基于YOLO的道路车辆拥堵分析模型
|
摘要
针对当前交通运行出现的拥堵问题,提出一种新型的道路状态判断模型。首先,模型基于YOLOv3目标检测算法,然后结合图片对应的特征值矩阵,通过相邻帧之间的特征矩阵作差并将差值逐项求和得到的结果与预设值进行比较来判断当前道路是处于拥堵状态还是正常通行状态,其次再将当前计算出的道路状态与前两次计算出的道路状态进行比较,最后运用模型里的状态统计法来统计道路某状态(拥堵或通畅)的持续时间。该模型能够同时对一条道路的三个车道进行状态统计分析,经过实验,模型对单条车道状态判断的平均准确率能达到80%以上,并且白天与夜晚的道路均适用。
To solve traffic congestion problems, a new road condition judgment model was proposed. Firstly, the model was based on YOLOv3 target detection algorithm. Then, according to the eigenvalue matrix corresponding to the picture, the difference between adjacent frames was made by the eigenvalue matrix, and the difference value was compared with preset value to determine whether the current road was in a congested state or a normal traffic state. Secondly, the current calculated road state was compared with previous two calculated road states. Finally, the state statistics method in the model was used to calculate the duration of a state( congestion or patency) of road. The proposed model could analyze the states of three lanes of a road at the same time. Through experiments, the average accuracy of model to judge the state of single lane could reach80% or more, and it was applicable to both day and night roads.
To solve traffic congestion problems, a new road condition judgment model was proposed. Firstly, the model was based on YOLOv3 target detection algorithm. Then, according to the eigenvalue matrix corresponding to the picture, the difference between adjacent frames was made by the eigenvalue matrix, and the difference value was compared with preset value to determine whether the current road was in a congested state or a normal traffic state. Secondly, the current calculated road state was compared with previous two calculated road states. Finally, the state statistics method in the model was used to calculate the duration of a state( congestion or patency) of road. The proposed model could analyze the states of three lanes of a road at the same time. Through experiments, the average accuracy of model to judge the state of single lane could reach80% or more, and it was applicable to both day and night roads.
引文
[1]刘羡.大全国机动车保有量达3. 04亿辆机动车驾驶人3. 71亿人[N/OL].中国新闻网,2017-07-11(14)[2018-05-30]. http://finance. chinanews. com/sh/2017/07-11/8274683. shtml.(LIU X.The number of motor vehicles in China has reached 304 million,with 371 million drivers[N/OL]. China News, 2017-07-11(14)[2018-05-30]. http://finance. chinanews. com/sh/2017/07-11/8274683. shtml.)
[2]于建SF069. 2016年全球最堵城市洛杉矶夺冠[N/OL].新浪财经,2017-02-21(15)[2018-05-30]. http://finance. sina. com. cn/stock/usstock/c/2017-02-21/us-ifyarrcf5236517. shtml.(YU J SF069. Los Angeles, the world's biggest city, wins in 2016[N/OL]. Sina Finance and Economics, 2017-02-21(15)[2018-05-30]. http://finance. sina. com. cn/stock/usstock/c/2017-02-21/us-ifyarrcf5236517. shtml.)
[3]张立东.城市交通溢流智能协调控制算法研究[D].济南:山东大学,2012:2-4.(ZHANG L D. Research on intelligent coordinated control algorithm of urban traffic overflow[D]. Jinan:Shandong University, 2012:2-4.)
[4]陆化普,孙智源,屈闻聪.大数据及其在城市智能交通系统中的应用综述[J].交通运输系统工程与信息,2015,15(5):45-52.(LU H J, SUN Z Y, QU W C. Big data and its application in urban intelligent transportation system[J]. Transportation Systems Engineering and Information, 2015, 15(5):45-52.)
[5]廖孝勇.浮动车交通参数检测及在道路交通状态分析中的应用研究[D].重庆:重庆大学,2011:6-8(LIAO X Y. Study on the detection of floating vehicle traffic parameters and its application in road traffic state analysis[D]. Chongqing:Chongqing University,2011:6-8.)
[6]LIU W, ANGUELOV D, ERHAN D, et al. SSD:Single Shot multibox Detector[C]//Proceedings of the 2016 European Conference on Computer Vision. Berlin:Springer. 2016:21-37.
[7]REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once:unified, real time object detection[C]//Proceedings of the2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:779-788.
[8]GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2014:580-587.
[9]GIRSHICK R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2015:1440-1448.
[10]UIJLINGS J R R, VAN DE SANDE K E A, GEVERS T, et al.Selective search for object recognition[J]. International Journal of Computer Vision, 2013, 104(2):154-171.
[11]KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Image Net classification with deep convolutional neural networks[C]//Proceed-ings of the 2012 Advances in Neural Information Processing Systems. Lake Tahoe:[s. n.], 2012:1097-1105.
[12]BRETT M, ANTON J L, VALABREGUE R, et al. Region of interest analysis using an SPM toolbox[C]//Proceedings of the 8th International Conference on Functional Mapping of the Human Brain. Cambridge:Academic Press, 2002:210-217.
[13]HE K, ZHANG X, REN S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[C]//Proceedings of the 2014 European Conference on Computer Vision. Berlin:Springer, 2014:346-361.
[14]GRAHAM B. Fractional max-pooling[J]. Ar Xiv Preprint, 2014,2014:1412. 6071.
