换道辅助系统中基于可调向滤波器的车道线分类检测
|
摘要
车道线识别与分类是车辆换道辅助系统(LCAS)中的一项关键研究内容,其中如何对不同类型车道线准确分类是一类难点问题。提出一种基于可调向滤波器的车道线识别方法;并提出基于时空窗口灰度特性统计的虚、实车道线分类方法。首先对YCbCr色彩空间中的路面信息进行窗口采样,通过建立灰度高斯分布模型提取路面区域。在此区域内设计可调向滤波器进行车道线边缘滤波;并通过梯度方向直方图对滤波器方向角θ进行初始化。提出一种灰度累加策略以降低由光照变化引起的车道线区域灰度漂移,根据车道线Hough直线模型设置动态车道线ROI,最终建立基于时间窗口内ROI灰度均值统计的虚、实车道线分类。高速公路实验证明:虚、实车道线分类准确率分别达到88.5%和90.3%,算法在克服路面环境与白天光照的干扰方面具有鲁棒性。研究对优化换道预警策略、提升LCAS的安全性与智能化水平具有理论意义。
Lane detection and classification are a key research of Lane Change Assist System( LCAS). It is a hard problem that how to classify different types of lane how to the lanes accurately. A robust lane detection method was proposed based on steerable filter. Firstly road surface in several windows is sampled in YCb Cr color space and a gray Gauss distribution model is built for road surface segmentation. A steerable filter is then designed for lane edge filtering within road surface region. The direction angle θ of the filter could be initialized by the histogram of gradient direction. Next a gray accumulation strategy is set up to reduce gray shift of lane region caused by illumination change. Dynamic lane ROI is designed by Hough straight line model. Finally lane classification method is proposed for distinguishing single dashed lane and solid lane based on the gray mean statistics of ROI within specific time window. Highway experimental results demonstrated that the classification accuracy rates of single dashed lane and solid lane reach 88. 5% and 90. 3%,respectively. The proposed algorithm is robust to interference from road environment and illumination. This research is significant for both the further optimization of lane change warning strategy and the enhancement of safety and intelligence level of LCAS.
Lane detection and classification are a key research of Lane Change Assist System( LCAS). It is a hard problem that how to classify different types of lane how to the lanes accurately. A robust lane detection method was proposed based on steerable filter. Firstly road surface in several windows is sampled in YCb Cr color space and a gray Gauss distribution model is built for road surface segmentation. A steerable filter is then designed for lane edge filtering within road surface region. The direction angle θ of the filter could be initialized by the histogram of gradient direction. Next a gray accumulation strategy is set up to reduce gray shift of lane region caused by illumination change. Dynamic lane ROI is designed by Hough straight line model. Finally lane classification method is proposed for distinguishing single dashed lane and solid lane based on the gray mean statistics of ROI within specific time window. Highway experimental results demonstrated that the classification accuracy rates of single dashed lane and solid lane reach 88. 5% and 90. 3%,respectively. The proposed algorithm is robust to interference from road environment and illumination. This research is significant for both the further optimization of lane change warning strategy and the enhancement of safety and intelligence level of LCAS.
