基于特征提取的点云自动配准优化研究
|
摘要
针对三维点云自动配准精度不高、鲁棒性不强等问题,提出一种基于判断点云邻域法向量夹角的自动配准算法。该算法首先计算点云中每个点的法向量与邻域点集的法向量夹角的余弦值,然后把邻域各点的余弦值作为该点的属性特征向量,进行特征分类提取特征点,根据几何特征的相似性初步搜索匹配点对,并采用欧式距离约束条件剔除匹配错误的点对;运用最小二乘法计算初始配准参数,再通过改进的迭代最近点(Iterative Closest Point,ICP)算法进行精匹配。实验证明,该算法相对于经典的ICP算法无论收敛速度还是匹配精度上都有提升。
In this paper,based on judging the angle between neighboring normal points of point cloud,an automatic registration algorithm is proposed to solve the problems of low accuracy and robustness of 3 D point cloud auto-registration.The algorithm firstly computes the cosine of the angle between the normal vector of each point in the point cloud and the normal vector set of the neighboring point set,and then takes the cosine of each point in the neighborhood as the attribute feature vector of the point.The algorithm extracts feature points by feature classification.In accordance with the similarity of the geometric features,the matching pairs are preliminarily searched,then the Euclidean distance constraint is used to eliminate matching pairs.The least squares method is used to calculate the initial registration parameters,then the refined Iterative Closest Point(ICP)algorithm is used for fine matching.Experiments show that the algorithm has improved both in convergence speed and matching accuracy with respect to the classic ICP algorithm.
In this paper,based on judging the angle between neighboring normal points of point cloud,an automatic registration algorithm is proposed to solve the problems of low accuracy and robustness of 3 D point cloud auto-registration.The algorithm firstly computes the cosine of the angle between the normal vector of each point in the point cloud and the normal vector set of the neighboring point set,and then takes the cosine of each point in the neighborhood as the attribute feature vector of the point.The algorithm extracts feature points by feature classification.In accordance with the similarity of the geometric features,the matching pairs are preliminarily searched,then the Euclidean distance constraint is used to eliminate matching pairs.The least squares method is used to calculate the initial registration parameters,then the refined Iterative Closest Point(ICP)algorithm is used for fine matching.Experiments show that the algorithm has improved both in convergence speed and matching accuracy with respect to the classic ICP algorithm.
引文
[1]安冬,盖绍彦,达飞鹏.一种新的基于条纹投影的三维轮廓测量系统模型[J].光学学报,2014,34(5):122-127.
[2]Li Z,Shi Y,Wang C,et al.Accurate calibration method for a structured light system[J].Optical Engineering,2008,47(5):525-534.
[3]Li Z.Hybrid parallel computing architecture for multiview phase shifting[J].Optical Engineering,2014,53(11):112214.
[4]吕江昭,达飞鹏,郑东亮.基于Sierra Lite抖动算法的散焦投影光栅测量[J].光学学报,2014,34(3):127-135.
[5]雷玉枕,李中伟,钟凯,等.基于随机抽样一致算法的误匹配标志点校正方法[J].光学学报,2013,33(3):0315002.
[6]Besl P J,Mckay N D.A method for registration of 3-D shapes[J].IEEE Transactions on PAMI,1992,14(2):239-256.
[7]Levoy M,Pulli K,Curless B,et al.The digital Michelangelo project:3D scanning of large statues[C]//Conference on Computer Graphics and Interactive Techniques.ACM Press/Addison-Wesley Publishing Co,2001:131-144.
[8]朱延娟,周来水,张丽艳.散乱点云数据配准算法[J].计算机辅助设计与图形学学报,2006,18(4):475-481.
[9]张广鹏,张艳宁,郭哲.基于精确主轴分析及ICP的三维人脸配准[J].计算机工程与应用,2006,42(29):62-64.
[10]刘艳丰.基于kd-tree的点云数据空间管理理论与方法[D].长沙:中南大学,2009.
[11]陶海跻,达飞鹏.一种基于法向量的点云自动配准方法[J].中国激光,2013,40(8):179-184.
[12]钟莹,张蒙.基于改进ICP算法的点云自动配准技术[J].控制工程,2014,21(1):37-40.
[13]Chen Y,Medioni G.Object modeling by registration of multiple range images[C]//1991 IEEE International Conference on Robotics and Automation,1991:2724-2729.
[14]Chen C S,Hung Y P,Cheng J B.RANSAC-based DARCES:a new approach to fast automatic registration of partially overlapping range images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1999:1229-1234.
[15]马忠玲,周明全,耿国华,等.一种基于曲率的点云自动配准算法[J].计算机应用研究,2015,32(6):1878-1880.
[16]Fukai H,Xu G.Fast and robust registration of multiple3D point clouds[C]//RO-MAN,2011:331-336.
[17]刘晓东,刘国荣,王颖,等.散乱数据点的k近邻搜索算法[J].微电子学与计算机,2006,23(4):23-28.
[18]李德江,殷福忠,孙利民.基于特征点的点云压缩方法研究[J].测绘通报,2012(1):39-41.
[19]刘正.三维点云法向量估计方法研究[D].河北保定:华北电力大学,2015.
[20]黄源,达飞鹏,陶海跻.一种基于特征提取的点云自动配准算法[J].中国激光,2015,42(3):242-248.
