基于双视角OpenMV的水果体积测量系统设计  

Design of fruit volume measurement system based on dual-view OpenMV

作　　者：李新超 孙国玺 LI Xin-chao;SUN Guo-xi(School of Electronic Information Engineering,Guangdong University of Petrochemical Technology,Maoming 525000,Guangdong Province,China)

机构地区：[1]广东石油化工学院电子信息工程学院,广东茂名525000

出　　处：《信息技术》2024年第11期57-62,共6页Information Technology

基　　金：广东省科技专项资金项目(2021S0078,pdjh2021a0330);广东省教育厅高校自然科学研究项目(2020KTSCX083);茂名市科技专项资金项目(2021KJZXZJGSPDX001,20-19S001004);广东石油化工学院博士启动项目(519004)。

摘　　要：在水果自动化分级和加工等过程中,快速获取水果体积等果形参数具有重要价值。针对现有水果体积等参数测量方案复杂且成本高的问题,文中设计了基于双视角OpenMV的水果体积参数测量系统,采用同一高度成90°放置的两个OpenMV摄像头采集水果图像数据,并结合摄像头参数在线测量水果的果形参数和体积,利用双视角图像修正水果果形不对称和倾斜摆放带来的测量误差,该方案操作简单、测量准确且成本低。实验中对水果体积测量的平均相对误差在1%以内,表明该测量系统设计方案可行有效,适用于生产流水线的在线测量。In the process of automatic grading and processing of fruits,it is of great application value to quickly obtain the volume and shape parameters of fruits.In this paper,a fruit volume parameter measurement system based on dual-view OpenMV is designed to solve the problem of complex and high cost of the existing fruit volume parameter measurement scheme.The system uses two OpenMV monocular cameras placed at the same height at 90 degrees to collect fruit image data from two viewing angles,further measures the fruit shape parameters of the fruit online according to the camera parameters,and the measurement errors caused by asymmetric fruit shape and inclined placement are corrected by using the dual-view images.The scheme is simple operation,accurate at a low cost.The average relative error of the fruit volume measurement in the experiment is within 1%,which shows that the design scheme of the measurement system is feasible and effective,and is suitable for the online measurement of the production line.

关 键 词：水果分级 体积测量 机器视觉 双视角 嵌入式视觉模块 

分 类 号：TP274.2[自动化与计算机技术—检测技术与自动化装置]