浏览全部资源
扫码关注微信
1.山西省煤炭地质物探测绘院有限公司,山西 晋中 030600
2.山东科技大学 测绘空间信息学院,山东 青岛 266590
3.中国人民解放军战略支援部队信息工程大学 地理空间信息学院,河南 郑州 450001
Published:25 May 2024,
Received:29 November 2023,
Revised:20 February 2024,
移动端阅览
李晋儒,王晋,郭松涛等.基于自适应局部邻域条件下的点云匹配[J].光学精密工程,2024,32(10):1606-1621.
LI Jinru,WANG Jin,GUO Songtao,et al.Point cloud matching algorithm based on adaptive local neighborhood conditions[J].Optics and Precision Engineering,2024,32(10):1606-1621.
李晋儒,王晋,郭松涛等.基于自适应局部邻域条件下的点云匹配[J].光学精密工程,2024,32(10):1606-1621. DOI: 10.37188/OPE.20243210.1606.
LI Jinru,WANG Jin,GUO Songtao,et al.Point cloud matching algorithm based on adaptive local neighborhood conditions[J].Optics and Precision Engineering,2024,32(10):1606-1621. DOI: 10.37188/OPE.20243210.1606.
为了应对传统迭代最近点(ICP)算法在处理复杂点云空间特征时,面临噪声干扰和数据缺失等问题导致收敛速度缓慢、配准精度不高以及鲁棒性较差等问题,本文提出了一种基于自适应局部邻域条件下的点云匹配算法。首先,采用体素网格滤波对数据进行预处理,根据不同半径邻域内邻近点的分布情况,定义邻域表面的弯曲程度,在此基础上,充分考虑到法向量分布和邻域曲率特征,从而得到更精确的特征点提取;其次,通过运用最小二乘曲面拟合方法,进一步提取出邻域曲率变化最为显著的特征点,采用快速点特征直方图(FPFH)对特征点进行描述,并通过设定距离阈值的采样一致性算法来匹配相似的特征点对,计算出关键的坐标转换参数,完成初始配准。最后,利用线性最小二乘优化点到面的ICP算法,以实现更精确的配准结果。通过一系列实验对比发现相较于现有的几种配准算法(ICP,SAC-IA+ICP,K4PCS+ICP),在存在噪声干扰和数据缺失的情况下,所提方法的配准准确度平均提高45%,配准速度平均提高38%,充分验证了该方法在应对大数据量、低重叠率点云配准方面具备出色的稳健性能。
To address the issues faced by traditional Iterative Closest Point (ICP) algorithms in handling complex point cloud spatial features, such as noise interference and data loss leading to slow convergence, low registration accuracy, and pool robustness, this paper proposed a point cloud matching algorithm based on adaptive local neighborhood conditions. Initially, voxel grid filtering was used for data preprocessing, and the curvature of neighborhood surfaces was defined based on the distribution of nearby points within different radii. Considering the distribution of normal vectors and neighborhood curvature features, more accurate feature points were extracted. Subsequently, the most significantly changing curvature feature points in the neighborhood were further extracted using the least squares surface fitting method. These points were described using the Fast Point Feature Histograms (FPFH), and similar feature point pairs were matched using a sample consensus algorithm with a set distance threshold. This calculated the key coordinate transformation parameters to complete the initial registration. Finally, a linear least squares optimization point-to-plane ICP algorithm was used to achieve more accurate registration results. Comparative experiments demonstrate that, under conditions of noise interference and data loss, the proposed method improves registration accuracy by an average of 45% and increases registration speed by 38%, compared to existing algorithms (ICP, SAC-IA+ICPK4PCS+lCP), thus confirming its excellent robustness in handling large-volume, low-overlap point cloud registrations.
点云匹配邻域法向量快速点特征直方图迭代最近点
point cloud matchingneighborhoodnormal vectorfast point feature histogramiterative closest point
张岱伟, 许彪, 董友强, 等. 一种局部平差影像添加策略的三维重建方法[J]. 测绘科学, 2020, 45(6): 103-109, 133.
