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

基于Darknet框架下YOLO v2算法的车辆多目标检测方法

李珣 刘瑶 李鹏飞 张蕾 赵征凡

李珣, 刘瑶, 李鹏飞, 张蕾, 赵征凡. 基于Darknet框架下YOLO v2算法的车辆多目标检测方法[J]. 交通运输工程学报, 2018, 18(6): 142-158. doi: 10.19818/j.cnki.1671-1637.2018.06.015
引用本文: 李珣, 刘瑶, 李鹏飞, 张蕾, 赵征凡. 基于Darknet框架下YOLO v2算法的车辆多目标检测方法[J]. 交通运输工程学报, 2018, 18(6): 142-158. doi: 10.19818/j.cnki.1671-1637.2018.06.015
LI Xun, LIU Yao, LI Peng-fei, ZHANG Lei, ZHAO Zheng-fan. Vehicle multi-target detection method based on YOLO v2 algorithm under darknet framework[J]. Journal of Traffic and Transportation Engineering, 2018, 18(6): 142-158. doi: 10.19818/j.cnki.1671-1637.2018.06.015
Citation: LI Xun, LIU Yao, LI Peng-fei, ZHANG Lei, ZHAO Zheng-fan. Vehicle multi-target detection method based on YOLO v2 algorithm under darknet framework[J]. Journal of Traffic and Transportation Engineering, 2018, 18(6): 142-158. doi: 10.19818/j.cnki.1671-1637.2018.06.015

基于Darknet框架下YOLO v2算法的车辆多目标检测方法

doi: 10.19818/j.cnki.1671-1637.2018.06.015
基金项目: 

国家自然科学基金项目 51607133

陕西省自然科学基础研究计划项目 2016JQ5106

陕西省教育厅专项科研计划项目 16JK1342

详细信息
    作者简介:

    李珣(1981-), 男, 陕西子长人, 西安工程大学副教授, 工学博士, 从事微观交通流模型与交通图像处理方法研究

    通讯作者:

    刘瑶(1994-), 女, 陕西延安人, 西安工程大学工学硕士研究生

  • 中图分类号: U492.84

Vehicle multi-target detection method based on YOLO v2 algorithm under darknet framework

More Information
  • 摘要: 针对道路车辆目标检测传统方法需随场景变化提取不同特征, 检测率较低与鲁棒性差的问题, 提出了一种基于Darknet框架下YOLO v2算法的车辆多目标检测方法; 根据目标路段场景与车流量的变化对YOLO-voc网络模型进行改进, 基于ImageNet数据集和微调技术获得分类训练网络模型, 对训练结果和车辆目标特征进行分析后进一步调整改进的算法参数, 最终获得更适合于道路车辆检测的YOLO-vocRV网络模型下车辆多目标检测方法; 为验证检测方法的有效性和完备性, 采用不同车流密度进行了车辆多目标检测试验, 并与经典YOLO-voc、YOLO9000模型进行了对比; 采用改进YOLO-vocRV网络模型, 选取20 000次迭代, 分析了多目标检测结果。试验结果表明: 在阻塞流样本条件下, YOLO9000网络模型检测率为93.71%, YOLO-voc网络模型检测率为94.48%, 改进YOLO-vocRV网络模型检测率达到了96.95%, 因此, 改进网络模型YOLOvocRV检测率较高; YOLO-vocRV模型精确度和召回率均聚集在0.95, 因此, 在获得较好精确度的条件下损失的召回率明显较小, 达到了很好的折中; 采用混合样本训练后, 基于YOLO-vocRV模型的车辆多目标检测方法的检测率在自由流状态下可达99.11%, 同步流状态下可达97.62%, 阻塞流状态下可达到97.14%, 具有较小的误检率和良好的鲁棒性。

     

