A spatial consistency-based point cloud registration method for the same platform

doi:10.11947/j.AGCS.2023.20220262

Abstract

Abstract: The feature-based point cloud registration establishes the correspondence by using the feature descriptor. However, due to the influence of noise and repetitive structure, there will inevitably be a large number of mismatches, resulting in a fall in registration accuracy. In this paper, a spatial consistency-based registration (SCR) method was developed for the point cloud from the same platform. SCR makes full advantage of geometric information between discrete points to improve the point cloud registration accuracy. The graph model of the point cloud that is collected by the same platform is constructed by increasing the number of candidates, and an optimization of reweight random walks matching (RRWM) was proposed to obtain the optimal result. The point cloud registration was built using the hypothesis-and-verify approach. Comprehensive experiments demonstrate that the proposed SCR algorithm is effective in registration methods.

Key words: point cloud registration, feature matching, outlier filtering, graph matching

CLC Number:

P232

ZHANG Guangyun, HAN Yi, ZHANG Rongting, LI Mingfeng, JI Wenlai. A spatial consistency-based point cloud registration method for the same platform[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(5): 789-797.

References

[1] 闫利, 戴集成, 谭骏祥, 等. SLAM激光点云整体精配准位姿图技术[J]. 测绘学报, 2019, 48(3):313-321.DOI:10.11947/j.AGCS.2019.20170716. YAN Li, DAI Jicheng, TAN Junxiang, et al. Global fine registration of point cloud in LiDAR SLAM based on pose graph[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(3):313-321. DOI:10.11947/j.AGCS.2019.20170716.
[2] YAN Li, DAI Jicheng, TAN Junxiang, et al. Global fine registration of point cloud in LiDAR SLAM based on pose graph[J]. Journal of Geodesy and Geoinformation Science, 2020, 3(2):26-35.
[3] BESL P J, MCKAY N D. A method for registration of 3D shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(2):239-256.
[4] 闫利, 谭骏祥, 刘华, 等. 融合遗传算法和ICP的地面与车载激光点云配准[J]. 测绘学报, 2018, 47(4):528-536. DOI:10.11947/j.AGCS.2018.20170235. YAN Li, TAN Junxiang, LIU Hua, et al. Registration of TLS and MLS point cloud combining genetic algorithm with ICP[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(4):528-536.DOI:10.11947/j.AGCS.2018.20170235.
[5] 孙文潇, 王健, 梁周雁, 等. 法线特征约束的激光点云精确配准[J]. 武汉大学学报(信息科学版), 2020, 45(7):988-995. SUN Wenxiao, WANG Jian, LIANG Zhouyan, et al. Accurate registration of laser point cloud based on normal feature constraint[J]. Geomatics and Information Science of Wuhan University, 2020, 45(7):988-995.
[6] RUSU R B, BLODOW N, BEETZ M. Fast point feature histograms (FPFH) for 3D registration[C]//Proceedings of 2009 IEEE International Conference on Robotics and Automation. Kobe:IEEE, 2009:3212-3217.
[7] CHOY C, PARK J, KOLTUN V. Fully Convolutional Geometric Features[C]//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision.Seoul:IEEE,2019:8958-8966.
[8] DENG Haowen, BIRDAL T, ILIC S. PPFNet:global context aware local features for robust 3D point matching[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake:IEEE, 2018:195-205.
[9] 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.
[10] SALTI S, TOMBARI F, STEFANO L D. SHOT:Unique signatures of histograms for surface and texture description[J]. Computer Vision and Image Understanding, 2014, 125:251-264.
[11] DONG Zhen,LIANG Fuxun,YANG Bisheng, et al. Registration of large-scale terrestrial laser scanner point clouds:a review and benchmark[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 163:327-342.
[12] LOWE D G. Distinctive image features from scale invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[13] RUBNER Y, TOMASI C, GUIBAS L J. The earth mover's distance as a metric for image retrieval[J]. International Journal of Computer Vision, 2000, 40(2):99-121.
[14] BRADSKI G, The OpenCV Library. Dr. Dobb's Journal of Software Tools[DB/OL]. http://opencv.arg/.2000.
[15] ZHOU Qianyi, PARK J, KOLTUN V. Fast global registration[M]//Proceedings of 2016 Computer Vision-ECCV European Conference, Amsterdam, The Netherlands. Springer International Publishing, 2016:766-782.
[16] LEE J, KIM S, CHO M, et al. Deep hough voting for robust global registration[C]//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision. Montreal:IEEE, 2021:15974-15983.
[17] LEORDEANU M, HEBERT M. A spectral technique for correspondence problems using pairwise constraints[C]//Proceedings of the 10th IEEE International Conference on Computer Vision. Beijing:IEEE, 2005:1482-1489.
[18] CHO M, LEE J, LEE K M. Reweighted random walks for graph matching[C]//Proceedings of the 11th European conference on Computer vision:Part V. New York:ACM Press, 2010:492-505.
[19] CHO M, SUN Jian, DUCHENNE O, et al. Finding matches in a haystack:a max-pooling strategy for graph matching in the presence of outliers[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus, OH, USA. IEEE, 2014:2091-2098.
[20] 李彩林, 王志勇, 俞路路, 等. 最邻近曲面约束的近景光学影像与地面激光点云几何配准[J]. 测绘学报, 2020, 49(8):1014-1022. DOI:10.11947/j.AGCS.2020.20190146. LI Cailin, WANG Zhiyong, YU Lulu, et al. Geometric registration of close-range optical image and terrestrial laser point cloud constrained by nearest surface[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(8):1014-1022. DOI:10.11947/j.AGCS.2020.20190146.
[21] FISCHLER M A, ROBERT C B. Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6):381-395.
[22] PAIS G D, RAMALINGAM S, GOVINDU V M, et al. 3DRegNet:a deep neural network for 3D point registration[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Seattle, WA:IEEE,2020:7193-7203.
[23] BAI Xuyang, LUO Zixin, ZHOU Lei, et al. PointDSC:robust point cloud registration using deep spatial consistency[C]//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville:IEEE, 2021:15859-15869.
[24] CHOY C, DONG Wei, KOLTUN V. Deep global registration[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle:IEEE, 2020:2511-2520.
[25] ZHONG Yu. Intrinsic shape signatures:a shape descriptor for 3D object recognition[C]//Proceedings of 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops. Kyoto:IEEE, 2010:689-696.
[26] GUO Yulan, BENNAMOUN M, SOHEL F, et al. A comprehensive performance evaluation of 3D local feature descriptors[J]. International Journal of Computer Vision, 2016, 116(1):66-89.
[27] LI Jiayuan. GESAC:robust graph enhanced sample consensus for point cloud registration[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 167:363-374.
[28] MUNKRES J. Algorithms for the assignment and transportation problems[J]. Journal of the Society for Industrial and Applied Mathematics, 1957, 5(1):32-38.
[29] SORKINE O, RABINOVICH M. Least-squares rigid motion using SVD[J]. Computing, 2017, 1(1):1-5.
[30] ZENG A, SONG S, NIEßNER M, et al. 3DMatch:learning the matching of local 3D geometry in range scans[C]//Proceedings of 2017 Conference on Computer Vision and Pattern Recognition. Honolulu:IEEE,2017:08182.
[31] ZHOU Q Y, PARK J, KOLTUN V. Open3D:A modern library for 3D data processing[J/OL].[2018-01-30]. https://arXiv.org/abs/1801.09847.