[21]Andreetto M,Brusco N,Cortelazzo G M.Automatic 3D modeling of textured cultural heritage objects[J].IEEE Transactions on Image Processing,2004,13(3):354-369.
[22]Barnea S,Filin S.Keypoint based autonomous registration of terrestrial laser point-clouds[J].ISPRS Journal of Photogrammetry&Remote Sensing,2008,63(1):19-35.
[23]Akca D.Matching of 3D surfaces and their intensities[J].ISPRS Journal of Photogrammetry&Remote Sensing,2007,62(2):112-121.
[24]Horn B K P.Closed-form solution of absolute orientation using unit quaternions[J].Journal of the Optical Society of America A,1987,4(4):629-642.
[25]Arun K S,Huang T S,Blostein S D.Least-squares fitting of two 3-D point sets[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1987,9(5):698-700.
[26]李凤霞,饶永辉,刘陈,等.基于法向夹角的点云数据精简算法[J].系统仿真学报,2012,24(9):1980-1983.
[27]Mian A S,Bennamoun M,Owens R.Three-dimensional model-based object recognition and segmentation in cluttered scenes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(10):1584-1601.
[28]姚吉利,贾象阳,马宁,等.地面激光扫描多站点云整体定向平差模型[J].测绘学报,2014,43(8):835-841.
[2]Li Z,Shi Y,Wang C,et al.Accurate calibration method for a structured light system[J].Optical Engineering,2008,47(5):525-534.
[3]Li Z.Hybrid parallel computing architecture for multiview phase shifting[J].Optical Engineering,2014,53(11):112214.
[4]吕江昭,达飞鹏,郑东亮.基于Sierra Lite抖动算法的散焦投影光栅测量[J].光学学报,2014,34(3):127-135.
[5]雷玉枕,李中伟,钟凯,等.基于随机抽样一致算法的误匹配标志点校正方法[J].光学学报,2013,33(3):0315002.
[6]Besl P J,Mckay N D.A method for registration of 3-D shapes[J].IEEE Transactions on PAMI,1992,14(2):239-256.
[7]Levoy M,Pulli K,Curless B,et al.The digital Michelangelo project:3D scanning of large statues[C]//Conference on Computer Graphics and Interactive Techniques.ACM Press/Addison-Wesley Publishing Co,2001:131-144.
[8]朱延娟,周来水,张丽艳.散乱点云数据配准算法[J].计算机辅助设计与图形学学报,2006,18(4):475-481.
[9]张广鹏,张艳宁,郭哲.基于精确主轴分析及ICP的三维人脸配准[J].计算机工程与应用,2006,42(29):62-64.
[10]刘艳丰.基于kd-tree的点云数据空间管理理论与方法[D].长沙:中南大学,2009.
[11]陶海跻,达飞鹏.一种基于法向量的点云自动配准方法[J].中国激光,2013,40(8):179-184.
[12]钟莹,张蒙.基于改进ICP算法的点云自动配准技术[J].控制工程,2014,21(1):37-40.
[13]Chen Y,Medioni G.Object modeling by registration of multiple range images[C]//1991 IEEE International Conference on Robotics and Automation,1991:2724-2729.
[14]Chen C S,Hung Y P,Cheng J B.RANSAC-based DARCES:a new approach to fast automatic registration of partially overlapping range images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1999:1229-1234.
[15]马忠玲,周明全,耿国华,等.一种基于曲率的点云自动配准算法[J].计算机应用研究,2015,32(6):1878-1880.
[16]Fukai H,Xu G.Fast and robust registration of multiple3D point clouds[C]//RO-MAN,2011:331-336.
[17]刘晓东,刘国荣,王颖,等.散乱数据点的k近邻搜索算法[J].微电子学与计算机,2006,23(4):23-28.
[18]李德江,殷福忠,孙利民.基于特征点的点云压缩方法研究[J].测绘通报,2012(1):39-41.
[19]刘正.三维点云法向量估计方法研究[D].河北保定:华北电力大学,2015.
[20]黄源,达飞鹏,陶海跻.一种基于特征提取的点云自动配准算法[J].中国激光,2015,42(3):242-248.
[21]Andreetto M,Brusco N,Cortelazzo G M.Automatic 3D modeling of textured cultural heritage objects[J].IEEE Transactions on Image Processing,2004,13(3):354-369.
[22]Barnea S,Filin S.Keypoint based autonomous registration of terrestrial laser point-clouds[J].ISPRS Journal of Photogrammetry&Remote Sensing,2008,63(1):19-35.
[23]Akca D.Matching of 3D surfaces and their intensities[J].ISPRS Journal of Photogrammetry&Remote Sensing,2007,62(2):112-121.
[24]Horn B K P.Closed-form solution of absolute orientation using unit quaternions[J].Journal of the Optical Society of America A,1987,4(4):629-642.
[25]Arun K S,Huang T S,Blostein S D.Least-squares fitting of two 3-D point sets[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1987,9(5):698-700.
[26]李凤霞,饶永辉,刘陈,等.基于法向夹角的点云数据精简算法[J].系统仿真学报,2012,24(9):1980-1983.
[27]Mian A S,Bennamoun M,Owens R.Three-dimensional model-based object recognition and segmentation in cluttered scenes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(10):1584-1601.
[28]姚吉利,贾象阳,马宁,等.地面激光扫描多站点云整体定向平差模型[J].测绘学报,2014,43(8):835-841.