检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:陈涛 刘娣[1] 乔贵方[1] 周霆威 田荣佳 CHEN Tao;LIU Di;QIAO Guifang;ZHOU Tingwei;TIAN Rongjia(School of Automation,Nanjing Institute of Technology,Nanjing 211167,China)
出 处:《组合机床与自动化加工技术》2023年第11期24-27,共4页Modular Machine Tool & Automatic Manufacturing Technique
基 金:国家自然科学基金项目(5190525);中国博士后科学基金项目(2019M650095);江苏省研究生科研与实践创新计划项目(SJCX21_0917,SJCX21_0930)。
摘 要:针对基于单目视觉的室内定位系统精度差的问题,提出了一种基于AprilTag标签和正多面体的正十二面体AprilTag靶标,并通过单目视觉检测该靶标的相对空间位姿。该靶标装置通过在正十二面体各个表面粘贴AprilTag标签,扩展了靶标的检测范围,同时结合多面体之间的约束关系,提升了位姿检测精度。通过搭建实验平台实施该靶标的位姿检测精度验证,实验结果表明提出的正十二面体AprilTag靶标的相对位姿检测精度明显优于单个AprilTag标签位姿检测精度,当采用相同尺寸的AprilTag标签时,相对位置误差降低了约83.6%,同时在3个轴向上的相对姿态误差分别减少了约95.2%、94.6%、89.1%。Aiming at the problem of poor accuracy of indoor positioning system based on monocular vision,this paper proposes a dodecahedral AprilTag target based on AprilTag tag and regular polyhedron.The relative spatial pose of the proposed target is detected by monocular visual sensor.The Apriltag tags are pasted on each surface of the regular dodecahedron to extend the detection range.Meanwhile,the pose detection accuracy is improved by combing the constraint relationship between multiple surfaces.An experimental platform was built to verify the pose detection accuracy of the proposed target.The experimental results show that the relative pose detection accuracy of the dodecahedral AprilTag target proposed in this paper is obviously better than that of a single AprilTag.When using AprilTag tags of the same size,the relative position error is reduced by about 83.6%,and the relative attitude error in the three axes is reduced by about 95.2%,94.6%,and 89.1%respectively.
关 键 词:多机器人 正多面体 定位系统 视觉系统 立体靶标 单目视觉
分 类 号:TH165[机械工程—机械制造及自动化] TG659[金属学及工艺—金属切削加工及机床]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.7