留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

多场景车道线检测与偏离预警方法研究

覃雄臻 鲁若宇 陈立明 耿黄政 杜玉峰 高长斌 孟浩磊

覃雄臻, 鲁若宇, 陈立明, 耿黄政, 杜玉峰, 高长斌, 孟浩磊. 多场景车道线检测与偏离预警方法研究[J]. 机械科学与技术, 2020, 39(9): 1439-1449. doi: 10.13433/j.cnki.1003-8728.20190290
引用本文: 覃雄臻, 鲁若宇, 陈立明, 耿黄政, 杜玉峰, 高长斌, 孟浩磊. 多场景车道线检测与偏离预警方法研究[J]. 机械科学与技术, 2020, 39(9): 1439-1449. doi: 10.13433/j.cnki.1003-8728.20190290
Qin Xiongzhen, Lu Ruoyu, Chen Liming, Geng Huangzheng, Du Yufeng, Gao Zhangbing, Meng Haolei. Research on Multi-scene Lane Line Detection and Deviation Warning Method[J]. Mechanical Science and Technology for Aerospace Engineering, 2020, 39(9): 1439-1449. doi: 10.13433/j.cnki.1003-8728.20190290
Citation: Qin Xiongzhen, Lu Ruoyu, Chen Liming, Geng Huangzheng, Du Yufeng, Gao Zhangbing, Meng Haolei. Research on Multi-scene Lane Line Detection and Deviation Warning Method[J]. Mechanical Science and Technology for Aerospace Engineering, 2020, 39(9): 1439-1449. doi: 10.13433/j.cnki.1003-8728.20190290

多场景车道线检测与偏离预警方法研究

doi: 10.13433/j.cnki.1003-8728.20190290
基金项目: 

柳州市科技计划项目 2018B0301b003

详细信息
    作者简介:

    覃雄臻(1976-), 工程师, 研究方向为车辆工程, Xiongzhen.Qin@sgmw.com.cn

  • 中图分类号: TP391.4

Research on Multi-scene Lane Line Detection and Deviation Warning Method

  • 摘要: 针对目前车道线检测与偏离预警方法适应性不强、检测精度不高,从而不能够满足多种道路环境下实际应用需求的问题,利用图像的不同特征信息并结合道路图像的空间位置关系及相关先验知识展开研究。提出一种能够适应多种道路场景的车道线检测方法,并建立相应的偏离预警模型,以增强整个系统的可靠性与环境适应性。
  • 图  1  整体方法流程

    图  2  去雾提清效果图

    图  3  图像灰度化

    图  4  图像滤波结果

    图  5  图像滤波灰度直方图

    图  6  灰度图像边缘强化结果

    图  7  道路区域划分

    图  8  ROI图像

    图  9  多场景ROI划分结果图像

    图  10  平面转换结果图像

    图  11  Prewitt算子卷积核

    图  12  Prewitt算子检测结果二值图

    图  13  改进Prewitt算子检测结果二值图

    图  14  RGB图像

    图  15  L通道图像

    图  16  RGB道路图像

    图  17  b通道的图像

    图  18  基于HSL与Lab颜色模型的车道线检测流程图

    图  19  64个灰度级的灰度直方图

    图  20  Lab颜色模型b通道车道线二值图

    图  21  预处理后的ROI图像

    图  22  L通道车道线二值图

    图  23  b通道车道线二值图

    图  24  基于颜色模型的检测结果

    图  25  车道线识别流程图

    图  26  左右边缘卷积模板

    图  27  图像平面坐标与世界坐标对应关系(部分)

    图  28  车道线左右边缘匹配结果图

    图  29  不同场景检测结果

    图  30  传统TLC模型数据流向

    图  31  车道偏离预警算法流程图

    图  32  所采集视频图像

    图  33  常规道路场景

    图  34  道路污迹场景

    图  35  雨天且前方有车辆场景

    图  36  弯道场景

    图  37  弯道且前方有干扰场景

    表  1  各检测算子的计算耗时

    边缘检测算子 Canny Roberts Sobel 改进
    Prewitt
    平均耗时/ms 57.7 13.3 15.2 10.2
    分辨率 295×640 295×640 295×640 295×640
    下载: 导出CSV

    表  2  测试结果对比表

    方法 时间/帧数 精度 召回率 综合评价指标
    方法A(文献[23]) 48.9 84.74% 89.1% 86.86%
    方法B(文献[7]) 33.09 88.2% 93.3% 90.67%
    本文方法 32.8 91.2% 94.5% 92.82%
    下载: 导出CSV
  • [1] Bar Hillel A, Lerner R, Levi D, et al. Recent progress in road and lane detection:a survey[J]. Machine Vision and Applications, 2014, 25(3):727-745 doi: 10.1007/s00138-011-0404-2
    [2] Aly M. Real time detection of lane markers in urban streets[C]//Proceedings of 2008 IEEE Intelligent Vehicles Symposium. Eindhoven, Netherlands: IEEE, 2008: 7-12
    [3] Li H, Feng M Y, Wang X. Inverse perspective mapping based urban road markings detection[C]//Proceedings of 2012 IEEE 2nd International Conference on Cloud Computing and Intelligence Systems. Hangzhou: IEEE, 2012: 1178-1182
    [4] 曾治, 李真, 陈静.一种实时的城市道路车道线识别方法及实现[J].电子技术与软件工程, 2015, (12):88-90 http://www.cqvip.com/QK/80675A/201512/664976707.html

