Second-order Spatial Measures Low Overlap Rate Point Cloud Registration Algorithm Based On FPFH Features 1

Abstract

When the sensor dynamically collects point cloud data for object or map reconstruction, the registration effect is poor and reconstruction application is difficult with a too low overlap rate of the collected point cloud data. The reason is that the objects are covered, the sensor rotation angle is too large and the speed of movement is too fast. Because of these problems, this paper proposes a point cloud registration algorithm based on FPFH feature matching, combined with second-order spatial measures. Firstly, using the FPFH feature extraction algorithm, the features of each point are extracted, and then feature matching is performed to generate the set of feature point pairs. Secondly, the second-order spatial measure is used to calculate the set of feature point pairs to obtain the second-order spatial measure matrix scores and sort them. Finally, the dichotomy method is used to find the appropriate second-order spatial measure scores for distinguishing the inner points (points in the overlap region) from the outer points (points that do not belong to the overlap region as well as the mismatched points and some disturbances). The contrast experiments between this algorithm and three common point cloud registration algorithms, FPFH-ICP, 4PCS-ICP, and NDT-ICP, on the Stanford dataset and 3DMatch dataset shows that the registration accuracy of the other algorithms decreases significantly with a low overlap rate. But this algorithm still has a high registration accuracy and is less affected by outliers than the other algorithms. Besides, this algorithm can still maintain a good registration effect on different data sets.

Keywords

Low overlap FPFH second-order spatial measures dichotomy point cloud registration

Get full access to this article

View all access options for this article.

References

Aiger ,

N.J.

Mitra and

Cohen-Or , 4-points congruent sets for robust pairwise surface registration, ACM (2008).

Aoki ,

Goforth ,

R.A.

Srivatsan and

Lucey , PointNetLK: Robust & Efficient Point Cloud Registration using PointNet, 2019.

M.S.

Bartlett , The frequency distribution of the difference between two independent variates following the same Poisson distribution, Journal of the Royal Statistical Society: Series A (General) 100(3) (1937), 296–302.

P.J.

Besl and

H.D.

Mckay , A method for registration of 3-D shapes, IEEE Transactions on Pattern Analysis & Machine Intelligence 14(2) (1992), 239–256. doi:10.1109/34.121791.

Biber , The normal distributions transform: A new approach to laser scan matching, 2003.

Bressler , Method of printing a 3d model from point cloud data, 2020.

Chao and

Chang-Bo , Point cloud reconstruction rapid algorithm for 3D printing, Journal of Donghua University (Natural Science) (2016).

Chen ,

Liu ,

Wang and

Li , PointDSC: Robust point cloud registration using deep spatial consistency, IEEE Transactions on Pattern Analysis and Machine Intelligence (2021).

Choy ,

Dong and

Koltun , Deep global registration, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 2514–2523.

10.

Chum and

Matas , Matching with PROSAC – progressive sample consensus, in: Computer Vision and Pattern Recognition, 2005.

11.

Dai ,

Nießner ,

Zollhoefer ,

Izadi and

Theobalt , BundleFusion: Real-time globally consistent 3D reconstruction using on-the-fly surface re-integration, Acm Transactions on Graphics 36(3) (2017), 76a.

12.

Dimitris and

Ntzoufras , Analysis of sports data by using bivariate Poisson models, Journal of the Royal Statistical Society (2003).

13.

M.A.

Fischler and

R.C.

Bolles , Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography – ScienceDirect, Readings in Computer Vision (1987), 726–740.

14.

Hu ,

Mellado ,

Mitra and

Aiger , 4 PCS Fast Global Pointcloud Registration via Smart Indexing, 2015.

15.

Jiaze ,

Hao and

Guohua , Registration optimization algorithm for 3D cultural relics point clouds model, Journal of Computer-Aided Design & Computer Graphics (2016).

16.

Karlis and

Ntzoufras , Bayesian analysis of the differences of count data, Statistics in Medicine 25(11) (2010), 1885–1905. doi:10.1002/sim.2382.

17.

Le ,

T.T.

Do ,

Hoang and

N.M.

Cheung , SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondences, 2019.

18.

Li ,

Lu ,

Liu and

Guo , Super edge 4-points congruent sets-based point cloud global registration, Remote Sensing 13 (2021).

19.

Lian ,

Li ,

Gu ,

Bian and

He , Path planning method based on discontinuous grid partition algorithm of point cloud for in situ printing, Rapid Prototyping Journal (2019).

20.

Liu ,

Fan and

Zhang , MaskNet: A fully-convolutional network to estimate inlier points, in: 2019 IEEE International Conference on Robotics and Automation (ICRA), IEEE, 2019, pp. 3796–3802.

21.

