摘要
为了解决城市半结构化道路识别过程中由于道路特征不明显,外界环境中各种干扰(光照、阴影、道路边线不连续)等因素的影响而导致道路识别鲁棒性差的问题,研究了基于Catmull-Rom样条曲线的城市半结构化道路检测算法。首先对摄像机采集的环境图像信息进行变换处理,然后根据图像处理结果和车辆当前状态设置自适应核心区域。通过引入Catmull-Rom样条曲线,构造半结构化城市道路检测模型,并使用最小二乘法求解Catmull-Rom样条曲线的最优控制点,从而完成对城市半结构化道路的检测。实验结果表明,该算法利用Catmull-Rom样条曲线模型在城市半结构化道路环境中能灵活且精确地提取车道标识线,采用自适应混合各向异性高斯滤波器保障了系统的稳定性及鲁棒性,对典型道路干扰因素均具有较好的检测效果。
In order to solve the problem of poor robustness of road recognition due to the lack of road features and various disturbances（illumination,shadow,discontinuity of road edges） in the external environment during the recognition of urban semi-structured road,westudy the algorithm of urban semi-structured road detection based on Catmull-Rom spline curve. Firstly,the environmental image information collected by the camera is transformed,and then the adaptive core area is set according to the image processing results and the current state of the vehicle. Through the introduction of Catmull-Rom splines,we construct a semi-structured urban road detection model,and use the least square method to solve the optimal control point of Catmull-Rom spline curve for detection of the urban semi-structuredroad. Experiment shows that the algorithm can rapidly and accurately extract the lane marking in the urban semi-structured road environment with Catmull-Rom spline curve and guarantee system’s stability and robustness with the adaptive mixed isotropic anisotropic Gussian filter,which has better detection effect on typical roads.
作者
葛媛媛
张宏基
GE Yuan-yuan;ZHANG Hong-ji(Research Center of Contemporary Design and Advanced Manufacturing Technology,Yulin University,Yulin 719000,China)
出处
《计算机技术与发展》
2018年第10期188-193,共6页
Computer Technology and Development
基金
国家自然科学基金(10872160)
