基于双目视觉的集装箱吊放位姿测量研究  

Research on Measurement of Container Lifting Posture Based on Binocular Vision

在线阅读下载全文

作  者:季娟娟 王佳[1] 高少薄 卢道华[1,2] JI Juan-juan;WANG Jia;GAO Shao-bo;LU Dao-hua(School of Mechanical Engineering,Jiangsu University of Science and Technology,Zhenjiang Jiangsu 212100,China;Marine Equipment and Technology Institute,Jiangsu University of Science and Technology,Zhenjiang Jiangsu 212003,China)

机构地区:[1]江苏科技大学机械工程学院,江苏镇江212100 [2]江苏科技大学海洋装备研究院,江苏镇江212003

出  处:《计算机仿真》2024年第5期296-302,共7页Computer Simulation

基  金:国家重点研发计划资助项目(2018YFC0309100)。

摘  要:为了解决港口集装箱运输装卸过程中吊放速率低的问题,提出了一种基于双目视觉的集装箱吊放位姿测量方法,该方法可使吊机操作员独立完成集装箱的吊放,使得港口装卸集装箱更加智能化。首先,通过HSV色彩空间的特征轮廓提取和改进的KCF算法来完成目标集装箱的识别与实时跟踪,再使用矩特征结合三维位姿检测算法来完成目标集装箱和龙门吊机吊具间的位姿测量。上述方法在目标集装箱与吊具间的偏角测量实验中的测量误差为-0.2~+0.4度,在相对距离测量实验中的测量误差为4mm左右,目标集装箱的检出率高达97%。实验结果表明,所提方法满足实际港口集装箱的吊放要求,可以准确地进行集装箱的吊放。In order to solve the problem of low lifting speed in the process of port container transportation and loading,a method of measuring the lifting posture of containers based on binocular vision is proposed.This method can make the crane operator complete the lifting of containers independently,and make the port container loading and unloading more intelligent.Firstly,the feature contour extraction of HSV color space and the improved KCF algorithm are used to complete the recognition and real-time tracking of the target container,and then the moment feature combined with the three-dimensional pose detection algorithm is used to complete the pose measurement between the target container and the gantry crane.The measurement error of this method is-0.2~+0.4 degrees in the deviation angle measurement experiment between the target container and the spreader,and about 4mm in the relative distance measurement experiment.The detection rate of the target container is as high as 97%.The experimental results show that this method meets the requirements of the actual port container lifting and placing,and can accurately lift and place the container.

关 键 词:双目视觉 位姿测量 集装箱 

分 类 号:TP391.41[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象