机器人视觉中目标物的位姿估计改进  

Improvement on Pose Estimation of an Object in the Robotic Vision

作　　者：张磊[1,2] 张天益 姚兴田 吕栋阳[1] ZHANG Lei;ZHANG Tianyi;YAO Xingtian;LU Dongyang(School of Mechanical Engineering,Nantong University,Nantong 226019,China;Lassonde School of Engineering,York University,Toronto M3J 1P3,Canada)

机构地区：[1]南通大学机械工程学院,江苏南通226019 [2]约克大学拉松德工学院,加拿大多伦多M3J1P3

出　　处：《南通大学学报（自然科学版）》2021年第4期38-45,共8页Journal of Nantong University(Natural Science Edition)　

基　　金：江苏省“六大人才高峰”项目(2015-ZBZZ-023);南通市应用研究计划项目(GY12017017)。

摘　　要：针对经典直接线性变换(direct linear transformation,DLT)、EPNP(efficient perspective-n-point)等方法对目标物位姿估计存在精度不高的问题,提出一种目标物位姿估计改进方法。首先将DLT方法的计算过程进行了优化整理,使之更容易求解;然后引入非线性优化以提高精度,根据LM(Levenberg-Marquardt)优化算法的特点,提出了便于求解雅可比矩阵的代价函数,并引入李群李代数表达位姿微调矩阵,进一步方便了雅可比矩阵的求解,简化了位姿参数值的迭代估计。实验结果表明,提出的改进方法比经典DLT方法和EPNP方法精度有明显提高,也比DLT+数值LM方法精度有所提高,总体平均反投影误差为0.2690像素;提出的改进方法由于简化了雅可比矩阵计算,缩短了迭代时间,总体耗时比非线性优化的DLT+数值LM方法少,每幅图像平均耗时67.48 ms左右。提出的位姿估计方法在精度与迭代时间上有着良好的综合性能,具有较好的实际应用价值。In order to solve the problem of inaccurate pose estimation by the classical direct linear transformation(DLT)and efficient perspective-n-point(EPNP)methods,an improved method for pose estimation is proposed.The computation process of the DLT method is optimized for easy solving.The nonlinear optimization is introduced to improve its accuracy.A proper cost function is proposed based on the Levenberg-Marquardt(LM)algorithm for solving Jocabian matrix easily.The Li group and Li algebra are introduced for representing the tiny transformation of the pose matrix,which simplifies the solution of Jocabian matrix and iterative process of optimization.The experimental results show that the proposed method is much more accurate than the DLT and the EPNP methods,and is more accurate than the DLT+numerical value-based LM algorithm.The total mean image re-projection error is 0.2690 pixel.The time consuming experiments indicate that the proposed method needs less time compared with the DLT+numeriacl value-based LM algorithm.Its total average time is 67.48 ms per frame.These prove that the proposed method has comprehensively good performance in precision and time cost,which has good practical value.

关 键 词：机器人 位姿估计 直接线性变换 非线性优化 摄像机标定 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]