点线特征约束下基于单位四元数描述的LiDAR点云配准算法  

A unit quaternion based,point-linear feature constrained registration approach for terrestrial LiDAR point clouds

作　　者：王永波[1] 汪云甲[1] 韩新哲 佘雯雯 WANG Yongbo;WANG Yunjia;HAN Xinzhe;SHE Wenwen(Key Laboratory for Land Environment ~ Disaster Monitoring of SBSM, Jiangsu Key Laboratory of Resources and Environmental Information Engineering, China University of Mining and Technology, Xuzhou, Jiangsu 221116, China)

机构地区：[1]中国矿业大学国土环境与灾害监测国家测绘局重点实验室江苏省资源环境信息工程重点实验室,江苏徐州221116

出　　处：《中国矿业大学学报》2018年第3期671-677,共7页Journal of China University of Mining & Technology

基　　金：国家自然科学基金项目(41271444)

摘　　要：针对经典的基于直线特征约束的LiDAR点云配准算法对于直线方向的高度依赖性问题,立足于直线特征的Plücker坐标描述方法,以点到线的距离为零作为点云配准的基本约束,以单位四元数作为描述空间旋转变换的基本算子,构建了点线特征约束下基于Plücker直线坐标描述的LiDAR点云配准的基本模型;立足于最小二乘法的基本准则,以配准后同名特征之间的距离平方和最小作为约束条件,根据Lagrange乘数法组建了相应的目标函数,推导并给出了求解配准参数的迭代计算模型.通过实测数据对算法进行了验证.结果表明:Plücker直线坐标的引入使得点与直线间距离的计算变得更加简洁、高效;利用单位四元数来实现空间旋转变换的描述,一方面,减少了描述参数的冗余,另一方面,对于配准模型的构建,较之于经典的基于向量代数的描述方法更为简洁;此外,较之于基于向量代数描述的LiDAR点云配准算法,四元数的引入降低了算法对迭代初值的依赖性,对任意选择的初始参数,该算法均能够得到正确的迭代结果.Due to the fact that the correctness of most available linear feature based registration methods highly depend on the consistency of each conjugate line＇s direction,a Plücker coordinate based point cloud registration approach,which is based on the correspondences between point and linear features,was presented in this paper.Based on the assumption that the distance between each point and its conjugate linear feature is zero after registration,a new error norm was constructed by the introduction of unit quaternions.On the basis of the theory of extreme value analysis,that is,by minimizing of the quadratic sum of correction to each esti-mate,an adaptive calculation model was constructed,in which the detailed derivation of all formulas were given.Experiments show that the calculation of the distance between a point and a line will become more compact and effective by the introduction of Plücker coordinates,and with the aid of unit quaternions,only 4 parameters are needed to describe spatial rotation,more importantly,less constraints are needed in the construction of registration model.Moreover,with the available test data employed in the paper,the presented method＇s sensitiveness to initial estimates of unknown parameters are greatly reduced,which proves that the new method has low dependence on them.

关 键 词：点云 配准 LIDAR 单位四元数 Plücker坐标 

分 类 号：P231.2[天文地球—摄影测量与遥感] P237[天文地球—测绘科学与技术]