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:胡飞 程剑 李瑞祥 孔铭泉 HU Fei;CHENG Jian;LI Ruixiang;KONG Mingquan(School of Information and Artificial Intelligence,Wuhu Institute of Technology,Wuhu 241006,China;Collaborative Innovation Center for Opto-Mechatronic Application Technology,Wuhu 241006,China)
机构地区:[1]芜湖职业技术学院信息与人工智能学院,安徽芜湖241006 [2]光机电一体化应用技术协同创新中心,安徽芜湖241006
出 处:《太原学院学报(自然科学版)》2023年第2期78-84,共7页Journal of TaiYuan University:Natural Science Edition
基 金:2020年度安徽高校自然科学研究项目(KJ2020A0927);芜湖职业技术学院校级科研团队(wzykjtd202004)。
摘 要:为实现无接触测量单摆系统的摆长与空间位置,采用基于局域网通信的网络摄像机,构建双目视觉测量系统,两台摄像机垂直放置并仅能拍摄到单摆物体末端的运动区域,Jetson Nano通过交换机获取两台摄像机拍摄后回传的图像,根据场景可选择基于HSV颜色空间方法或基于深度学习框架的YOLOv5方法,实现在动态图像中对单摆物体的跟踪并实时标记,并通过帧间的时间差与单摆物体的像素位置,计算单摆的摆长与空间位置。经实验,基于视觉的单摆测量系统测量摆长的精度小于2 cm,空间位置角度小于2°。In order to realize the non-contact measurement of the pendulum length and spatial position of the simple pendulum system,a binocular vision measurement system is constructed by using a network camera based on LAN communication.Two IP cameras are placed vertically,and the end motion area of the simple pendulum object can be observed.The platform-Jetson Nano acquires the images captured by two cameras through the switch,and the HSV color space method or YOLOv5 method based on the deep learning framework can be selected according to the scene;the simple pendulum object is tracked and marked in the dynamic image,and the pendulum length and spatial position are calculated by the time difference between frames and the pixel position of the simple pendulum object.Experimental results show that the precision of the length of simple pendulum measurement system based on vision is less than 2cm,and that the spatial position angle is less than 2°.
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:216.73.216.170