  • 图  1  YOLO v2中CNN网络结构

    Figure  1.  CNN network structure in YOLO v2

    图  2  YOLO v2目标检测方法

    Figure  2.  YOLO v2target detection method

    图  3  试验模型测试结果

    Figure  3.  Test results of test models

    图  4  YOLO-vocRV网络结构

    Figure  4.  YOLO-vocRV network structure

    图  5  车辆检测流程

    Figure  5.  Process of vehicle detection

    图  6  自由流数据样本

    Figure  6.  Data samples of free flow

    图  7  同步流数据样本

    Figure  7.  Data samples of synchronous flow

    图  8  阻塞流数据样本

    Figure  8.  Data samples of blocking flow

    图  9  同步流条件下损失函数对数曲线

    Figure  9.  Loss function logarithmic curves under synchronous flow

    图  10  自由流条件下不同模型验证结果

    Figure  10.  Verification results of different models under free flow condition

    图  11  阻塞流条件下不同模型验证结果

    Figure  11.  Verification results of different models under blocking flow condition

    图  12  自由流训练样本下YOLO9000模型测试结果

    Figure  12.  Test results of YOLO9000model under free flow training samples

    图  13  自由流训练样本下YOLO-voc模型测试结果

    Figure  13.  Test results of YOLO-voc model under free flow training samples

    图  14  自由流训练样本下YOLO-vocRV模型测试结果

    Figure  14.  Test results of YOLO-vocRV model under free flow training samples

    图  15  同步流训练样本下YOLO9000模型测试结果

    Figure  15.  Test results of YOLO9000model under synchronous flow training samples

    图  16  同步流训练样本下YOLO-voc模型测试结果

    Figure  16.  Test results of YOLO-voc model under synchronous flow training samples

    图  17  同步流训练样本下YOLO-vocRV模型测试结果

    Figure  17.  Test results of YOLO-vocRV model under synchronous flow training samples

    图  18  阻塞流下训练20 000次YOLO9000模型的测试结果

    Figure  18.  Test results of YOLO9000model under block flow and training iteration 20 000times

    图  19  阻塞流下训练20 000次YOLO-voc模型的测试结果

    Figure  19.  Test results of YOLO-voc model under block flow and training iteration 20 000times

    图  20  阻塞流下训练20 000次YOLO-vocRV模型的测试结果

    Figure  20.  Test results of YOLO-vocRV model under block flow and training iteration 20 000times

    表  1  网络框架

    Table  1.   Network framework

    下载: 导出CSV

    表  2  同步流下不同模型训练样本结果

    Table  2.   Results of different models under synchronous flow training samples

    下载: 导出CSV

    表  3  阻塞流下不同模型训练样本结果

    Table  3.   Results of different models under block flow training samples

    下载: 导出CSV

    表  4  混合训练样本下YOLO-vocRV模型测试结果

    Table  4.   Test results of YOLO-vocRV model under mixed training samples

    下载: 导出CSV
  • [1] OTTLIK A, NAGEL H H. Initialization of model-based vehicle-tracking in video sequences[J]. International Journal of Computer Vision, 2008, 80 (2): 211-225. doi: 10.1007/s11263-007-0112-6
    [2] FLEYEH H, DAVAMI E. Eigen-based traffic sign recognition[J]. IET Intelligent Transport Systems, 2011, 5 (3): 190-196. doi: 10.1049/iet-its.2010.0159
    [3] 高云峰, 徐立鸿, 胡华, 等. 交叉口定周期信号控制多目标优化方法[J]. 中国公路学报, 2011, 24 (5): 82-88. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL201105014.htm

    GAO Yun-feng, XU Li-hong, HU Hua, et al. Multiobjective optimization method for fixed-time signal control at intersection[J]. China Journal of Highway and Transport, 2011, 24 (5): 82-88. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL201105014.htm
    [4] CHOIM K, PARK J, LEE S C. Event classification for vehicle navigation system by regional optical flow analysis[J]. Machine Vision and Applications, 2014, 25 (3): 547-559. doi: 10.1007/s00138-011-0384-2
    [5] 高韬, 刘正光, 岳士宏, 等. 用于智能交通的运动车辆跟踪算法[J]. 中国公路学报, 2010, 23 (3): 89-94. doi: 10.3969/j.issn.1001-7372.2010.03.014

