基于机器人运动参数与特征向量的标记点匹配方法

摘要

为提高移动摄影测量中相机定向方法的速度和柔性,提出一种基于机器人运动参数的相机定向方法.首先对机器人进行手眼标定,得出相机与机器人工具之间的相对位姿.然后利用手眼关系与机器人运动参数,将相机位姿统一到机器人基坐标系中,实现相机的自动定向.为消除极线约束匹配产生的歧义,本文提出一种基于特征向量的歧义匹配校正方法.实验表明,本文方法具有匹配率高、准确性高、速度快、柔性高的特点,适合智能制造中的在线精密测量.%In order to improve the speed and flexibility of camera orientation in the moving photogrammetry, a new method for camera orientation based on kinematics parameters of robot is proposed. Firstly, the hand-eye calibration is operated to get the spatial relationship between the camera and the tool fixed on the robot. Then the automatic orientation of camera is performed by unifying the positions to the base coordinate system with the use of hand-eye relation and robot kinematics parameters. In addition, the eigenvector approach is proposed to eliminate the matching ambiguity caused by the method based on epipolar constraint. Experiment results show that the proposed method is suitable for the on-line precision measurement in intelligent manufacturing with several wonderful features such as high matching rate, high accuracy, high speed and high flexibility.