摘要
为提高工业机器人抓取物品的速度,提出一个基于机器视觉的目标姿态识别与定位的检测方案。采用图像中值滤波技术消除灰度图像噪声,利用改进遗传算法(genetic algorithm,GA)与最佳直方图(KSW)熵融合的方法实现图像的分割,得到需识别的对象,经过边缘检测技术提取边缘,由欧氏距离度量法识别物体的位姿,根据矩特征计算图像物体的质心坐标,根据摄像机标定算法转换到世界坐标,设计GUI(图形用户界面)集成相应的功能。实验结果表明,该方案能够有效缩短识别与定位的时间。
To improve the speed of industrial robots on grabbing items,a detection scheme based on machine vision for target pose recognition and positioning was proposed.Image median filtering was used to eliminate gray image noise.The improved genetic algorithm(GA)and optimal histogram(KSW)entropy fusion method were used to segment the image to obtain the object to be identified,and edge detection was implemented.The edge was extracted,the pose of the object was recognized using Euclidean distance metric,the centroid coordinate of the image object was calculated according to the moment feature,which was converted to the world coordinate according to the camera calibration algorithm,and the GUI(graphical user interface)was designed to integrate the corresponding function.Experimental results show that the proposed scheme can effectively shorten the time of identification and positioning.
作者
柴钰
许继科
CHAI Yu;XU Ji-ke(School of Electrical and Control Engineering,Xi’an University of Science and Technology,Xi’an 710054,China)
出处
《计算机工程与设计》
北大核心
2019年第12期3557-3562,共6页
Computer Engineering and Design
关键词
机器视觉
相似性度量
阈值分割
遗传算法
摄像机标定
machine vision
similarity measure
threshold segmentation
genetic algorithm
camera calibration