Novel 3D point set registration method based on regionalized Gaussian process map reconstruction

Bo LI; Yu ZHANG; Wen-jie ZHAO; Ping LI

doi:10.1631/FITEE.1900457

Your Location：

Home >

Browse articles >

Novel 3D point set registration method based on regionalized Gaussian process map reconstruction

Special Issue on Intelligent Unmanned Systems | Updated：2022-05-19

- Novel 3D point set registration method based on regionalized Gaussian process map reconstruction
- 基于区域化高斯过程地图重构的新型三维点集配准方法
- Frontiers of Information Technology & Electronic Engineering Vol. 21, Issue 5, Pages: 760-776(2020)
- Affiliations：
  
  School of Aeronautics and Astronautics, Zhejiang University, Hangzhou 310027, China
  State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China
- Author bio：
  
  [ "Bo LI, E-mail: jameslb20@hotmail.com" ]
  [ "Yu ZHANG, E-mail: zhangyu80@zju.edu.cn" ]
  Wen-jie ZHAO, zhaowenjie8@zju.edu.cn
  [ "Ping LI, E-mail: pli@iipc.zju.edu.cn" ]
- Funds：
- DOI：10.1631/FITEE.1900457
  CLC： TP242.6
- Received：31 August 2019，
  
  Revised：2020-;3-20，
  
  Published：2020-05
- Accepted：
Scan QR Code
Bo LI, Yu ZHANG, Wen-jie ZHAO, et al. Novel 3D point set registration method based on regionalized Gaussian process map reconstruction[J]. Frontiers of Information Technology & Electronic Engineering, 2020, 21(5): 760-776.
DOI：

Bo LI, Yu ZHANG, Wen-jie ZHAO, et al. Novel 3D point set registration method based on regionalized Gaussian process map reconstruction[J]. Frontiers of Information Technology & Electronic Engineering, 2020, 21(5): 760-776. DOI： 10.1631/FITEE.1900457.

摘要

点集配准问题是移动智能无人系统领域一项重要研究课题。本文提出一种全新"帧到地图"式三维点集配准方法。首先提出区域化高斯过程（Gaussian process，简称GP）地图重构算法，由此得到一种全新地图表现形式。将由GP得到的预测值和预测位置组合在一起作为预测点，以此自然地建立起预测点对的对应关系，并使用迭代方式计算位姿变换。利用3组标准点集数据集对该方法进行验证和测试。实验结果表明，相较于迭代最近点算法和正态分布变换两种经典点集配准方法，该方法在精度和效率两方面都有更佳表现。此外，所提的地图重构算法能够在降低内存消耗的同时，提供稠密的类点云地图。

Abstract

Point set registration has been a topic of significant research interest in the field of mobile intelligent unmanned systems. In this paper

we present a novel approach for a three-dimensional scan-to-map point set registration. Using Gaussian process (GP) regression

we propose a new type of map representation

based on a regionalized GP map reconstruction algorithm. We combine the predictions and the test locations derived from the GP as the predictive points. In our approach

the correspondence relationships between predictive point pairs are set up naturally

and a rigid transformation is calculated iteratively. The proposed method is implemented and tested on three standard point set datasets. Experimental results show that our method achieves stable performance with regard to accuracy and efficiency

on a par with two standard methods

the iterative closest point algorithm and the normal distribution transform. Our mapping method also provides a compact point-cloud-like map and exhibits low memory consumption.

关键词

Keywords

references

PJ Besl , , , ND McKay . . A method for registration of 3-D shapes . . IEEE Trans Patt Anal Mach Intell , , 1992 . . 14 ( ( 2 ): ): 239 - - 256 . . DOI: 10.1109/34.121791 http://doi.org/10.1109/34.121791 . .

C Cadena , , , L Carlone , , , H Carrillo , , , 等 . . Past, present, and future of simultaneous localization and mapping: toward the robust-perception age . . IEEE Trans Robot , , 2016 . . 32 ( ( 6 ): ): 1309 - - 1332 . . DOI: 10.1109/TRO.2016.2624754 http://doi.org/10.1109/TRO.2016.2624754 . .

Y Chen , , , G Medioni . . Object modeling by registration of multiple range images . . Proc IEEE Int Conf on Robotics and Automation , , 1991 . . p.2724 - - 2729 . . DOI: 10.1109/ROBOT.1991.132043 http://doi.org/10.1109/ROBOT.1991.132043 . .

K Doherty , , , JK Wang , , , B Englot . . Bayesian generalized kernel inference for occupancy map prediction . . Proc IEEE Int Conf on Robotics and Automation , , 2017 . . p.3118 - - 3124 . . DOI: 10.1109/ICRA.2017.7989356 http://doi.org/10.1109/ICRA.2017.7989356 . .

G Grisetti , , , R Kümmerle , , , C Stachniss , , , 等 . . A tutorial on graph-based SLAM . . IEEE Intell Transp Syst Mag , , 2010 . . 2 ( ( 4 ): ): 31 - - 43 . . DOI: 10.1109/MITS.2010.939925 http://doi.org/10.1109/MITS.2010.939925 . .

V Guizilini , , , F Ramos . . Variational Hilbert regression for terrain modeling and trajectory optimization . . Int J Robot Res , , 2019 . . 38 ( ( 12-13 ): ): 1375 - - 1387 . . DOI: 10.1177/0278364919844586 http://doi.org/10.1177/0278364919844586 . .

W Hess , , , D Kohler , , , H Rapp , , , 等 . . Real-time loop closure in 2D LIDAR SLAM . . Proc IEEE Int Conf on Robotics and Automation , , 2016 . . p.1271 - - 1278 . . DOI: 10.1109/ICRA.2016.7487258 http://doi.org/10.1109/ICRA.2016.7487258 . .