ZHANG D W, XU B, DONG Y Q, et al. The 3D-reconstruction based on a new strategy of adding images[J]. Science of Surveying and Mapping, 2020, 45(6): 103-109, 133.(in Chinese)
WANG G H, CHENG J. Three-dimensional reconstruction of hybrid surfaces using perspective shape from shading[J]. Optik, 2016, 127(19): 7740-7751. doi: 10.1016/j.ijleo.2016.05.120http://dx.doi.org/10.1016/j.ijleo.2016.05.120
JUN M. Target detection and recognition algorithm for moving UAV based on machine vision[J]. Cluster Computing, 2019, 22(2): 4263-4269. doi: 10.1007/s10586-018-1857-0http://dx.doi.org/10.1007/s10586-018-1857-0
WANG Z H, ZHAO Y, WANG S G. Approach for improving efficiency of three-dimensional object recognition in light-field display[J]. Optical Engineering, 2019, 58(12): 1. doi: 10.1117/1.oe.58.12.123101http://dx.doi.org/10.1117/1.oe.58.12.123101
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. doi: 10.1109/34.121791http://dx.doi.org/10.1109/34.121791
RUSU R B, BLODOW N, BEETZ M. Fast point feature histograms (FPFH) for 3D registration[C]. 2009 IEEE International Conference on Robotics and Automation. Kobe, Japan. IEEE, 2009: 3212-3217. doi: 10.1109/robot.2009.5152473http://dx.doi.org/10.1109/robot.2009.5152473
RUSU R B, BLODOW N, MARTON Z C, et al. Aligning point cloud views using persistent feature histograms[C]. 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems. Nice, France. IEEE, 2008: 3384-3391. doi: 10.1109/iros.2008.4650967http://dx.doi.org/10.1109/iros.2008.4650967
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. doi: 10.1109/34.765655http://dx.doi.org/10.1109/34.765655
SALTI S, 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. doi: 10.1016/j.cviu.2014.04.011http://dx.doi.org/10.1016/j.cviu.2014.04.011
刘飞, 黄瀚霖, 杨恬, 等. 面向狭窄场景的鲁棒多视角配准方法[J]. 红外与激光工程, 2022, 51(12): 3788/IRLA20220114.
LIU F, HUANG H L, YANG T, et al. Robust multi-view registration method for narrow scenes[J]. Infrared and Laser Engineering, 2022, 51(12): 3788/IRLA20220114.(in Chinese)
孙培芪, 卜俊洲, 陶庭叶, 等. 基于特征点法向量的点云配准算法[J]. 测绘通报, 2019(8): 48-53.
SUN P Q, BU J Z, TAO T Y, et al. Point cloud registration algorithm based on feature point method vector[J]. Bulletin of Surveying and Mapping, 2019(8): 48-53.(in Chinese)
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. doi: 10.3788/lop54.111503http://dx.doi.org/10.3788/lop54.111503
LI R Z, YANG M, TIAN Y, et al. Point cloud registration algorithm based on the ISS feature points combined with improved ICP algorithm[J]. Laser & Optoelectronics Progress, 2017, 54(11): 111503.(in Chinese). doi: 10.3788/lop54.111503http://dx.doi.org/10.3788/lop54.111503
马骊溟, 徐毅, 李泽湘. 基于高斯曲率极值点的散乱点云数据特征点提取[J]. 系统仿真学报, 2008, 20(9): 2341-2344.
MA L M, XU Y, LI Z X. Extracting feature points for scattered points based on Gauss curvature extreme point[J]. Journal of System Simulation, 2008, 20(9): 2341-2344.(in Chinese)
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, 26(4): 780-787.
LU J, PENG Z T, XIA G H. Point cloud registration algorithm based on neighborhood features of multi-scale normal vectors[J]. Journal of Optoelectronics·Laser, 2015, 26(4): 780-787.(in Chinese)
LIU Y S, KONG D H, ZHAO D D, et al. A point cloud registration algorithm based on feature extraction and matching[J]. Mathematical Problems in Engineering, 2018, 2018: 7352691. doi: 10.1155/2018/7352691http://dx.doi.org/10.1155/2018/7352691
LIN C C, TAI Y C, LEE J J, et al. A novel point cloud registration using 2D image features[J]. EURASIP Journal on Advances in Signal Processing, 2017, 2017(1): 5. doi: 10.1186/s13634-016-0435-yhttp://dx.doi.org/10.1186/s13634-016-0435-y
THEILER P W, WEGNER J D, SCHINDLER K. Markerless point cloud registration with keypoint-based 4-points congruent sets[J]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2013, II-5/W2: 283-288. doi: 10.5194/isprsannals-ii-5-w2-283-2013http://dx.doi.org/10.5194/isprsannals-ii-5-w2-283-2013
胡春梅, 费华杰, 夏国芳, 等. 激光扫描与摄影测量异源点云高精度配准方法[J]. 激光与光电子学进展, 2022, 59(24): 2415007. doi: 10.3788/LOP202259.2415007http://dx.doi.org/10.3788/LOP202259.2415007
