一种拟人空间机械臂视觉伺服图像处理研究  

A Personification Space Robot Arm Visual Servoing Image Processing Research

作　　者：胡硕[1] 王芳[1] 秦利[1] 刘福才[1] 

机构地区：[1]燕山大学工业计算机控制工程河北省重点实验室,河北秦皇岛066004

出　　处：《控制工程》2015年第1期25-31,共7页Control Engineering of China

基　　金：国家高技术研究发展计划(863计划)资助课题;国家自然科学基金资助项目(61271409);国家自然科学基金资助项目(61005034);河北省自然科学基金资助项目(F2012203182)

摘　　要：针对四自由度串并混联拟人空间机械臂本体,构建了基于运动控制卡模式的机器人软件和硬件系统。采用基于位置的控制结构,利用所求得的机械臂逆运动学方程,设计了由图像反馈和末端运动组成的视觉伺服控制系统。提出了一种基于SURF特征的静态目标识别算法,算法首先对目标图像提取SURF特征,并利用欧氏距离实现模板图像与目标图像特征点匹配,然后计算已匹配特征点的质心来获得目标的位置信息,最终实现了稳定的伺服定位。实验结果证明了系统的可靠性,并且证明了四自由度串并混联机械臂本体在实际运动的精确性和稳定性。For the four degrees of freedom serial-parallel personification space robot arm, a new system which is based on the robot motion control card is proposed. By using the location of control structure and IKP inferential of robot arm, the system which consists of image feedback and terminal movement is designed. With the SURF, a static target identification algorithm is conducted. Firstly, the SURF features of template image and target image are extracted and matched by the Euclid distance method. Then the coordinates of object are gotten by calculating controid of features matched, and a stable servo positioning system is performed finally. The experimental results prove that the system is effective, and the movement is accurate and stable.

关 键 词：串并混联机械臂 视觉伺服 目标匹配 SURF 

分 类 号：TP242.62[自动化与计算机技术—检测技术与自动化装置]