    GAO Tao, LIU Zheng-guang, YUE Shi-hong, et al. Moving vehicle tracking algorithm used for intelligent traffic[J]. China Journal of Highway and Transport, 2010, 23 (3): 89-94. (in Chinese). doi: 10.3969/j.issn.1001-7372.2010.03.014
    [6] TEOHS S, BRÄUNL T. Symmetry-based monocular vehicle detection system[J]. Machine Vision and Applications, 2012, 23 (5): 831-842. doi: 10.1007/s00138-011-0355-7
    [7] LALIMI M A, GHOFRANI S, MCLERNON D et al. A vehicle license plate detection method using region and edge based methods[J]. Computers and Electrical Engineering, 2013, 39 (3): 834-845. doi: 10.1016/j.compeleceng.2012.09.015
    [8] LONG W, YANG Y H. Stationary background generation: an alternative to the difference of two images[J]. Pattern Recognition, 1990, 23 (12): 1351-1359. doi: 10.1016/0031-3203(90)90081-U
    [9] 田军, 魏振华, 武思远. 能量法的自适应背景更新算法[J]. 计算机科学与探索, 2009, 3 (2): 218-224. doi: 10.3778/j.issn.1673-9418.2009.02.010

    TIAN Jun, WEI Zhen-hua, WU Si-yuan. A self-adaptive background updating algorithm of energy method[J]. Journal of Frontiers of Computer Science and Technology, 2009, 3 (2): 218-224. (in Chinese). doi: 10.3778/j.issn.1673-9418.2009.02.010
    [10] 李喜来, 李艾华, 白向峰. 智能交通系统运动车辆的光流法检测[J]. 光电技术应用, 2010, 25 (2): 75-78. doi: 10.3969/j.issn.1673-1255.2010.02.021

    LI Xi-lai, LI Ai-hua, BAI Xiang-feng. Moving vehicles detection in intelligent transportation systems based on optical flow[J]. Electro-Optic Technology Application, 2010, 25 (2): 75-78. (in Chinese). doi: 10.3969/j.issn.1673-1255.2010.02.021
    [11] 梁敏健, 崔啸宇, 宋青松, 等. 基于HOG-Gabor特征融合与Softmax分类器的交通标志识别方法[J]. 交通运输工程学报, 2017, 17 (3): 151-158. http://transport.chd.edu.cn/article/id/201703016

    LIANG Min-jian, CUI Xiao-yu, SONG Qing-song, et al. Traffic sign recognition method based on HOG-Gabor feature fusion and Softmax classifier[J]. Journal of Traffic and Transportation Engineering, 2017, 17 (3): 151-158. (in Chinese). http://transport.chd.edu.cn/article/id/201703016
    [12] AHONEN T, HADID A, PIETIKÄINEN M. Face description with local binary patterns: application to face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28 (12): 2037-2041. doi: 10.1109/TPAMI.2006.244
    [13] SIVARAMAN S, TRIVEDI M M. Active learning for on-road vehicle detection: a comparative study[J]. Machine Vision and Applications, 2014, 25 (3): 599-611. doi: 10.1007/s00138-011-0388-y
    [14] 王永忠, 梁彦, 潘泉, 等. 基于自适应混合高斯模型的时空背景建模[J]. 自动化学报, 2009, 35 (4): 371-378. https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO200904008.htm

    WANG Yong-zhong, LIANG Yan, PAN Quan, et al. Spatiotemporal background modeling based on adaptive mixture of Gaussians[J]. Acta Automatica Sinica, 2009, 35 (4): 371-378. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO200904008.htm
    [15] 金立生, 王岩, 刘景华, 等. 基于Adaboost算法的日间前方车辆检测[J]. 吉林大学学报: 工学版, 2014, 44 (6): 1604-1608. https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY201406011.htm

