附件A摄像头黑线识别算法和赛车行驶控制策略.pdfVIP

摄像头黑线识别算法和赛车行驶控制策略 1 2 贾秀江 ，李颢 1. 上海交大 机械设计及自动化研究所 上海 200240 2. 上海交大 自动化系 上海 200240 文 摘: 本文在图像采集系统已经获取比赛赛道的实时图像的基础之上， 研究和分析了赛道中黑线的实时检测算法；并根据识别的黑线信息， 来对赛车的转向舵机和行驶速度进行控制，使之达到较为完美的转弯 特性和速度控制。首先简单的介绍了整个图像采集系统的所获取的图 像信息和比赛赛道信息的特点。然后针对性的提出赛道黑线的边沿检 测算法，通过实验确定黑白色之间的阀值和其他主要参数值。最后根 据前面识别的黑线信息来预判前方路况信息，从而控制转向舵机的转 向角度和赛车的行驶速度。 关键词：图像采集；实时图像处理；边沿检测；转向舵机；驾驶速度 中图分类号: TP1 Distinguish Black Line by Camera and Drive the Smart Car Jia Xiujiang1，Li Hao2 1. School of Mechanical Engineering , Shanghai Jiaotong University, Shanghai 200240, China； 2. Department of Automation, Shanghai Jiaotong University, Shanghai 200240, China Abstract: In this paper we make a study on the tracking method of the guideline on a lane, on the base that the real time images of the lane have already been obtained by the image-sampling system. We also make use of the information of the tracked guideline to control the steer and speed of the vehicle so as to achieve comparatively perfect turing performance and speed control. First we briefly introduce the characteristics of the image and lane information obtained by the image-sampling system, then demonstrates the edge-detecting method of the guideline intended for those characteristics. We get the threshold difference value between white pixels and black pixels and other major parameters by experiments. In the last we use the guideline information obtained to figure out the lane information in front of the vehicle by which we could exert proper control on the turning angle of the steer and the speed of the vehicle. Key words: image acquire, real time image process, edge detective, steer control, speed con