CLC number: TP242.6
On-line Access: 2020-05-18
Received: 2019-08-31
Revision Accepted: 2020-02-02
Crosschecked: 2020-03-20
Cited: 0
Clicked: 5298
Citations: Bibtex RefMan EndNote GB/T7714
Bo Li, Yu Zhang, Wen-jie Zhao, Ping Li. 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.
@article{title="Novel 3D point set registration method based on regionalized Gaussian process map reconstruction",
author="Bo Li, Yu Zhang, Wen-jie Zhao, Ping Li",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="21",
number="5",
pages="760-776",
year="2020",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.1900457"
}
%0 Journal Article
%T Novel 3D point set registration method based on regionalized Gaussian process map reconstruction
%A Bo Li
%A Yu Zhang
%A Wen-jie Zhao
%A Ping Li
%J Frontiers of Information Technology & Electronic Engineering
%V 21
%N 5
%P 760-776
%@ 2095-9184
%D 2020
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1900457
TY - JOUR
T1 - Novel 3D point set registration method based on regionalized Gaussian process map reconstruction
A1 - Bo Li
A1 - Yu Zhang
A1 - Wen-jie Zhao
A1 - Ping Li
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 21
IS - 5
SP - 760
EP - 776
%@ 2095-9184
Y1 - 2020
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1900457
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.
[1]Besl PJ, McKay ND, 1992. A method for registration of 3-D shapes. IEEE Trans Patt Anal Mach Intell, 14(2):239-256.
[2]Cadena C, Carlone L, Carrillo H, et al., 2016. Past, present, and future of simultaneous localization and mapping: toward the robust-perception age. IEEE Trans Robot, 32(6):1309-1332.
[3]Chen Y, Medioni G, 1991. Object modeling by registration of multiple range images. Proc IEEE Int Conf on Robotics and Automation, p.2724-2729.
[4]Doherty K, Wang JK, Englot B, 2017. Bayesian generalized kernel inference for occupancy map prediction. Proc IEEE Int Conf on Robotics and Automation, p.3118-3124.
[5]Grisetti G, Kümmerle R, Stachniss C, et al., 2010. A tutorial on graph-based SLAM. IEEE Intell Transp Syst Mag, 2(4):31-43.
[6]Guizilini V, Ramos F, 2019. Variational Hilbert regression for terrain modeling and trajectory optimization. Int J Robot Res, 38(12-13):1375-1387.
[7]Hess W, Kohler D, Rapp H, et al., 2016. Real-time loop closure in 2D LIDAR SLAM. Proc IEEE Int Conf on Robotics and Automation, p.1271-1278.
[8]Hornung A, Wurm KM, Bennewitz M, et al., 2013. OctoMap: an efficient probabilistic 3D mapping framework based on octrees. Auton Robot, 34(3):189-206.
[9]Kim S, Kim J, 2013. Continuous occupancy maps using overlapping local Gaussian processes. Proc IEEE/RSJ Int Conf on Intelligent Robots and Systems, p.4709-4714.
[10]Li B, Wang YQ, Zhang Y, et al., 2020. GP-SLAM: laser-based SLAM approach based on regionalized Gaussian process map reconstruction. Auton Robot, in press.
[11]Magnusson M, Lilienthal A, Duckett T, 2007. Scan registration for autonomous mining vehicles using 3D-NDT. J Field Robot, 24(10):803-827.
[12]O’Callaghan ST, Ramos FT, 2012. Gaussian process occupancy maps. Int J Robot Res, 31(1):42-62.
[13]Plagemann C, Kersting K, Burgard W, 2008. Nonstationary Gaussian process regression using point estimates of local smoothness. Proc European Conf on Machine Learning and Knowledge Discovery in Databases, p.204-219.
[14]Pomerleau F, Liu M, Colas F, et al., 2012. Challenging data sets for point cloud registration algorithms. Int J Robot Res, 31(14):1705-1711.
[15]Rasmussen CE, Williams CKI, 2006. Gaussian Processes for Machine Learning. The MIT Press, Cambridge, USA.
[16]Saarinen JP, Andreasson H, Stoyanov T, et al., 2013. 3D normal distributions transform occupancy maps: an efficient representation for mapping in dynamic environments. Int J Robot Res, 32(14):1627-1644.
[17]Salvi J, Matabosch C, Fofi D, et al., 2007. A review of recent range image registration methods with accuracy evaluation. Image Vis Comput, 25(5):578-596.
[18]Shen YR, Ng AY, Seeger M, 2006. Fast Gaussian process regression using kd-trees. Proc Annual Conf on Neural Information Processing Systems, p.1225-1232.
[19]Smith M, Posner I, Newman P, 2010. Efficient non-parametric surface representations using active sampling for push broom laser data. Proc Robotics: Science and Systems.
[20]Stoyanov T, Magnusson M, Andreasson H, et al., 2012. Fast and accurate scan registration through minimization of the distance between compact 3D NDT representations. Int J Robot Res, 31(12):1377-1393.
[21]Thrun S, Burgard W, Fox D, 2005. Probabilistic Robotics. The MIT Press, Cambridge, USA.
[22]Vasudevan S, Ramos F, Nettleton E, et al., 2009. Gaussian process modeling of large scale terrain. Proc IEEE Int Conf on Robotics and Automation, p.1047-1053.
Open peer comments: Debate/Discuss/Question/Opinion
<1>