    JIN Li-sheng, WANG Yan, LIU Jing-hua, et al. Front vehicle detection based on Adaboost algorithm in daytime[J]. Journal of Jilin University: Engineering and Technology Edition, 2014, 44 (6): 1604-1608. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY201406011.htm
    [16] 徐姗姗, 刘应安, 徐昇. 基于卷积神经网络的木材缺陷识别[J]. 山东大学学报: 工学版, 2013, 43 (2): 23-28. https://www.cnki.com.cn/Article/CJFDTOTAL-SDGY201302006.htm

    XU Shan-shan, LIU Ying-an, XU Sheng. Wood defects recognition based on the convolutional neural network[J]. Journal of Shandong University: Engineering Science, 2013, 43 (2): 23-28. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-SDGY201302006.htm
    [17] 丁松涛, 曲仕茹. 基于深度学习的交通目标感兴趣区域检测[J]. 中国公路学报, 2018, 31 (9): 167-174. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL201809020.htm

    DING Song-tao, QU Shi-ru. Traffic object detection based on deep learning with region of interest selection[J]. China Journal of Highway and Transport, 2018, 31 (9): 167-174. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL201809020.htm
    [18] LIM K, HONG Y, CHOI Y, et al. Real-time traffic sign recognition based on a general purpose GPU and deeplearning[J]. Plos One, 2017, 12 (3): 1-22.
    [19] TANAKA M, MORIE T. Shadow detection and elimination using a light-source color vector and its application to invehicle camera images[J]. International Journal of Innovative Computing, Information and Control, 2015, 11 (3): 865-879.
    [20] HE Kai-ming, ZHANG Xiang-yu, REN Shao-qing, et al. Delving deepintorectifiers: surpassinghuman-level performance on imagenet classification[C]//IEEE. 15th IEEE International Conference on Computer Vision. New York: IEEE, 2015: 1026-1034.
    [21] SZEGEDY C, TOSHEV A, ERHAN D. Deep neural networks for object detection[C]//Neural Information Processing Systems Foundation. 27th Annual Conference on Neural Information Processing Systems. La Jolla: Neural Information Processing Systems Foundation, 2013: 1-9.
    [22] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//IEEE. 27th IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2014: 1-21.
    [23] 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.
    [24] GIRSHICK R. Fast R-CNN[C]//IEEE. 15th IEEE International Conference on Computer Vision. New York: IEEE, 2015: 1440-1448.
    [25] REN Shao-qing, HE Kai-ming, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137-1149.
    [26] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//IEEE. 29th IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2016: 779-788.
    [27] AHONEN T, HADID A, PIETIKÄINEN M. Face description with local binary patterns: application to face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28 (12): 2037-2041.
    [28] DONG Jing-wei, SUN Mei-ting, LIANG Geng-rui, et al. The improved neural network algorithm of license plate recognition[J]. International Journal of Signal Processing, Image Processing and Pattern Recognition, 2015, 8 (5): 49-54.
    [29] 梁琳, 何卫平, 雷蕾, 等. 光照不均图像增强方法综述[J]. 计算机应用研究, 2010, 27 (5): 1625-1628. https://www.cnki.com.cn/Article/CJFDTOTAL-JSYJ201005008.htm

    LIANG Lin, HE Wei-ping, LEI Lei, et al. Survey on enhancement methods for non-uniform illumination image[J]. Application Research of Computers, 2010, 27 (5): 1625-1628. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JSYJ201005008.htm
    [30] LI Xun, ZHAO Zheng-fan, LIU Li, et al. An optimization model of multi-intersection signal control for trunk road under collaborative information[J]. Journal of Control Science and Engineering, 2017, 2017: .
  • 加载中
图(20) / 表(4)
计量
  • 文章访问数:  1026
  • HTML全文浏览量:  246
  • PDF下载量:  424
  • 被引次数: 0
出版历程
  • 收稿日期:  2018-06-26
  • 刊出日期:  2018-12-25

目录

    /

    返回文章
    返回