Ma ,

Jiang ,

Qin and

Tan , Vision-based indoor positioning method by joint using 2D images and 3D point cloud map, in: International Wireless Communications and Mobile Computing Conference, 2020.

22.

Marc , The Stanford 3D Scanning Repository, 2003.

23.

Montuori et al., Combined use of ground-based systems for cultural heritage conservation monitoring, in: IGARSS 2014 & 35th CSRS, 2014.

24.

R.A.

Newcombe ,

Izadi ,

Hilliges ,

Molyneaux and

A.W.

Fitzgibbon , KinectFusion: Real-time dense surface mapping and tracking, in: IEEE International Symposium on Mixed & Augmented Reality, 2012.

25.

G.D.

Pais ,

Ramalingam ,

V.M.

Govindu ,

J.C.

Nascimento ,

Chellappa and

Miraldo , 3DRegNet: A Deep Neural Network for 3D Point Registration, 2019.

26.

Pajdla and

Matas , Recognizing Objects in Range Data Using Regional Point Descriptors, eccv, 2004.

27.

A.P.

Placitelli and

Gallo , 3D point cloud sensors for low-cost medical in-situ visualization, in: IEEE BIBM’11 Proceedings of the 2011 IEEE International Conference on Bioinformatics and Biomedicine, 2011.

28.

C.R.

Qi ,

Su ,

Mo and

L.J.

Guibas , PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation, IEEE, 2017.

29.

Rusinkiewicz and

Levoy , Efficient variants of the ICP algorithm, in: Proceedings Third International Conference on 3-D Digital Imaging and Modeling, 2002.

30.

R.B.

Rusu ,

Blodow and

Beetz , Fast Point Feature Histograms (FPFH) for 3D registration, in: IEEE International Conference on Robotics & Automation, 2009.

31.

R.B.

Rusu ,

Blodow ,

Z.C.

Marton and

Beetz , Aligning point cloud views using persistent feature histograms, in: 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, Acropolis Convention Center, Nice, France, September 22–26, 2008, 2008.

32.

Shuyu ,

Ning ,

Li ,

Chunkang and

University , Adaptive slicing-based compression algorithm with cultural relics point clouds, Application Research of Computers (2018).

33.

J.P.D.

Silva ,

D.L.

Borges and

F.D.B.

Vidal , A dynamic approach for approximate pairwise alignment based on 4-points congruence sets of 3D points, IEEE (2011).

34.

Tashi ,

Ullah and

Kubo , Geometric modeling and 3D printing using recursively generated point cloud, Mathematical and Computational Applications 24(3) (2019), 1(83)–21(83). doi:10.3390/mca24030083.

35.

Tombari ,

Salti and

Di Stefano , Unique signatures of histograms for local surface description, Lecture Notes in Computer Science 6313 (2010), 356–369. doi:10.1007/978-3-642-15558-1_26.

36.

C.Y.

Tsai ,

C.W.

Wang and

W.Y.

Wang , Design and implementation of a RANSAC RGB-D mapping algorithm for multi-view point cloud registration, in: Automatic Control Conference, 2014.

37.

Wang and

J.M.

Solomon , Deep Closest Point: Learning Representations for Point Cloud Registration, 2019.

38.

Wang ,

Zhu ,

Shen and

Zhang , The Method and Performance Analysis of Constructing Visual Point Cloud Map to Assist Inertial Positioning, 2020.

39.

Whelan ,

Leutenegger ,

R.F.

Salas-Moreno† ,

Glocker† and

A.J.

Davison , ElasticFusion: Dense SLAM Without a Pose Graph, in: Robotics: Science & Systems, 2015.

40.

Wu ,

Li and

Yan , 3D scene reconstruction based on improved ICP algorithm, Microprocessors and Microsystems 75(12) (2020), 103064. doi:10.1016/j.micpro.2020.103064.

41.

Zeng ,

Song ,

Niener ,

Fisher ,

Xiao and

Funkhouser , 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions, 2016.

42.

Zhang ,

Li ,

Zhang ,

Wang and

Wang , SC2-PCR: A second order spatial compatibility for efficient and robust point cloud registration, IEEE Transactions on Image Processing (2021).

43.

Q.-Y.

Zhou ,

Park and

Koltun , Fast global registration, in: European Conference on Computer Vision, Springer, 2016, pp. 766–782.

44.

Lee ,

Kim ,

Cho and

Park , Deep hough voting for robust global registration, Proceedings of the IEEE/CVF international conference on computer vision (2021), pages 15994–16003.

45.

Abdi , Singular value decomposition (SVD) and generalized singular value decomposition, Encyclopedia of measurement and statistics, volume 907, number 912, pages 44, (2007), publisher Thousand Oaks (CA) Sage.