为了提高分拣工作的效率、降低成本,设计了基于视觉识别的颜色分拣机器人。该机器人将OpenMV作为机器视觉的主要模块,机械臂作为运动模块,通过KPZ51核心系统板完成模块之间的信息互通,基于Lab颜色空间以及CamShift跟踪算法实现了颜色识别与跟踪、物体抓取、串口通信等多种技术。测试结果表明,改进后机器人识别的正确率从56%提高到了92%。颜色分拣机器人能够根据颜色对物体进行分拣。

In order to improve the efficiency of sorting and reduce the cost,a color sorting robot based on machine vision is designed in the paper.The robot takes OpenMV as the main module of machine vision,uses the manipulator to undertake the task of motion module,and completes the information exchange between modules through KPZ51 core system board.Based on Lab color space and CamShift tracking algorithm,it realizes color recognition and tracking,object grabbing,serial port communication and other technologies.The test results show that the recognition accuracy of the improved robot is increased from 56% to 92%,the color sorting robot can sort objects according to color.