基于双目视觉技术的茶叶嫩芽定位方法研究  

Research on Tea Bud Location Method Based on Binocular Vision Technology

在线阅读下载全文

作  者:朱龙舜[1] 郑旻璐 Zhu Longshun;Zheng Minlu(Southeast University Cheng Xian College,Nanjing 210088,China;Nanjing Vocational Institute of Mechatronic Technology,Nanjing 211306,China)

机构地区:[1]东南大学成贤学院,南京210088 [2]南京机电职业技术学院,南京211306

出  处:《农机化研究》2025年第2期49-53,共5页Journal of Agricultural Mechanization Research

基  金:江苏省教育科学“十四五”规划项目(D/2021/03/36)。

摘  要:进一步提升茶叶嫩芽定位的准确性及茶叶嫩芽采摘的作业效率,选取双目视觉技术作为切入点,针对其识别、定位、采摘等环节展开设计研究。考虑茶叶嫩芽采摘的基础特征和双目视觉技术的应用条件,合理搭建双目视觉模型,选用立体匹配的核心定位算法,完成茶叶嫩芽的定位方法与采摘功能优化,并布置相应的试验机构,展开定位采摘验证试验。结果表明:基于双目视觉技术的茶叶嫩芽定位方法应用具有显著的优越性,较普通定位方法而言,识别误匹配率可降低至4.01%,平均漏采率为3.20%,嫩芽采摘完整率达93.40%,可以很好地促进茶叶嫩芽的后续处理加工,是采摘茶叶嫩芽的品质化的重要基础保障。In order to further improve the accuracy of tea bud location and the efficiency of tea bud picking,the binocular vision technology was selected as the entry point to carry out design research on its identification,positioning,picking and other links.Considering the basic characteristics of tea buds picking and the application conditions of binocular vision technology,the binocular vision model was reasonably built,the core positioning algorithm of stereo matching was selected,the positioning method and picking function optimization of tea buds were completed,and the corresponding test institutions were arranged,and the location picking verification test was carried out.The results showed that the application of tea buds location method based on binocular vision technology had significant advantages,compared with the common positioning method,the recognition error matching rate could be reduced to 4.01%,the average miss picking rate was 3.20%,and the complete picking rate of buds could reach 93.40%,which would well promote the subsequent processing of tea buds,and be an important basic guarantee for the quality of tea buds picked.

关 键 词:茶叶嫩芽定位 双目视觉 立体匹配 采摘完整率 品质化 

分 类 号:S126[农业科学—农业基础科学] TP391.41[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象