Please wait a minute...
浙江大学学报(工学版)
土木与交通工程     
基于图像识别的信号灯路口辅助驾驶方法
隗海林, 包翠竹, 王涵, 李明达
1.吉林大学 交通学院,吉林 长春 130000; 
2.长春工程学院 机电工程学院,吉林 长春 130000
Driving assistance model at traffic light intersection based on image recognition
KUI Hai-lin, BAO Cui-zhu, WANG Han, LI Ming-da
1. College of Transportation, Jilin University, Changchun 130022, China;
2. School of Mechatronics Engineering, Changchun Institute of Technology, Changchun 130012, China
 全文: PDF(1956 KB)   HTML
摘要:

为了提高有信号灯路口的通行效率,将通过路口的车辆行驶状态分为4种情况(匀速通过、加速通过、减速通过和停车等待),并针对不同情况对驾驶员提出相应的驾驶行为提示.提出基于单一摄像头的图像识别系统,该系统通过加权K近邻方法识别出信号灯的颜色和倒计时.根据信号灯识别结果,建立车载摄像头与信号灯之间距离的计算模型,得到车辆与信号灯之间的距离和车辆车速.根据信号灯状态以及距离和车速信息判断车辆所处的行驶状态,给出合理的车速控制建议.实验结果表明:信号灯识别准确率高于97%;速度计算的平均误差小于5%;仿真实验验证结果表明:所提辅助驾驶方法能够减少车辆在信号灯路口的停车等待时间,提高通行效率.

Abstract:

Driving state through the intersection were divided into four driving situations (driving through traffic light at constant velocity, accelerating through traffic light, decelerating through traffic light and stopping) in order to improve the traffic efficiency and reduce fuel cost. Then corresponding driving behavior suggestions were proposed for different driving situations. An image recognition system based on a single camera was proposed, which could recognize traffic light status (color) and remaining time (countdown) using Weighted K-nearest neighbor recognition method. The computational model for distance between vehicle and traffic light was built using the results of traffic light recognition. Then the distance between traffic light and vehicle and current vehicle velocity information were calculated. Reasonable speed control suggestions were put forward with driving state judged through traffic light status, distance and velocity information. The experimental results show that the accuracy of traffic light is more than 97% and the mean error of estimated velocity is less than 5%. Verification results of the simulation experiments indicate that the proposed driver assistance model can reduce the waiting time before signaled intersection and improve the traffic efficiency.

出版日期: 2017-06-11
CLC:  U 471.1  
基金资助:

吉林省科技厅重点科技攻关资助项目(20150204052GX).

作者简介: 隗海林(1969—),男,教授,从事汽车节能、智能交通研究. ORCID: 0000-0002-1365-0980. E-mail:khl69@163.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  

引用本文:

隗海林, 包翠竹, 王涵, 李明达. 基于图像识别的信号灯路口辅助驾驶方法[J]. 浙江大学学报(工学版), 10.3785/j.issn.1008-973X.2017.06.005.

KUI Hai-lin, BAO Cui-zhu, WANG Han, LI Ming-da. Driving assistance model at traffic light intersection based on image recognition. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 10.3785/j.issn.1008-973X.2017.06.005.