A Hornung , , , KM Wurm , , , M Bennewitz , , , 等 . . OctoMap: an efficient probabilistic 3D mapping framework based on octrees . . Auton Robot , , 2013 . . 34 ( ( 3 ): ): 189 - - 206 . . DOI: 10.1007/s10514-012-9321-0 http://doi.org/10.1007/s10514-012-9321-0 . .

S Kim , , , J Kim . . Continuous occupancy maps using overlapping local Gaussian processes . . Proc IEEE/RSJ Int Conf on Intelligent Robots and Systems , , 2013 . . p.4709 - - 4714 . . DOI: 10.1109/IROS.2013.6697034 http://doi.org/10.1109/IROS.2013.6697034 . .

B Li , , , YQ Wang , , , Y Zhang , , , 等 . . GP-SLAM: laser-based SLAM approach based on regionalized Gaussian process map reconstruction . . Auton Robot, in press , , 2020 . . DOI: 10.1007/s10514-020-09906-z http://doi.org/10.1007/s10514-020-09906-z . .

M Magnusson , , , A Lilienthal , , , T Duckett . . Scan registration for autonomous mining vehicles using 3D-NDT . . J Field Robot , , 2007 . . 24 ( ( 10 ): ): 803 - - 827 . . DOI: 10.1002/rob.20204 http://doi.org/10.1002/rob.20204 . .

ST O'Callaghan , , , FT Ramos . . Gaussian process occupancy maps . . Int J Robot Res , , 2012 . . 31 ( ( 1 ): ): 42 - - 62 . . DOI: 10.1177/0278364911421039 http://doi.org/10.1177/0278364911421039 . .

C Plagemann , , , K Kersting , , , W Burgard . . Nonstationary Gaussian process regression using point estimates of local smoothness . . Proc European Conf on Machine Learning and Knowledge Discovery in Databases , , 2008 . . p.204 - - 219 . . DOI: 10.1007/978-3-540-87481-2-14 http://doi.org/10.1007/978-3-540-87481-2-14 . .

F Pomerleau , , , M Liu , , , F Colas , , , 等 . . Challenging data sets for point cloud registration algorithms . . Int J Robot Res , , 2012 . . 31 ( ( 14 ): ): 1705 - - 1711 . . DOI: 10.1177/0278364912458814 http://doi.org/10.1177/0278364912458814 . .

CE Rasmussen , , , CKI Williams . . Gaussian Processes for Machine Learning , , : : Cambridge, USA The MIT Press , , 2006 . . .

JP Saarinen , , , H Andreasson , , , T Stoyanov , , , 等 . . 3D normal distributions transform occupancy maps: an efficient representation for mapping in dynamic environments . . Int J Robot Res , , 2013 . . 32 ( ( 14 ): ): 1627 - - 1644 . . DOI: 10.1177/0278364913499415 http://doi.org/10.1177/0278364913499415 . .

J Salvi , , , C Matabosch , , , D Fofi , , , 等 . . A review of recent range image registration methods with accuracy evaluation . . Image Vis Comput , , 2007 . . 25 ( ( 5 ): ): 578 - - 596 . . DOI: 10.1016/j.imavis.2006.05.012 http://doi.org/10.1016/j.imavis.2006.05.012 . .

YR Shen , , , AY Ng , , , M Seeger . . Fast Gaussian process regression using kd-trees . . Proc Annual Conf on Neural Information Processing Systems , , 2006 . . p.1225 - - 1232 . . http://d.old.wanfangdata.com.cn/NSTLHY/NSTL_HYCC026236226/ http://d.old.wanfangdata.com.cn/NSTLHY/NSTL_HYCC026236226/ , , . .

M Smith , , , I Posner , , , P Newman . . Efficient non-parametric surface representations using active sampling for push broom laser data . . Proc Robotics: Science and Systems , , 2010 . . DOI: 10.15607/RSS.2010.VI.027 http://doi.org/10.15607/RSS.2010.VI.027 . .

T Stoyanov , , , M Magnusson , , , H Andreasson , , , 等 . . Fast and accurate scan registration through minimization of the distance between compact 3D NDT representations . . Int J Robot Res , , 2012 . . 31 ( ( 12 ): ): 1377 - - 1393 . . DOI: 10.1177/0278364912460895 http://doi.org/10.1177/0278364912460895 . .

S Thrun , , , W Burgard , , , D Fox . . Probabilistic Robotics , , : : Cambridge, USA The MIT Press , , 2005 . . .

S Vasudevan , , , F Ramos , , , E Nettleton , , , 等 . . Gaussian process modeling of large scale terrain . . Proc IEEE Int Conf on Robotics and Automation , , 2009 . . p.1047 - - 1053 . . DOI: 10.1109/ROBOT.2009.5152677 http://doi.org/10.1109/ROBOT.2009.5152677 . .

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

Hybrid-driven Gaussian process online learning for highly maneuvering multi-target tracking

Ahybrid-model optimization algorithm based on the Gaussian process and particle swarm optimization for mixed-variable CNN hyperparameter automatic search

Related Author

Qiang GUO

Long TENG

Tianxiang YIN

Yunfei GUO

Xinliang WU

Wenming SONG

Han YAN

Chongquan ZHONG

Related Institution

College of Information and Communication Engineering, Harbin Engineering University

China National Aeronautical Radio Electronics Research Institute

College of Automation, Hangzhou Dianzi University

School of Control Science and Engineering, Dalian University of Technology

Chat

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
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