交通运输系统工程与信息

交通运输系统工程与信息 ›› 2022, Vol. 22 ›› Issue (3): 158-167.DOI: 10.16097/j.cnki.1009-6744.2022.03.018

• 系统工程理论与方法 • 上一篇    下一篇

基于生成对抗网络的交通流参数实时估计模型

姚荣涵1，王荣贇1，张文松1，叶劲松* 2，孙锋3   

  1. 1. 大连理工大学，交通运输学院，辽宁 大连 116024；2. 交通运输部科学研究院，综合交通运输大数据应用技术交通运输行业重点实验室，北京 100029；3. 山东理工大学，交通与车辆工程学院，山东 淄博 255049
  • 收稿日期:2022-01-09 修回日期:2022-03-13 接受日期:2022-03-23 出版日期:2022-06-25 发布日期:2022-06-22
  • 作者简介:姚荣涵(1979- )，女，山西运城人，副教授，博士。
  • 基金资助:
    国家自然科学基金；交通运输部科学研究院综合交通运输大数据应用技术交通运输行业重点实验室开放课题

Real-time Traffic Flow Parameters Estimation Model Based on Generative Adversarial Network

YAO Rong-han1 , WANG Rong-yun1 , ZHANG Wen-song1 , YE Jin-song* 2 , SUN Feng3   

  1. 1. School of Transportation and Logistics, Dalian University of Technology, Dalian 116024, Liaoning, China; 2. Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport, China Academy of Transportation Sciences, Beijing 100029, China; 3. School of Transportation and Vehicle Engineering, Shandong University of Technology, Zibo 255049, Shandong, China
  • Received:2022-01-09 Revised:2022-03-13 Accepted:2022-03-23 Online:2022-06-25 Published:2022-06-22
  • Supported by:
    National Natural Science Foundation of China(52172314)；Open Foundation of Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport(2020B1203)。

PDF

摘要： 为有效调控道路网时空资源，需实时估计交通流参数。若要准确估计交通流参数，应详细考虑道路网交通流时空特征。本文基于生成对抗网络，提出一种能捕捉交通流时空特征的实时估计模型，即TSTGAN模型。该模型包括生成器和判别器两部分，生成器利用门控卷积神经网络 捕捉交通流的动态空间特征，使用基于注意力机制的长短期记忆神经网络分析交通流的动态时间特征；采用门控卷积神经网络与长短期记忆神经网络构建判别器；通过对抗方式训练生成对抗网络的生成器与判别器，实时获得交通流参数估计值。使用中国山东省淄博市12个卡口设备和美国加州洛杉矶市23个线圈检测器获得的交通流量数据，验证TSTGAN模型的可靠性。结果表 明，TSTGAN模型引入的时空模块能有效提取交通流的时空特征，所得均方根误差和平均绝对误差比现有模型分别降低2.12%~42.41%和1.66%~40.49%，证明所提TSTGAN模型可以提高交通 流参数的估计精度。

关键词: 智能交通, 生成对抗网络, 深度学习, 交通流参数, 时空特征

Abstract: To effectively allocate the spatio-temporal resources of a road network, it is necessary to estimate the traffic flow parameters in real time. The accurate estimation of traffic flow parameters requires the detailed consideration of the spatio-temporal characteristics of traffic flow in the road network. Based on the generative adversarial network, a real-time estimation model that can capture the spatio-temporal characteristics of traffic flow was formulated, that is, the TSTGAN model. This model included a generator and a discriminator. In the generator, the gated convolutional neural network was used to capture the dynamic spatial characteristics of traffic flow, and the long short-term memory neural network based on the attention mechanism was used to analyze the dynamic temporal characteristics of traffic flow. The discriminator consisted of the gated convolutional neural network and the long short-term memory neural network. The generator and discriminator in the generative adversarial network were trained by an adversarial mode, and the real-time estimated values of traffic flow parameters were obtained. The reliability of the TSTGAN model was validated using the traffic flow data obtained from 12 bayonet devices in Zibo City, Shandong Province, China, and 23 loop detectors in Los Angeles, California, America. The results show that: the introduced spatio-temporal block in the TSTGAN model can effectively extract the spatio-temporal characteristics of traffic flow, and the obtained root meansquare and mean absolute errors decrease by 2.12%~42.41% and 1.66%~40.49%, respectively, compared with those obtained from the existing models, which indicates that the formulated TSTGAN model can improve the estimation precision of traffic flow parameters.

Key words: intelligent transportation, generative adversarial network, deep learning, traffic flow parameters, spatiotemporal characteristics

中图分类号: