基于机器视觉的智能车设计与实验研究  

Design and research of intelligence vehicle based on machine vision

作　　者：路亚宁 陆翔[1] 方凤才 LU Yaning;LU Xiang;FANG Fengcai(School of Physical Science Technology,Guangxi University,Nanning 530004,China;School of Astronautics,Harbin Institute of Technology,Harbin 150001,China;College of Physics and Electronic Engineering,Nanning Normal University,Nanning 530001,China)

机构地区：[1]广西大学物理科学与工程技术学院,广西南宁530004 [2]哈尔滨工业大学航天学院,黑龙江哈尔滨150001 [3]南宁师范大学物理与电子工程学院,广西南宁530001

出　　处：《现代电子技术》2022年第2期177-182,共6页Modern Electronics Technique

基　　金：广西自然科学基金项目面上项目(2018JJA110048);广西高等教育本科教学改革工程重点项目(2021JGZ105;2019JGZ102)。

摘　　要：为适应复杂且不适宜人操作的工作环境,设计一种机器视觉处理算法与智能系统控制算法相结合的智能车。首先,电脑端通过目标颜色识别算法、图像填充去噪算法以及最大轮廓检测算法实现物体的检测与定位;接着,根据物体与车体的距离与相对方位,智能车控制系统相应接收动作指令;最后,无线路由网络控制模块将该控制算法与智能车控制系统相结合,实现智能车的移动与机械臂的抓取。实验结果表明,该算法能够在复杂环境中准确识别目标颜色物体,判断物体的位置,为智能车的勘探、分拣等带来极大的便利。An intelligence vehicle based on the combination of machine vision processing algorithm and intelligent system control algorithm is designed to adapt to the complex and unsuitable working environment.Firstly,the computer terminal can detect and locate target by means of the target color recognition algorithm,image-padding de-noising algorithm and maximum contour detection algorithm.The intelligence vehicle control system can receive action instruction according to the distance and orientation between the target and the vehicle.The wireless fidelity network module is used to combine the control algorithm with the intelligence vehicle control system to implement the movement of the intelligence vehicle and the grasping of the robotic arm.The experimental results show that the algorithm can accurately identify the target color and judge the position of the object in the complex environment,which brings great convenience to the exploration and sorting of intelligent vehicle.

关 键 词：智能车 机器视觉 目标检测 颜色识别 控制系统 目标定位 网络传输 

分 类 号：TN915-34[电子电信—通信与信息系统]