参考文献(References):
[1] 杨晓光,庄斌,李克平.信号交叉口饱和流率和启动延误的影响分析[J].同济大学学报:自然科学版, 2006,34(6): 738-743.
YANG Xiao-guang, ZHUANG Bin, LI Ke-ping. Analysis of saturation flow rate and delay at signalized intersection [J]. Journal of Tongji University: Natural Science, 2006, 34(6): 738-743.
[2] RITTGER L, SCHMIDT G, MAAG C, et al. Driving behaviour at traffic light intersections [J]. Cognition, Technology and Work 2015, 17(4): 593-605.
[3] BARTH M, MANDAVA S, Boriboonsomsin K, et al. Dynamic ECO-driving for arterial corridors [C] ∥Proceedings of the IEEE Forum of Integrated Sustainable Transportation. Vienna Austria: IEEE, 2011: 182-188.
[4] LI M, BORIBOONSOMSIN K, WU G Y, et al. Traffic energy and emission reductions at signalized intersections: a study of the benefits of advanced driver information [J]. International Journal of ITS Research, 2009,7(1): 49-58.
[5] 靳秋思,宋国华,叶蒙蒙,等.车辆通过交叉口的生态驾驶轨迹优化研究[J].安全与环境工程, 2015, 5(3): 75-82.
JIN Qiu-si, SONG Guo-hua, YE Meng-meng, et al. Optimization of eco-driving trajectories at intersections for energy saving and emission reduction [J]. Safety and Environmental Engineering, 2015, 5(3): 75-82.
[6] 王建强,王海鹏,刘佳熙,等.基于车路一体化的交叉口车辆驾驶辅助系统[J].中国公路学报,2013,6(4):169-175.
WANG Jian-qiang, WANG Hai-peng, LIU Jia-xi, et al. Intersection vehicle driving assistance system based on vehicle-to-infrastructure communication [J]. China Journal of Highway and Transport, 2013, 6(4):169-175.
[7] 安实,姚焓东,姜慧夫,等.信号交叉口绿色驾驶车速控制方法[J].交通运输系统工程与信息,2015,15(5):53-59.
AN Shi, YAO Han-dong, JIANG Hui-fu, et al. A green driving speed control method at signal intersection [J]. Journal of Transportation Systems Engineering and Information Technology, 2015, 15(5): 53-59.
[8] CHEN W, BAI Y, YANG X. Delay estimation undera dynamic speed control based intersection [C] ∥ Transportation Research Board 92nd Annual Meeting. Washington DC: [s.n.], 2013: 2570-2587.
[9] RAKHA H, KAMALANATHSHARMA R K. Eco-driving at signalized intersections using V2I communication [C] ∥ 2011 14th International IEEE Conference on Intelligent Transportation Systems. Washington DC: IEEE, 2011: 341-346.
[10] 王可,陆长德,乐万德,等.基于Lab均匀色彩空间的色彩调和系统[J].西北工业大学学报,2004,22(6):695-699.
WANG Ke, LU Chang-de, YUE Wan-de, et al. Color harmony system based on Lab perceptual uniform color space [J]. Journal of North Western Polytechnical University, 2004, 22(6): 695-698.
[11] 李微,李德仁.基于HSV色彩空间的MODIS云检测算法研究[J].中国图象图形学报, 2011, 16(9):1696-1701.
LI Wei, LI De-ren. The cloud detection study of modis based on HSV colors pace [J]. Journal of Image and Graphics, 2011, 16(9): 1696-1701.
[12] WU L N, CI Y S, CHU J W, et al. The influence of intersections on fuel consumption in urban arterial road traffic: a single vehicle test in Harbin, China [J]. PLoS One, 2015, 10(9): 1-10.
[13] LEE J, PARK B. Development and evaluation of a cooperative vehicle intersection control algorithm un the connected vehicles environment [J]. IEEE Transactions on Intelligent Transportation Systems, 2012, 13(1):81-90.
[14] NIU D N, SUN J. Eco-driving versus green wave speed guidance for signalized highway traffic: a multi-vehicle driving simulator study [J]. Procedia-Social and Behavioral Sciences, 2013, 96: 1079-1090.
[15] DIAZ-CABRERA M, CERRI P, MEDICI P. Robust real-time traffic light detection and distance estimation using a single camera [J]. Expert Systems with Applications 2015, 42(8): 3911-3923.
[16] 中华人民共和国质量监督检疫检疫质量总局.道路交通信号灯:GB/T 14887-2011[S/OL]. 北京:中国标准出版社, 2012: 3 [2015-12-22]. http:∥www.122.cn/zcfg/flfl/gjbz/570885.shtm.
[17] HALTAKOV V, MAYR J, UNGER C, et al. Semantic segmentation based traffic light detection at day and at night [M]. Berlin: Pattern Recognition, 2015:446-457.
[18] SIOGKAS G, SKODRAS E, DERMATAS E. Traffic lights detection in adverse conditions using color, symmetry and spatiotemporal information [C] ∥ International Conference on Computer Vision Theory and Applications. Rome: VISAPP, 2012: 620-627.
[19] SOOKSATRA S, KONDO T. Red traffic light detection using fast radial symmetry transform [C] ∥ International Conference on Electrical Engineering/electronics, Computer, Telecommunications and Information Technology. Nakhon Ratchasima: IEEE, 2014: 1-6.
[20] 谷明琴,蔡自兴,李仪.应用圆形度和颜色直方图的交通信号灯识别[J].计算机工程与设计,2012,33(1): 243-247.
GU Ming-qin, CAI Zi-xing, LI Yi. Traffic light recognition with circulartiy and color histogram [J]. Computer Engineering and Design. 2012, 33(1): 243-247.
[21] La Route Automatisée. Traffic lights recognition (TLR) public benchmarks [EB/OL]. [2013-10-29]. http:∥www.lara.prd.fr/benchmarks/trafficlightsrecognition.

No related articles found!