| 基于机器视觉的茄科幼苗切削特征识别 |
| |
| 引用本文： | 贾 靖,赵 晖,周 磊,费焕强,龚征绛,喻擎苍.基于机器视觉的茄科幼苗切削特征识别[J].教育技术导刊,2020,19(1):25-31. |
| |
| 作者姓名： | 贾 靖 赵 晖 周 磊 费焕强 龚征绛 喻擎苍 |
| |
| 作者单位： | 浙江理工大学 信息学院，浙江 杭州 310018 |
| |
| 基金项目： | 国家自然科学基金项目（51375460） |
| |
| 摘 要： | 为了提升蔬菜自动嫁接机嫁接自动化程度，在嫁接过程中实现机器替代人眼进行操作，基于机器视觉分析茄科幼苗轮廓链特征参数、幼苗轮廓链链角变化、跨距、水平截线宽度、幼苗估计苗茎及幼苗中心线斜率参数，确定幼苗子叶、真叶和根部位置，根据幼苗轮廓特征结合曲线拟合确定切削点位置和切削角度，使用100幅蕃茄幼苗图像进行实验。实验表明，基于机器视觉的幼苗切削参数特征识别及定位准确率较高，幼苗轮廓链提取准确为97%，切削点位置与切削角度确定的准确率分别为93%和90%。因此基于机器视觉可以快速、准确地确定切削点位置及切削角度，提高嫁接机嫁接过程中嫁接操作准确率及幼苗成活率。
|
| 关 键 词： | 机器视觉 轮廓提取 特征识别 切削点 切削角度 曲线拟合 |
| 收稿时间： | 2019-04-15 |
Cutting Feature Recognition of Solanaceae Seedlings Based on Machine Vision |
| |
| JIA Jing,ZHAO Hui,ZHOU Lei,FEI Huan-qiang,GONG Zheng-jiang,YU Qing-cang.Cutting Feature Recognition of Solanaceae Seedlings Based on Machine Vision[J].Introduction of Educational Technology,2020,19(1):25-31. |
| |
| Authors: | JIA Jing ZHAO Hui ZHOU Lei FEI Huan-qiang GONG Zheng-jiang YU Qing-cang |
| |
| Institution: | School of Information Science and Technology， Zhejiang Sci-Tech University， Hangzhou 310018， China |
| |
| Abstract: | In order to improve the automation degree of the grafting process of vegetable automatic grafting machine， the replacement of the eyes of the staff in the grafting process is realized. Based on machine vision analysis of the characteristic parameters of the chain profile of Solanaceae seedlings， analysis of the chain chain angle change， span， horizontal section width， seedling stem and seedling centerline slope parameters of seedlings to determine cotyledons， true leaves and seedlings of seedlings The position of the root was determined according to the contour characteristics of the seedlings and the curve fitting to determine the position of the cutting point and the cutting angle. Experiments were carried out using 100 tomato seedling images. Experiments show that the machine vision-based seedling cutting parameters feature recognition and positioning accuracy is high， the seedling contour chain extraction accuracy is 97%， the cutting point position and cutting angle determination accuracy are 93% and 90% respectively. Based on machine vision， the position and cutting angle of the cutting point can be determined quickly and accurately， and the accuracy of the grafting operation and the survival rate of the seedlings in the grafting process of the grafting machine are improved. |
| |
| Keywords: | machine vision contour extraction feature recognition cutting point cutting angle curve fitting |
|
| 点击此处可从《教育技术导刊》浏览原始摘要信息 |
| 点击此处可从《教育技术导刊》下载免费的PDF全文 |
