坐标点分布对三维坐标变换参数估计不确定度的影响（英文）  

Influence of common feature points distribution on uncertainty of 3D coordinate transformation parameter estimation

作　　者：朱程广 赵健康[1] 龙海辉[1] 夏轩 王红雨[1] ZHU Chengguang;ZHAO Jiankang;LONG haihui;XIA Xuan;WANG Hongyu(School of Electronic and Electrical Engineering,Shanghai Jiao Tong University,Shanghai 200240,China;Shenzhen Institute of Advanced Technology,Chinese Academy of sciences,Shenzhen 518000,China)

机构地区：[1]上海交通大学电子信息与电气工程学院,上海200240 [2]中国科学院深圳先进技术研究所,深圳518000

出　　处：《中国惯性技术学报》2019年第4期460-465,共6页Journal of Chinese Inertial Technology

基　　金：科技部重大专项（2016YFC0200402）;国家自然科学基金（61806190）

摘　　要：相机坐标系和目标坐标系中公共特征点的测量精度和相对几何分布对参数估计具有重要影响,直接影响视觉导航精度。由于坐标点的测量精度依赖于测量系统的精度,而公共点的分布选取更容易调整,因此仅讨论公共特征点相对几何分布对平移旋转参数估计精度的影响。首先,采用非线性模型和加权整体最小二乘算法求解变换参数,并采用蒙特卡罗方法归纳总结了不同的特征点分布对参数估计精度的影响。同时,为了工程化应用,将坐标点分布的分散度进行量化作为其权重,提出一种重构协因数矩阵的方法。最后,基于实际测量数据的对比试验表明,在没有先验知识的情况下,所提出的方法可以改善参数的估计精度,即变换参数的后验标准差至少减小6.7%。Measurement precision and relative geometric distribution of common feature points are two factors affecting the parameter estimation and then the visual navigation precision.In view that the relative geometric distribution is easier to be adjusted than the measurement precision,the influence of the relative geometric distribution on the estimation accuracy of translation and rotation parameters is only discussed.Firstly,the nonlinear model and the weighted global least square algorithm are used to solve transformation parameters,and Monte Carlo method is used to summarize the influence of different feature points distribution on parameter estimation accuracy.Then,a method of reconstructing cofactor matrix is proposed,which quantifies the dispersion of coordinate point distribution as its weight for engineering application.Finally,comparison tests are carried out based on actual measurement data,which shows that the proposed method can improve the estimation accuracy of parameters without prior knowledge,where the posterior standard deviation of transformation parameters is reduced by at least 6.7%.

关 键 词：三维坐标变换 不确定度 加权整体最小二乘 蒙特卡洛方法 

分 类 号：U666.1[交通运输工程—船舶及航道工程]