RGBD-Delta棉花打顶装置视觉系统标定方法  

Calibration method of the RGBD-Delta visual system for cotton topping device

作　　者：彭强吉 赵露强 陈玉龙 杨茹莎 张敬文 康建明 PENG Qiangji;ZHAO Luqiang;CHEN Yulong;YANG Rusha;ZHANG Jingwen;KANG Jianming(Shandong Academy of Agricultural Machinery Sciences,Jinan 250100,China;Colleges of Agricultural Engineering and Food Science,Shandong University of Technology,Zibo 255000,China)

机构地区：[1]山东省农业机械科学研究院,济南250100 [2]山东理工大学农业工程与食品科学学院,淄博255000

出　　处：《农业工程学报》2024年第19期12-20,共9页Transactions of the Chinese Society of Agricultural Engineering

基　　金：山东省农机研发制造推广应用一体化试点项目(NJYTHSD-202317)。

摘　　要：针对RGBD相机和Delta并联机械臂棉花打顶装置视觉系统标定精度低、相机视野区与机械臂工作区分离导致标定难度增加的问题,该研究提出了一种适用于相机视野区与工作区域分离的DAHEC(disjoint area visual calibration)视觉标定方法。搭建搭载RGBD相机和Delta并联机械臂传送带试验台,构建完整视觉关联系统,借助Python/OpenCV视觉程序与TSAI视觉标定法进行对比试验。对试验平均定位误差、离散情况及偏移误差统计分析,结果表明:DAHEC视觉标定法偏移误差为(4.72±0.86) mm,TSAI视觉标定法偏移误差为(7.97±1.46) mm,DAHEC标定法优于TSAI法。依据Box-Behnken设计三因素试验,以光照强度、机械臂累计运动次数、相机标定板距离为试验因素,以偏移误差小于圆盘刀半径为评价指标,分析各因素对偏移误差的影响,确定了棉花打顶刀的工作参数。正交试验结果表明:各因素对偏移误差影响显著性顺序为相机标定板距离、机械臂累计运动次数、光照强度;工作参数最优组合为光照强度为800 lx,机械臂累计运动次数为99次,相机标定板距离(RGBD相机到棉花顶芽的距离)为300~560 mm。最优工作参数下,打顶验证试验的平均偏移误差为9.76 mm,偏移误差在圆盘刀半径范围内,打顶率为93.75%,漏打率为6.25%。该研究结果可为棉花打顶装置视觉系统标定和作业参数设置提供科学依据。This study addressed several significant challenges encountered in the visual calibration of RGBD cameras and Delta parallel robots used in cotton topping devices.Specifically,it tackled the issues of the separation between the camera's field-of-view and the operational space,as well as the problem of insufficient calibration accuracy.An innovative approach known as Disjoint Area Visual Calibration(DAHEC)was proposed to address these issues effectively.The study explored the principles and procedures of visual calibration technology and,based on cotton planting patterns and topping requirements,selected an eye-to-hand visual calibration method.The DAHEC method was specifically developed to handle situations where the camera's field-of-view is separate from the operational space.By leveraging the principles of projective geometry and least-squares estimation,the DAHEC method simplifies the calibration process and enhances accuracy.An experimental setup was constructed to integrate the RGBD camera with a Delta parallel robot mounted on a conveyor belt,establishing a comprehensive visual relationship system.A visualization program was developed using Python and OpenCV,and comparative experiments were conducted against the traditional TSAI visual calibration method.Detailed statistical analysis was performed on average positioning errors,dispersion characteristics,and offset errors from these comparative experiments.The results indicated that the DAHEC method achieved an offset error of(4.72±0.86)mm,whereas the TSAI method had an offset error of(7.97±1.46)mm,demonstrating a clear advantage of the DAHEC method over TSAI.To further optimize the calibration process,a three-factor experiment was designed using Box-Behnken design theory,with lighting intensity,arm cumulative movement,and camera calibration board distance as experimental factors.The main objective was to ensure that the offset error remained within the acceptable range of the disk knife radius.Orthogonal tests were conducted to analyze the impact of thes

关 键 词：农业机械 视觉标定 Delta机械臂 RGBD相机 棉花打顶 

分 类 号：S23[农业科学—农业机械化工程] TP24[农业科学—农业工程]