摘要
针对现代农业自动化嫁接机的嫁接过程中,嫁接夹的分拣整理仍然需要使用刚性振动盘或人工参与,整体自动化程度有待提高的问题,提出基于机器视觉的嫁接夹轮廓链特征点定位方法与朝向检测;设计了一种自动化嫁接专用的嫁接夹,采用背光源打光方式,对每个阴影轮廓计算Hu矩,根据Hu矩匹配值进行分类以获得正确的嫁接夹个体轮廓;对每个嫁接夹个体轮廓采用轮廓链角分析方法,获得嫁接夹抓取点的像素位置;根据抓取点位置信息计算朝向角度;实验结果表明,嫁接夹抓取点平均定位误差为2.16个像素,嫁接夹朝向角度检测误差为0.40°;该方法可以准确地对嫁接夹进行视觉检测,对嫁接机的嫁接过程中,嫁接夹的自动分拣方面,具有机器视觉方面的价值。
In the grafting process of modern agricultural automated grafting machine,the sorting ofgrafting clips still requires the use of rigid shakers or manual involvement,and overall automation process needs to be improved.Aimed at this problem,a grafting clipgripping point positioningand orientationangle detection method based on machine vision is proposed;A grafting clip for automation grafting is designed,the backlighting method is used to calculate Hu moment for each shadow contour,and the matching valueof Hu moment isclassified to get the correct individual contour of the grafting clip;By the contour chain angle analysis,the individual contour for each grafting clip is appliedto obtain the pixel position of the grafting clip gripping point;The orientation angleof the grafting clip gripping point is calculatedby the position information of the gripping point;The experimental results show that the average positioning error of the grafting clip gripping point is 2.16 pixels,and the orientation angle detection error is 0.40 degrees;This methodrealizesthe visual inspection of thegrafting clipaccurately,and it is valuable in machine vision for the automatic sorting of grafting clips.
作者
黄铮
吴尧
赖一波
周杰
赵明朗
喻擎苍
HUANG Zheng;WU Yao;LAI Yibo;ZHOU Jie;ZHAO Minglang;YU Qingcang(School of ComputerScience,Zhejiang Sci-Tech University,Hangzhou 310000,China)
出处
《计算机测量与控制》
2023年第8期51-57,共7页
Computer Measurement &Control
关键词
机器视觉
嫁接夹
轮廓特征
HU矩
图像处理
machine vision
grafting clip
contourfeatures
Hu moment
image process