+高级检索
首页 > 过刊浏览>2021年第44卷第4期 >107-116. DOI:10.11835/j.issn.1000-582X.2020.298
PDF HTML阅读 XML下载 导出引用 引用提醒
基于深度学习的交通拥堵检测
作者:
中图分类号:

TP751

基金项目:

国家自然科学基金资助项目（61604105）。


Traffic congestion detection based on deep learning
Author:
  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [16]
    • |
  • 相似文献 [20]
    • | | |
  • 文章评论
    摘要:

    针对交通拥堵检测，提出一种利用深度学习中卷积神经网络（convolutional neural network，CNN）对交通拥堵图像进行检测的方法。首先，使用基于TensorFlow框架设计了含有三层卷积层的神经网络分类模型。其次，利用道路拥堵与非拥堵图片对分类模型进行训练，并进行评估。最后，利用训练完成的模型进行道路拥堵检测，与多种深度学习分类模型分类方法进行对比实验，表明该卷积神经网络模型能够更有效地进行拥堵检测，检测准确率达到了98.1%。

    Abstract:

    Aimed at traffic congestion detection, a method of detecting traffic congestion images using convolutional neural network (CNN) was proposed. First, a neural network classification model with three layers of convolutional layers was designed based on the TensorFlow framework. Then, the classification model was trained and evaluated using road congestion and non-congestion pictures. Finally, the well-trained model was used to carry out road congestion detection. Compared with many other deep learning classification models, the proposed convolutional neural network model showed high efficiency in congestion detection, and the detection accuracy reached 98.1%.

    参考文献
    [1] 郭继孚, 刘莹, 余柳. 对中国大城市交通拥堵问题的认识[J].城市交通,2011, 9(2):8-14. Guo J F, Liu Y, Yu L. Traffic congestion in large metropolitan area in China[J]. Urban Transport of China, 2011, 9(2):8-14. (in Chinese)
    [2] 邓顺熙, 陈爱侠, 曹申存. 高速公路汽车污染物排放因子的测试与研究[J].中国公路学报,1999(S1):96-102. Deng S X, Chen A X, Cao S C. An experimental study of emission factors of vehicular pollutants in a freeway tunnel[J]. China Journal of Highway and Transport, 1999(S1):96-102. (in Chinese)
    [3] Sikirić I, Brkić K, Bevandić P, et al. Traffic scene classification on a representation budget[J]. IEEE transactions on intelligent transportation systems, 2019, 21(1):336-345.
    [4] 黄磊磊, 汤一平, 孟焱. 基于机器视觉的道路拥堵状态检测的研究[J]. 小型微型计算机系统, 2014,35(1):148-153. Huang L L, Tang Y P, Meng Y. Research on road congestion state detection based on machine vision[J]. Journal of Chinese Computer Systems, 2014,35(1):148-153. (in Chinese)
    [5] Desa S M, Salih Q A. Image subtraction for real time moving object extraction[C]//International Conference on Computer Graphics, Imaging & Visualization. New York, NY, USA:IEEE, 2004:41-45.
    [6] 安纪存, 吕鑫, 季琳雅. 不完全数据下基于时空相关性拥堵预测方法[J]. 计算机工程与应用, 2019, 55(4):96-100,124. An J C, Lv X, Ji L Y. Traffic congestion prediction based on spatial-temporal correlation with incomplete data[J]. Computer Engineering and Applications, 2019,55(4):96-100,124. (in Chinese)
    [7] Guillaume R, Soullard Y, Chatelain C, et al. Fully convolutional network with dilated convolutions for handwritten text line segmentation[J]. International Journal on Document Analysis and Recognition, 2018, 3(21):177-186.
    [8] Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
    [9] Krizhevsky A, Sutskever I, Hinton G. ImageNet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012, 25(2):1097-1105.
    [10] Schlichtkrull M, Kipf T N, Bloem P, et al. Modeling relational data with graph convolutional networks[J/OL]. arXiv, 2017(2017-10-26)[2020-01-25]. https://arxiv.org/pdf/1703.06103.pdf.
    [11] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Las Vegas, NV, USA, June 27-30,2016. IEEE, 2016:770-778.
    [12] Howard A G, Zhu M, Chen B, et al. MobileNets:efficient convolutional neural networks for mobile vision applications[J/OL]. Computer Vision and Pattern Recognition,2017[2020-01-25]. https://arxiv.org/abs/1704.04861.
    [13] 罗荣辉,袁航,钟发海,等.基于卷积神经网络的道路拥堵识别研究[J].郑州大学学报(工学版), 2019,40(2):18-22. Luo R H, Yuang H, Zhong F H, et al. Traffic jam detection based on convolutional neural network[J]. Journal of Zhengzhou University (Engineering Science), 2019, 40(2):18-22. (in Chinese)
    [14] Krizhevsky A, Sutskever I, Hinton G. ImageNet classification with deep convolutional neural networks[C]//NIPS'12:Proceedings of the 25th International Comference on Neural Information Proceessing Systems. NY, United States:Curran Associates Inc, 2012,1:1097-1105.
    [15] Li Z, Jiang L Y, Zhu Z Q, et al. Vehicle classification for large-scale traffic surveillance videos using Convolutional Neural Networks[J]. Machine Vision and Applications,2017,28(7):793-802.
    [16] Liu X, Liu W, Ma H, et al. Large-scale vehicle re-identification in urban surveillance videos[C]//IEEE International Conference on Multimedia and Expo (ICME) 2016. New York, USA:IEEE, 2016:1-6.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

丁洁,刘晋峰,杨祖莨,阎高伟.基于深度学习的交通拥堵检测[J].重庆大学学报,2021,44(4):107-116.

复制
分享
文章指标
  • 点击次数:1057
  • 下载次数: 1796
  • HTML阅读次数: 2679
  • 引用次数: 0
历史
  • 收稿日期:2019-12-13
  • 在线发布日期: 2021-04-20
文章二维码
您是第11664838 位访问者
主管单位：中华人民共和国教育部
主办单位：重庆大学
地址：重庆市沙坪坝正街174号
电话：
重庆大学学报 ® 2025 版权所有