摘要
采用道路模型与道路特征相结合的方法建立车道线检测与跟踪的模型。首先,运用车道线和车道的色彩特征辨别图像中道路区域和非道路区域。然后,建立车道线的模型,通过确定各个模型参数完成对车道线相应形态的表达,得到较高的检测准确度,最后利用识别结果对车道线的类型进行分类并标记绘制。该模型能够综合道路模型和道路特征的车道线检测优点,解决利用道路特征检测车道线受光照以及环境因素影响。
In this paper,a model of lane detection and tracking is established by combining road model with road features.Firstly,the color features of lane lines and lanes are used to identify the road area and non-road areas in the image.Then,the model of lane line is established,and the corresponding shape of lane line is expressed by determining the parameters of each model to obtain high detection accuracy.Finally,the types of lane lines are classified and marked by the recognition results.The model can integrate the advantages of road model and road features in lane line detection and solve the problem of using road features to detect lane affected by illumination and environmental factors.
作者
吕颖
李红建
李骏
吕铮
董小瑜
Lü Ying;Li Hongjian;Li Jun;Lü Zheng;Dong Xiaoyu(Intelligent and Connected Vehicle Development Institute,China FAW Corporation Limited,Changchun 130013;Innovative Technology Research Institute,China FAW Corporation Limited,Changchun 130013;State Key Laboratory of Comprehensive Technology on Automobile Vibration and Noise&Safety Control,Changchun 130013;School of Vehicle and Mobility,Tsinghua University,Beijing 100084)
出处
《汽车文摘》
2021年第10期58-62,共5页
Automotive Digest
基金
国家重点研发计划(2017YFB0102605)资助。
关键词
车道线检测
道路特征
道路模型
智能驾驶
Lane line detection
Road features
Road model Autonomous driving
