| 5,101 | 41 | 1353 |
| 下载次数 | 被引频次 | 阅读次数 |
本文使用STM32单片机作为核心控制器,并协同机器视觉模块OpenMV组成智能小车系统,针对摄像头提取的道路图像信息,采用阈值法和鲁棒线形回归算法提取道路引导线,采用多重模版匹配法提取障碍物信息,并结合传统PID控制技术和模糊控制技术,实现了智能小车系统的引导线自动循迹和避障功能.实验表明,在直径为4mm引导线场地中,小车巡线性能表现良好;在静态障碍物环境下,小车能够有效识别障碍物,并完成避障路径规划.
Abstract：Single chip microcomputer STM32,which is used as the core controller,forms the smart car system with machine vision module OpenMV.Aiming at the road image information extracted by cameras,threshold method and robust linear regression algorithm are used to track the guide line.Adopting the multi-template matching for detecting obstacles and combined with the traditional PID control technology and fuzzy control technology,the automatic tracking and obstacle avoidance function are realized.The experimental results show that the performance of line-patrol is good in the site of 4 mm-diameter guide line,under the static obstacle circumstances,smart car can effectively identify the obstacles and complete the obstacle avoidance path planning.
[1]QU S C,TIAN Y,CHEN C.Fuzzy PID control for intelligent smartcar system with CCD camera[J].Key Engineering Materials,2011,467/468/469:433-436.
[2]YUAN Q,ZHANG Y,WU H,et al.Fuzzy control research in the courses of smart car[C]//International Conference on Machine Vision&Human-machine Interface.Kaifeng:IEEE Computer Society,2010:764-767.
[3]周柱．基于STM32的智能小车研究[D]．成都：西南交通大学，2011.
[4]韩思奇，王蕾．图像分割的阈值法综述[J]．系统工程与电子技术，2002,24(6):91-94,102.
[5]WILCOX R R.Some results on extensions and modifications of the Theil-Sen regression estimator[J].The British Journal of Mathematical and Statistical Psychology,2004,57(2):265-280.
[6]杨通钰，彭国华．基于NCC的图像匹配快速算法[J]．现代电子技术，2010,33(22):107-109.
[7]易礼智．基于机器视觉的避障智能小车系统研究[D]．长沙：中南大学，2012.
基本信息:
中图分类号:TP23;TP391.41
引用信息:
[1]岳俊峰,李秀梅.基于机器视觉的智能小车自动循迹及避障系统[J],2020,19(02):200-207.
基金信息:
国家自然科学基金项目(61571174)