    Zeng Z, Li Z, Chen J. A real-time urban road lane line identification method and implementation[J]. Electronic Technology & Software Engineering, 2015, (12):88-90(in Chinese) http://www.cqvip.com/QK/80675A/201512/664976707.html
    [5] Jiang R Y, Reinhard K, Tobi V, et al. Lane detection and tracking using a new lane model and distance transform[J]. Machine Vision and Applications, 2011, 22(4):721-737 doi: 10.1007/s00138-010-0307-7
    [6] Chang C Y, Lin C H, An efficient method for lane-mark extraction in complex conditions[C]//Proceedings of 2012 9th International Conference on Ubiquitous Intelligence and Computing and 9th International Conference on Autonomic and Trusted Computing. Fukuoka, Japan: IEEE, 2012: 330-336
    [7] Hoang T M, Hong H G, Vokhidov H, et al. Road lane detection by discriminating dashed and solid road lanes using a visible light camera sensor[J]. Sensors, 2016, 16(8):1313 doi: 10.3390/s16081313
    [8] Collado J M, Hilario C, De La Escalera A, et al. Adaptative road lanes detection and classification[C]//Proceedings of the 8th International Conference on Advanced Concepts for Intelligent Vision Systems. Antwerp, Belgium: Springer, 2006: 1151-1162
    [9] Sehestedt S, Kodagoda S, Alempijevic A, et al. Robust lane detection in urban environments[C]//Proceedings of 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems. San Diego, CA, USA: IEEE, 2007: 123-128
    [10] Xu H R, Wang X D, Huang H W, et al. A fast and stable lane detection method based on b-spline curve[C]//Proceedings of 2009 IEEE 10th International Conference on Computer-Aided Industrial Design & Conceptual Design. Wenzhou: IEEE, 2009: 1036-1040
    [11] Zhou S Y, Jiang Y H, Xi J Q, et al. A novel lane detection based on geometrical model and Gabor filter[C]//Proceedings of 2010 IEEE Intelligent Vehicles Symposium. San Diego, CA, USA: IEEE, 2010: 59-64
    [12] Parajuli A, Celenk M, Riley H B. Performance assessment of predictive lane boundary detection for non-uniformly illuminated roadway driving assistance[C]//Proceedings of 2016 13th Conference on Computer and Robot Vision. Victoria, BC, Canada: IEEE, 2016: 170-177
    [13] 吴彦文, 张楠, 周涛, 严等.基于多传感融合的车道线检测与跟踪方法的研究[J].计算机应用研究, 2018, 35(2): 600-603, 607

    Wu Y W, Zhang N, Zhou T, et al. Research of lane detection and tracking methods based on multi-sensor fusion[J]. Application Research of Computers, 2018, 35(2): 600-603, 607(in Chinese)
    [14] Lu W J, Rodriguez F S A, Seignez E, et al. Monocular multi-kernel based lane marking detection[C]//Proceedings of the 4th Annual IEEE International Conference on Cyber Technology in Automation, Control and Intelligent. Hong Kong, China: IEEE, 2014: 123-128
    [15] Taha M, Zayed H H, Nazmy T, et al. An efficient method for multi moving objects tracking at nighttime[J]. IJCSI International Journal of Computer Science Issues, 2014, 11(6):17-27 http://www.researchgate.net/publication/271445923_An_Efficient_Method_for_Multi_Moving_Objects_Tracking_at_Nighttime
    [16] Nieto M, Salgado L, Jaureguizar F, et al. Robust multiple lane road modeling based on perspective analysis[C]//Proceedings of 2008 15th IEEE International Conference on Image Processing. San Diego, CA, USA: IEEE, 2008: 2396-2399
    [17] 谷燕如, 黄忠朝.车道检测与偏离预警系统研究综述[J].时代农机, 2018, 45(3):24-27 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=0120181102460822

    Gu Y R, Huang Z C. Review on lane detection and departure warning system[J]. Hunan Agricultural Machinery, 2018, 45(3):24-27(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=0120181102460822
    [18] Wang W S, Zhao D, Han W, et al. A learning-based approach for lane departure warning systems with a personalized driver model[J]. IEEE Transactions on Vehicular Technology, 2018, 67(10):9145-9157 doi: 10.1109/TVT.2018.2854406
    [19] Yin X L, Zhao J D, Wu X G, et al. An improved lane departure warning algorithm based on fusion of F-Kalman filter and F-TLC[J]. Multimedia Tools and Applications, 2019, 78(9):12203-12222 doi: 10.1007/s11042-018-6762-2
    [20] 李福俊, 顾敏明.车道线实时检测与偏离预警系统设计与研究[J].光电子·激光, 2018, 29(3):298-304 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gdzjg201803010

    Li F J, Gu M M. Design and research on lane detection and the departure warning system[J]. Journal of Optoelectronics·Laser, 2018, 29(3):298-304(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gdzjg201803010
    [21] Li W H, Gong X H, Wang Y, et al. A lane marking detection and tracking algorithm based on sub-regions[C]//Proceedings of 2014 International Conference on Informative and Cybernetics for Computational Social Systems. Qingdao: IEEE, 2014: 68-73
    [22] Von Gioi R G, Jakubowicz J, Morel J M, et al. LSD:a fast line segment detector with a false detection control[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(4):722-732 doi: 10.1109/TPAMI.2008.300
    [23] 陈涛, 张洪丹, 陈东, 等.基于优先像素与卡尔曼滤波追踪的车道线检测[J].汽车工程, 2016, 38(2):200-205, 220 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=qcgc201602011

    Chen T, Zhang H D, Chen D, et al. Lane detection based on high priority pixels and tracking by Kalman filter[J]. Automotive Engineering, 2016, 38(2):200-205, 220(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=qcgc201602011
  • 加载中
图(37) / 表(2)
计量
  • 文章访问数:  326
  • HTML全文浏览量:  91
  • PDF下载量:  25
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-05-30
  • 刊出日期:  2020-09-01

目录

    /

    返回文章
    返回