[15]REN S, HE K, GIRSHICK R, et al. Faster R-CNN:towards realtime object detection with region proposal networks[C]//Proceedings of the 2015 Advances in Neural Information Processing Systems. Montréal:[s. n.], 2015:91-99.
[16]MA Y, JIANG Z, ZHANG H, et al. Generating region proposals for histopathological whole slide image retrieval[J]. Computer methods and Programs in Biomedicine, 2018, 159:1-10.
[17]REDMON J, FARHADI A. YOLOv3:an incremental improvement[J]. Ar Xiv Preprint, 2018, 2018:1804. 02767.
[18]汪毅.基于车窗定位的车辆特征提取与车型分类识别[J].科学技术创新,2018(3):17-19.(WANG Y. Vehicle feature extraction and vehicle classification based on window location[J]. Science and Technology Innovation, 2018(3):17-19.)
[19]刘家旭.基于HOG特征提取的车辆检测方法研究[D].北京:华北电力大学,2017:4-6.(LIU J X. Research on vehicle detection method based on HOG feature extraction[D]. Beijing:North China Electric Power University, 2017:4-6.)
[20]刘荆桥,戴光明.角点检测在车辆特征提取中的应用[J].软件导刊,2008(4):91-92.(LIU J Q, DAI G M. The application of corner detection in vehicle feature extraction[J]. Software Guide,2008(4):91-92.)
[2]于建SF069. 2016年全球最堵城市洛杉矶夺冠[N/OL].新浪财经,2017-02-21(15)[2018-05-30]. http://finance. sina. com. cn/stock/usstock/c/2017-02-21/us-ifyarrcf5236517. shtml.(YU J SF069. Los Angeles, the world's biggest city, wins in 2016[N/OL]. Sina Finance and Economics, 2017-02-21(15)[2018-05-30]. http://finance. sina. com. cn/stock/usstock/c/2017-02-21/us-ifyarrcf5236517. shtml.)
[3]张立东.城市交通溢流智能协调控制算法研究[D].济南:山东大学,2012:2-4.(ZHANG L D. Research on intelligent coordinated control algorithm of urban traffic overflow[D]. Jinan:Shandong University, 2012:2-4.)
[4]陆化普,孙智源,屈闻聪.大数据及其在城市智能交通系统中的应用综述[J].交通运输系统工程与信息,2015,15(5):45-52.(LU H J, SUN Z Y, QU W C. Big data and its application in urban intelligent transportation system[J]. Transportation Systems Engineering and Information, 2015, 15(5):45-52.)
[5]廖孝勇.浮动车交通参数检测及在道路交通状态分析中的应用研究[D].重庆:重庆大学,2011:6-8(LIAO X Y. Study on the detection of floating vehicle traffic parameters and its application in road traffic state analysis[D]. Chongqing:Chongqing University,2011:6-8.)
[6]LIU W, ANGUELOV D, ERHAN D, et al. SSD:Single Shot multibox Detector[C]//Proceedings of the 2016 European Conference on Computer Vision. Berlin:Springer. 2016:21-37.
[7]REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once:unified, real time object detection[C]//Proceedings of the2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:779-788.
[8]GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2014:580-587.
[9]GIRSHICK R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2015:1440-1448.
[10]UIJLINGS J R R, VAN DE SANDE K E A, GEVERS T, et al.Selective search for object recognition[J]. International Journal of Computer Vision, 2013, 104(2):154-171.
[11]KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Image Net classification with deep convolutional neural networks[C]//Proceed-ings of the 2012 Advances in Neural Information Processing Systems. Lake Tahoe:[s. n.], 2012:1097-1105.
[12]BRETT M, ANTON J L, VALABREGUE R, et al. Region of interest analysis using an SPM toolbox[C]//Proceedings of the 8th International Conference on Functional Mapping of the Human Brain. Cambridge:Academic Press, 2002:210-217.
[13]HE K, ZHANG X, REN S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[C]//Proceedings of the 2014 European Conference on Computer Vision. Berlin:Springer, 2014:346-361.
[14]GRAHAM B. Fractional max-pooling[J]. Ar Xiv Preprint, 2014,2014:1412. 6071.
[15]REN S, HE K, GIRSHICK R, et al. Faster R-CNN:towards realtime object detection with region proposal networks[C]//Proceedings of the 2015 Advances in Neural Information Processing Systems. Montréal:[s. n.], 2015:91-99.
[16]MA Y, JIANG Z, ZHANG H, et al. Generating region proposals for histopathological whole slide image retrieval[J]. Computer methods and Programs in Biomedicine, 2018, 159:1-10.
[17]REDMON J, FARHADI A. YOLOv3:an incremental improvement[J]. Ar Xiv Preprint, 2018, 2018:1804. 02767.
[18]汪毅.基于车窗定位的车辆特征提取与车型分类识别[J].科学技术创新,2018(3):17-19.(WANG Y. Vehicle feature extraction and vehicle classification based on window location[J]. Science and Technology Innovation, 2018(3):17-19.)
[19]刘家旭.基于HOG特征提取的车辆检测方法研究[D].北京:华北电力大学,2017:4-6.(LIU J X. Research on vehicle detection method based on HOG feature extraction[D]. Beijing:North China Electric Power University, 2017:4-6.)
[20]刘荆桥,戴光明.角点检测在车辆特征提取中的应用[J].软件导刊,2008(4):91-92.(LIU J Q, DAI G M. The application of corner detection in vehicle feature extraction[J]. Software Guide,2008(4):91-92.)