A point cloud registration algorithm based on ISS-SHOT features

doi:10.13474/j.cnki.11-2246.2020.0106

Abstract

Abstract: Aiming at the problems of error-corresponding points, slow convergence rate and long time for the point cloud registration, a registration algorithm based on theintrinsic shape signatures(ISS) and signature of histograms of orientations(SHOT) is proposed.After down-sampling by voxel grid method, the feature points of point cloud are extracted by the ISS algorithm, described by the SHOT and matched by the cosine similarity. Then, the wrong corresponding points are eliminated by the RANSAC algorithm, so that the two point clouds obtain a good initial positon. Finally, an accurate result can be obtained based on point to plane ICP algorithm.The experimental results show that compared with the traditional ICP algorithm and the ISS-based SAC-IA+ICP algorithm, the proposed algorithm has higher registration accuracy and efficiency, and it is robust to point clouds with large data quantity and low overlap rate.

Key words: ISS, SHOT, feature descriptor, point cloud registration, point to plane ICP

CLC Number:

P237

LI Yuxiang, GUO Jiming, PAN Shangyi, Lü Lili, LU Zhuxing, ZHANG Di. A point cloud registration algorithm based on ISS-SHOT features[J]. Bulletin of Surveying and Mapping, 2020, 0(4): 21-26.

References

[1] 王延亮, 夏国芳, 胡春梅. 利用三维激光扫描技术进行工业设备三维重建及变形分析[J]. 测绘通报, 2012(2):94-96.
[2] 刘坤, 樊廷立, 杨晶, 等. 复杂环境下基于移动测量技术的城市数字地表数据的获取[J]. 测绘通报, 2017(6):165-166.
[3] 陈弘奕, 胡晓斌, 李崇瑞. 地面三维激光扫描技术在变形监测中的应用[J]. 测绘通报, 2014(12):74-77.
[4] BESL P J, MCKAY N D. A method for registration of 3-D shapes[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1992, 14(2):239-256.
[5] CHEN Y, MEDIONI G G. Object modeling by registration of multiple range images[J]. Image and Vision Computing, 1992, 10(3):145-155.
[6] LI Q, GRIFFITHS J G. Iterative closest geometric objects registration[J]. Computers & Mathematics with Applications, 2000, 40(10):1171-1188.
[7] 刘斌, 郭际明, 邓祥祥. 结合八叉树和最近点迭代算法的点云配准[J]. 测绘科学, 2016, 41(2):130-132.
[8] JOHNSON A E, HEBERT M. Using spin images for efficient object recognition in cluttered 3D scenes[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2002, 21(5):433-449.
[9] RUSU R B, BLODOW N, MARTON Z C, et al. Aligning point cloud views using persistent feature histograms[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems.Nice:IEEE, 2008.
[10] RUSU R B, BLODOW N, BEETZ M. Fast point feature histograms (FPFH) for 3D registration[C]//IEEE International Conference on Robotics and Automation. Kobe:IEEE, 2009.
[11] GUOY, SOHEL F, BENNAMOUN M, et al. Rotational projection statistics for 3D local surface description and object recognition[J]. International Journal of Computer Vision, 2013, 105(1):63-86.
[12] 陆军, 彭仲涛, 夏桂华. 点云多法向量邻域特征配准算法[J]. 光电子·激光, 2015(4):28.
[13] 曾繁轩, 李亮, 刁鑫鹏. 基于曲率特征的迭代最近点算法配准研究[J]. 激光与光电子学进展, 2017(1):113-120.
[14] 胡修祥, 张良. 结合NARF特征的改进型3D-NDT多视点云配准[J]. 信号处理, 2015, 31(12):1674-1679.
[15] 舒程珣, 何云涛, 孙庆科. 基于卷积神经网络的点云配准方法[J]. 激光与光电子学进展, 2017(3):129-137.
[16] 李仁忠, 杨曼, 田瑜, 等. 基于ISS特征点结合改进ICP的点云配准算法[J]. 激光与光电子学进展, 2017,54(11):312-319.
[17] ZHONG Y. Intrinsic shape signatures:a shape descriptor for 3D object recognition[C]//Proceedings of the 12th IEEE International Conference on Computer Vision Workshops (ICCV Workshops). Kyoto:IEEE, 2009:689-696.
[18] SALTIS, TOMBARI F, DI STEFANO L. SHOT:Unique signatures of histograms for surface and texture description[J]. Computer Vision and Image Understanding, 2014, 125:251-264.
[19] FISCHLER M A. Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J]. Readings in Computer Vision, 1987:726-740.
[20] PULLI K. Multiview registration for large data sets[C]//Proceedings of the 2nd International Conference on 3D Digital Imaging and Modeling. Ottawa, Ontario:IEEE,1999.
[21] LI Bin. Three dimensional laser point cloud slicing method for calculating irregular Volume[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(4):31-43.