[1]葛媛媛,张宏基.基于 Catmull-Rom 样条的道路检测算法研究[J].计算机技术与发展,2018,28(10):188-193.[doi:10.3969/ j. issn.1673-629X.2018.10.039]
　GE Yuan-yuan,ZHANG Hong-ji.Research on Road Detection Algorithm Based on Catmull-Rom Spline[J].,2018,28(10):188-193.[doi:10.3969/ j. issn.1673-629X.2018.10.039]
点击复制

基于 Catmull-Rom 样条的道路检测算法研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年10期
页码:
188-193
栏目:
智能、算法、系统工程
出版日期:
2018-10-10

文章信息/Info

Title:
Research on Road Detection Algorithm Based on Catmull-Rom Spline
文章编号:
1673-629X(2018)10-0188-06
作者:
葛媛媛; 张宏基
榆林学院 现代设计与先进制造技术研究中心,陕西 榆林 719000
Author(s):
GE Yuan-yuan; ZHANG Hong-ji
Research Center of Contemporary Design and Advanced Manufacturing Technology,Yulin University,Yulin 719000,China
关键词:
半结构化道路; Catmull-Rom 样条; 层次搜索优化; 高斯滤波; 道路模型
Keywords:
semi-structured road; Catmull-Rom spline; level search optimization; Gaussian filtering; road model
分类号:
TP391.41
DOI:
10.3969/ j. issn.1673-629X.2018.10.039
文献标志码:
A
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。
Abstract:
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,we study 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-structured road. 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.
更新日期/Last Update: 2018-10-10