
    [20]SILVA L,BELLON O R P,BOYER K L.Enhanced,Robust Genetic Algorithms for Multiview Range Image Registration[C]//Proceedings of the Fourth International Conference on3D Digital Imaging and Modeling.Banff,Alta.,Canada:IEEE,2003:268-275.
    [21]SCHENK S,HANKE K.Genetic Algorithms for Automatic Registration of Laser Scans with Imperfect and Subdivided Features(GAReg-ISF)[J].Photogrammetrie-FernerkundungGeoinformation,2009,2009(1):23-32.
    [22]LOMONOSOV E,CHETVERIKOV D,EKART A.PreRegistration of Arbitrarily Oriented 3DSurfaces Using a Genetic Algorithm[J].Pattern Recognition Letters,2006,27(11):1201-1208.
    [23]ZHU Jihua,MENG Deyu,LI Zhongyu,et al.Robust Registration of Partially Overlapping Point Sets via Genetic Algorithm with Growth Operator[J].IET Image Processing,2014,8(10):582-590.
    [24]BRINDLE A.Genetic Algorithms for Function Optimization[D].Alberta:University of Alberta,1981.
    [25]MAN K F,TANG K S,KWONG S.Genetic Algorithms:Concepts and Applications[J].IEEE Transactions on Industrial Electronics,1996,43(5):519-534.
    [26]周明,孙树栋.遗传算法原理及应用[M].北京:国防工业出版社,1999.ZHOU Ming,SUN Shudong.Genetic Algorithms:Theory and Applications[M].Beijing:National Defense Industry Press,1999.
    [27]HOLZ D,ICHIM A E,TOMBARI F,et al.Registration with the Point Cloud Library:A Modular Framework for Aligning in 3-D[J].IEEE Robotics&Automation Magazine,2015,22(4):110-124.
    [28]VAN DER PAS R.An Introduction into OpenMP[EB/OL].http://www.nic.uoregon.edu/iwomp2005/iwomp2005_tutorial_openmp_rvdp.pdf.
    [29]COLOMINA I C.On Trajectory Determination for Photogrammetry and Remote Sensing:Sensors,Models and Exploitation[C]//Proceedings of the Photogrammetric Week.Stuttgart,Germany:[s.n.],2015:131-142.
    [30]PAULY M,KEISER R,GROSS M.Multi-scale Feature Extraction on Point-sampled Surfaces[J].Computer Graphics Forum,2003,22(3):281-289.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700