基于ISS特征点结合改进ICP的点云配准算法

针对迭代最近点(ICP)配准算法易陷入局部最优、迭代收敛速度慢等问题，提出基于内部描述子(ISS)特征点结合改进ICP点云配准算法，先对基准点云和待配准点云进行体素网格下采样，随后选用ISS算法提取特征点，采用点特征直方图(FPFH)对特征点进行特征描述，并寻找两片点云特征点的对应点对，之后利用随机采样一致性算法(RANSAC)算法去除错误对应点对，最后对已有良好初始位姿的两片点云采用基于Nanoflann加速的点到平面ICP算法进行精配准，将配准精度和配准效率进一步提高。试验结果表明，该算法比传统ICP算法迭代次数减少，在精度与速度方面均有显著提升；比尺度不变特征(SIFT)的ICP算法在欧氏适合度评分和配准用时上分别平均减少了64.4%和73.75%。

Abstract

To address the problems that the Iterative Closest Point (ICP) registration algorithm tends to fall into local optimum and slow convergence of iterations, this paper proposes an improved ICP point cloud registration algorithm based on Intrinsic Shape Signatures (ISS) feature point combination, which firstly down samples the reference point cloud and the point cloud to be aligned with voxel grid. Then extracts the feature points by ISS algorithm and uses Fast Point Feature Histogram (FPFH) to characterize the feature points. After that, this paper finds the corresponding point pairs of the two sets of point cloud feature points, and then uses Random Sample Consensus (RANSAC) to remove the wrong corresponding point pairs. Finally, the two sets of point clouds with good initial poses are accurately aligned by the point-to-plane ICP algorithm based on Nanoflann acceleration, which further improves the registration accuracy and registration efficiency. The experimental results show that the algorithm reduces the number of iterations compared with the traditional ICP algorithm, and has a significant improvement in accuracy and speed; compared with the Scale Invariant Feature (SIFT) ICP algorithm, the Euclidean fitness score and registration time are reduced on average respectively 64.4% and 73.75%.

参考文献

[1] 王庄. 基于3D激光打印的建筑景观可视化视觉艺术重建［J］. 应用激光, 2022, 42(4): 160-166.WANG Z. Visual art reconstruction of architectural landscape visualization based on 3D laser printing［J］. Applied Laser, 2022, 42(4): 160-166.

[2] 何士伟, 王健, 刘宇. 基于激光点云与倾斜影像的复杂表面重建［J］. 应用激光, 2021, 41(4): 909-915.HE S W, WANG J, LIU Y. Complex surface reconstruction based on laser point cloud and oblique image［J］. Applied Laser, 2021, 41(4): 909-915.

[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.CHEN H Y, HU X B, LI C R. Application of terrestrial 3D laser scanning technology in deformation monitoring［J］. Bulletin of Surveying and Mapping, 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 and Machine Intelligence, 1992, 14(2): 239-256.

[5] CHEN Y,MEDIONI G. Object modelling by registration of multiple range images［J］. Image and Vision Computing, 1992, 10(3): 145-155.

[6] LI Q D, GRIFFITHS J G. Iterative closest geometric objects registration［J］. Computers & Mathematics With Applications, 2000, 40(10/11): 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.LIU B, GUO J M, DENG X X. A point cloud registration method based on Octree and ICP［J］. Science of Surveying and Mapping, 2016, 41(2): 130-132.

[8] 沈跃, 潘成凯, 刘慧, 等. 基于改进SIFF-ICP算法的Kinect植株点云配准方法［J］. 农业机械学报, 2017, 48(12)：183-189.SHEN Y, PAN C K, LIU H, et al. Method of plant point cloud registration based on kinect of improved SIFT-ICP［J］. Transactions of the Chinese Society for Agricultural Machinery, 2017, 48(12)：183-189.

[9] 赵明富, 黄铮, 宋涛, 等. 融合采样一致性和迭代最近点算法的点云配准方法［J］. 激光杂志, 2019, 40(10): 45-50.ZHAO M F, HUANG Z, SONG T, et al. Point cloud registration method based on sample consensus initial alignment and iterative closest point algorithm［J］. Laser Journal, 2019, 40(10): 45-50.

[10] 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): 111503.LI R Z, YANG M, TIAN Y, et al. Point cloud registration algorithm based on ISS feature points combined with improved ICP［J］. Laser & Optoelectronics Progress, 2017, 54(11): 111503.

[11] 荆路, 武斌, 方锡禄. 基于SIFT特征点结合ICP的点云配准方法［J］. 激光与红外, 2021, 51(7): 944-950.JING L, WU B, FANG X L. Point cloud registration method based on the SIFT feature points combined with ICP algorithm［J］. Laser & Infrared, 2021, 51(7): 944-950.

[12] 李宇翔, 郭际明, 潘尚毅, 等. 一种基于ISS-SHOT特征的点云配准算法［J］. 测绘通报, 2020(4): 21-26.LI Y X, GUO J M, PAN S Y, et al. A point cloud registration algorithm based on ISS-SHOT features［J］. Bulletin of Surveying and Mapping, 2020(4): 21-26.

张赵良, 董一鸣, 朱菊香, 陆佳嘉. 基于ISS特征点结合改进ICP的点云配准算法[J]. 应用激光, 2023, 43(6): 0124. Zhang Zhaoliang, Dong Yiming, Zhu Juxiang, Lu Jiajia. An Improved ICP Point Cloud Registration Algorithm Based on ISS-FPFH Features[J]. APPLIED LASER, 2023, 43(6): 0124.

基于ISS特征点结合改进ICP的点云配准算法

关于本站 Cookie 的使用提示

全站搜索

基于ISS特征点结合改进ICP的点云配准算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索