基于CMOS图像传感器的采摘机器人嵌入式视觉系统  

Embedded Vision System of Picking Robot Based on CMOS Image Sensor

作　　者：李娜娜 Li Nana(Department of Mechanical and Electrical Engineering,Luoyang Vocational & Technical College,Luoyang 471003,China)

机构地区：[1]洛阳职业技术学院机电工程系,河南洛阳471000

出　　处：《农机化研究》2019年第9期180-184,共5页Journal of Agricultural Mechanization Research

基　　金：河南省高等教育教学改革研究项目(2017SJGLX176)

摘　　要：为了提高采摘机器人的自动化程度,实现自主导航和自主采摘作业能力,将基于CMOS图像传感器的嵌入式视觉系统引入到了采摘机器人的设计过程中,有效降低了机器人的设计复杂程度,提高了机器人的设计效率。采用DSP主控芯片构建了嵌入式图像处理系统,可以处理CMOS相机实时采集的图像,并采用模块化设计,构建了包括通讯单元、存储单元及视频输入输出接口的硬件系统,使各模块之间协调工作。为了验证方案的可行性,对一款果实采摘机器人进行了改装,安装了嵌入式视觉系统,并对其性能进行了测试。测试结果表明:采用基于CMOS图像传感器嵌入式视觉系统后,采摘机器人的定位准确率和采摘准率率都较高,满足了自动化采摘作业需求。In order to improve the automation of the picking robot and realize the ability of autonomous navigation and independent picking,the embedded visual system based on CMOS image sensor is introduced to the design process of the picking robot,which effectively reduces the complexity of the design of the robot and improves the efficiency of the robot.The embedded image processing system is built with the DSP main control chip,which can handle the real-time image collected by the CMOS camera.The hardware system including the communication unit,the storage unit and the video input and output interface is constructed by the modular design,so as to coordinate the work among the modules.In order to verify the feasibility of the scheme,a fruit picking robot is modified,embedded visual system is installed,and its performance is tested.The test results show that the accuracy rate and rate of picking accuracy of the picking robot are higher after using the embedded visual system based on CMOS image sensor,automatic harvesting needs.

关 键 词：采摘机器人 图像传感器 视觉系统 嵌入式 CMOS相机 

分 类 号：S225[农业科学—农业机械化工程]