引文
1倪捷,刘志强,涂孝军,等.面向驾驶辅助系统的换道安全性预测模型研究.交通运输系统工程与信息,2016;(4):95—100Ni Jie,Liu Zhiqiang,Tu Xiaojun,et al.Safety prediction model of lane changing based on driver assistance system.Journal of Transportation Systems Engineering and Information Technology,2016;(4):95 —100
2 孟丽霞,孙富春,邵宇.基于单目视觉的道路图像理解综述.计算机应用,2010;(6):1552—1555Meng Lixia,Sun Fuchun,Shao Yu.Survey on road image interpretation based on monocular vision.Journal of Computer Applications,2010;(6):1552—1555
3 初雪梅,王珂娜,张维刚.基于分段直线模型的弯道识别算法的研究.汽车工程,2012;(12):1141—1144Chu Xuemei,Wang Kena,Zhang Weigang.A study on a recognition algorithm of curved lane based on piecewise straightline model.Automotive Engineering,2012;(12):1141—1144
4 Wu P C,Chang C Y,Lin C H.Lane-mark extraction for automobiles under complex conditions.Pattern Recognition,2014;47(8):2756—2767
5 李亚娣,黄海波,李相鹏,等.基于Canny算子和Hough变换的夜间车道线检测.科学技术与工程,2016;16(31):234—237,242Li Yadi,Huang Haibo,Li Xiangpeng,et al.Nighttime lane markings detection based on canny operator and Hough transform.Science Technology and Engineering,2016;16(31):234—237,242
6 陈戈珩,潘晓旭,侯作辉.基于车道线识别和多特征的前车检测算法.科学技术与工程,2016;16(15):245—250Chen Geheng,Pan Xiaoxu,Hou Zuohui.Preceding vehicle detection algorithm based on lane recognition and multi-characteristics.Science Technology and Engineering,2016;16(15):245—250
7 魏华,何对燕.低对比度图像边缘增强算法的研究与应用.科学技术与工程,2014;14(34):246—252Wei Hua,He Duiyan.Research and application of edge enhancement algorithm of low-contrast images.Science Technology and Engineering,2014;14(34):246—252
8 Hoffman C,Dang T,Stiller C.Vehicle detection fusing 2D visual features.Intelligent Vehicles Symposium.New York:IEEE,2004:280 —285
9 魏庆媛,程文冬,沈云波.车道线图像检测与车辆偏航预警模型构建.西安工业大学学报,2015;(6):500—505Wei Qingyuan,Cheng Wendong,Shen Yunbo.Research of lanemark recognition and vehicle departure pre-warning.Journal of Xi'an Technological University,2015;(6):500—505
10 Borkar A,Hayes M,Smith M T.A novel lane detection system with efficient ground truth generation.IEEE Transactions on Intelligent Transportation Systems,2012;13(1):365—374
2 孟丽霞,孙富春,邵宇.基于单目视觉的道路图像理解综述.计算机应用,2010;(6):1552—1555Meng Lixia,Sun Fuchun,Shao Yu.Survey on road image interpretation based on monocular vision.Journal of Computer Applications,2010;(6):1552—1555
3 初雪梅,王珂娜,张维刚.基于分段直线模型的弯道识别算法的研究.汽车工程,2012;(12):1141—1144Chu Xuemei,Wang Kena,Zhang Weigang.A study on a recognition algorithm of curved lane based on piecewise straightline model.Automotive Engineering,2012;(12):1141—1144
4 Wu P C,Chang C Y,Lin C H.Lane-mark extraction for automobiles under complex conditions.Pattern Recognition,2014;47(8):2756—2767
5 李亚娣,黄海波,李相鹏,等.基于Canny算子和Hough变换的夜间车道线检测.科学技术与工程,2016;16(31):234—237,242Li Yadi,Huang Haibo,Li Xiangpeng,et al.Nighttime lane markings detection based on canny operator and Hough transform.Science Technology and Engineering,2016;16(31):234—237,242
6 陈戈珩,潘晓旭,侯作辉.基于车道线识别和多特征的前车检测算法.科学技术与工程,2016;16(15):245—250Chen Geheng,Pan Xiaoxu,Hou Zuohui.Preceding vehicle detection algorithm based on lane recognition and multi-characteristics.Science Technology and Engineering,2016;16(15):245—250
7 魏华,何对燕.低对比度图像边缘增强算法的研究与应用.科学技术与工程,2014;14(34):246—252Wei Hua,He Duiyan.Research and application of edge enhancement algorithm of low-contrast images.Science Technology and Engineering,2014;14(34):246—252
8 Hoffman C,Dang T,Stiller C.Vehicle detection fusing 2D visual features.Intelligent Vehicles Symposium.New York:IEEE,2004:280 —285
9 魏庆媛,程文冬,沈云波.车道线图像检测与车辆偏航预警模型构建.西安工业大学学报,2015;(6):500—505Wei Qingyuan,Cheng Wendong,Shen Yunbo.Research of lanemark recognition and vehicle departure pre-warning.Journal of Xi'an Technological University,2015;(6):500—505
10 Borkar A,Hayes M,Smith M T.A novel lane detection system with efficient ground truth generation.IEEE Transactions on Intelligent Transportation Systems,2012;13(1):365—374