基于概率霍夫变换的车道线识别算法

详细信息    查看全文 | 推荐本文 |

英文篇名：Research on lane recognition algorithm based on probability Hough transform 作者：辛超 ; 刘扬 英文作者：XIN Chao;LIU Yang;School of Surveying and Urban Space Information,Beijing University of Civil Engineering and Architecture;Beijing's Future Urban Design High-tech Innovation Center,Beijing University of Civil Engineering and Architecture; 关键词：车道线识别 ; 图像增强 ; 颜色空间转换 ; 自适应Canny边缘检测 英文关键词：lane detection;;image enhancement;;color space conversion;;adaptive Canny edge detection 中文刊名：测绘通报 英文刊名：Bulletin of Surveying and Mapping 机构：北京建筑大学测绘与城市空间信息学院;北京建筑大学北京未来城市设计高精尖创新中心; 出版日期：2019-09-01 出版单位：测绘通报 年：2019 期：S2 基金：国家重点研发计划课题(2018YFC0706003);; 北京建筑大学金字塔人才培养项目(21082717008) 语种：中文; 页：59-62 页数：4 CN：11-2246/P ISSN：0494-0911 分类号：TP391.41;U463.6

摘要

为满足在高精细导航电子地图中进行车道线绘制的需求,本文提出一种基于概率霍夫变换的车道线识别算法。算法在图像预处理部分使用一种基于转换颜色空间的方法提取车道线像素,之后利用自适应阈值的Canny边缘检测算法和概率霍夫变换算法实现车道线识别。试验结果表明,本文算法的运算速度维持在2秒/帧;识别正确率与Matlab经典Hough算法相比提升9%左右,漏检率也有所降低。同时拍摄质量较差图像的针对性试验结果,也证实了本文算法能有效降低天气和光照等因素对车道线识别造成的影响。
        In order to meet the requirements of lane line drawing in high-precision navigation electronic map,a lane recognition algorithm based on probabilistic Hough transform is proposed. In the image preprocessing part,the proposed algorithm extracts lane pixels based on the method of transforming color space. Then the lane recognition is realized by using Canny edge detection algorithm with adaptive threshold and probability Hough transform algorithm. Experiments show that the computational speed of the algorithm is maintained at 2 seconds per frame. In terms of accuracy,the recognition accuracy rate is improved by about 9% compared with the Matlab classic Hough algorithm,and the missed detection rate is also reduced. It is also proved that the proposed algorithm can effectively reduce the influence of weather and illumination on lane recognition.

引文

[1]田晟，张剑锋，张裕天，等．基于扩张卷积金字塔网络的车道线检测[J/OL]．西南交通大学学报:1-8[2019-06-20]. http:∥kns. cnki. net/kcs/detail/51. 1277. U.20190306.1211.002.html.
    [2]祖玉川．车道级高精度地图优化[J]．北京测绘，2019,33(5):555-559.
    [3]王玉萍，张晨晨．基于Open CV的车道线识别与跟踪算法[J]．企业科技与发展，2018(2):197-198.
    [4]王科，黄智，钟志华．基于不定Bezier变形模板的城市道路检测算法[J]．机械工程学报，2013,49(8):143-150.
    [5]王晓锦，王增才，赵磊．基于消失点检测与分段直线模型的车道线识别[J]．机电一体化，2017,23(5):41-46.
    [6]易世春，李克强，郭君斌，等．基于边缘分布及特征聚类的车道标记线检测[J]．汽车工程，2014,36(10):1210-1215,1179.
    [7]杨宁．基于边缘特征的前方车辆识别[D]．长春:吉林大学，2007.
    [8] YOO H,YANG U,SOHN K. Gradient-enhancing conversion for illumination-robust lane detection[J]. IEEE Transactions on Intelligent Transportation Systems,2013,14(3):1083-1094.
    [9] CHENG H Y,JENG B S,TSENG P T,et al. Lane detection with moving vehicles in the traffic scenes[J].IEEE Transactions on Intelligent Transportation Systems,2006,7(4):571-582.
    [10]张洪丹．车道偏离预警系统车道线检测及预警策略算法研究[D]．长沙:湖南大学，2015.
    [11]刘庆祥，蒋天发．彩色与灰度图像间转换算法的研究[J]．武汉理工大学学报(交通科学与工程版)，2003(3):344-346.
    [12]余厚云，张为公，赵转萍．基于车道线斜率的车道偏离检测[J]．光电工程，2012,39(7):43-48.
    [13]刘庆祥，蒋天发．彩色与灰度图像间转换算法的研究[J]．武汉理工大学学报(交通科学与工程版)，2003(3):344-346.