HU C M, FEI H J, XIA G F, et al. High-precision registration of non-homologous point clouds in laser scanning and photogrammetry[J]. Laser & Optoelectronics Progress, 2022, 59(24): 2415007.(in Chinese). doi: 10.3788/LOP202259.2415007http://dx.doi.org/10.3788/LOP202259.2415007
徐文菲, 金莉, 韩旭, 等. 面向缺失点云配准的镜像迭代最近点算法[J]. 西安交通大学学报, 2023, 57(7): 201-212, 220. doi: 10.7652/xjtuxb202307019http://dx.doi.org/10.7652/xjtuxb202307019
XU W F, JIN L, HAN X, et al. Mirrored iterative closest point algorithm for missing point cloud registration[J]. Journal of Xi’an Jiaotong University, 2023, 57(7): 201-212, 220.(in Chinese). doi: 10.7652/xjtuxb202307019http://dx.doi.org/10.7652/xjtuxb202307019
刘今越, 张港, 贾晓辉, 等. 基于曲率阈值的点云配准方法研究[J]. 激光与光电子学进展, 2022, 59(18): 466-472. doi: 10.3788/LOP202259.1828006http://dx.doi.org/10.3788/LOP202259.1828006
LIU J Y, ZHANG G, JIA X H, et al. Point cloud registration method based on curvature threshold[J]. Laser & Optoelectronics Progress, 2022, 59(18): 466-472.(in Chinese). doi: 10.3788/LOP202259.1828006http://dx.doi.org/10.3788/LOP202259.1828006
杨鹏程, 杨朝, 孟杰, 等. 基于法向量和面状指数特征的文物点云棱界配准方法[J]. 中国光学(中英文), 2023, 16(3): 654-662. doi: 10.37188/co.2022-0156http://dx.doi.org/10.37188/co.2022-0156
YANG P C, YANG Z, MENG J, et al. Aligning method for point cloud prism boundaries of cultural relics based on normal vector and faceted index features[J]. Chinese Optics, 2023, 16(3): 654-662.(in Chinese). doi: 10.37188/co.2022-0156http://dx.doi.org/10.37188/co.2022-0156
张赵良, 董一鸣, 朱菊香, 等. 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): 124-131.
ZHANG Z L, DONG Y M, ZHU J X, et al. An improved ICP point cloud registration algorithm based on ISS-FPFH features[J]. Applied Laser, 2023, 43(6): 124-131.(in Chinese)
余永维, 王康, 杜柳青, 等. 点云模型的匹配点对优化配准[J]. 光学 精密工程, 2023, 31(4): 503-516. doi: 10.37188/ope.20233104.0503http://dx.doi.org/10.37188/ope.20233104.0503
YU Y W, WANG K, DU L Q, et al. Matching point pair optimization registration method for point cloud model[J]. Opt. Precision Eng., 2023, 31(4): 503-516.(in Chinese). doi: 10.37188/ope.20233104.0503http://dx.doi.org/10.37188/ope.20233104.0503
AIJAZI A K, CHECCHIN P. Non-repetitive scanning LiDAR sensor for robust 3D point cloud registration in localization and mapping applications[J]. Sensors, 2024, 24(2): 378. doi: 10.3390/s24020378http://dx.doi.org/10.3390/s24020378
KIRSCH A, GÜNTER A, KÖNIG M. Predicting alignability of point cloud pairs for point cloud registration using features[C]. 2022 12th International Conference on Pattern Recognition Systems (ICPRS). Saint-Etienne, France. IEEE, 2022: 1-6. doi: 10.1109/icprs54038.2022.9854071http://dx.doi.org/10.1109/icprs54038.2022.9854071
GAO Q H, ZHAO Y, XI L, et al. Break and splice: a statistical method for non-rigid point cloud registration[J]. Computer Graphics Forum, 2023, 42(6): e14788. doi: 10.1111/cgf.14788http://dx.doi.org/10.1111/cgf.14788
XU N, QIN R, SONG S. Point cloud registration for LiDAR and photogrammetric data: a critical synthesis and performance analysis on classic and deep learning algorithms[J]. ISPRS open journal of photogrammetry and remote sensing, 2023, 8:100032. doi: 10.1016/j.ophoto.2023.100032http://dx.doi.org/10.1016/j.ophoto.2023.100032
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 W X, WANG J, LIANG Z Y, 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.(in Chinese)
YANG M, LEE E. Segmentation of measured point data using a parametric quadric surface approximation[J]. Computer-Aided Design, 1999, 31(7): 449-457. doi: 10.1016/s0010-4485(99)00042-1http://dx.doi.org/10.1016/s0010-4485(99)00042-1
李新春, 闫振宇, 林森, 等. 基于邻域特征点提取和匹配的点云配准[J]. 光子学报, 2020, 49(4): 0415001. doi: 10.3788/gzxb20204904.0415001http://dx.doi.org/10.3788/gzxb20204904.0415001
LI X C, YAN Z Y, LIN S, et al. Point cloud registration based on neighborhood characteristic point extraction and matching[J]. Acta Photonica Sinica, 2020, 49(4): 0415001.(in Chinese). doi: 10.3788/gzxb20204904.0415001http://dx.doi.org/10.3788/gzxb20204904.0415001
0
Views
24
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution