Image-to-Image Learning to Predict Traffic Speeds by Considering Area-Wide Spatio-Temporal Dependencies

Spatio-temporal dependencies are the key to predicting the traffic parameters of an urban arterial network. However, their inclusion in forecasting traffic states has been hampered due to both the absence of a robust model and the computational burden. Recently, an innovative way to tackle the problem was developed by adopting a convolutional neural network (CNN) to deal with map images representing traffic states. Unlike previous studies that utilized map images only for input, the present study adopted images for both the input and the output of a CNN model to predict traffic speeds. The results show that the performance of the proposed model based on image-to-image learning is superior to that of the existing models.

[1]  Keemin Sohn,et al.  Image-Based Learning to Measure Traffic Density Using a Deep Convolutional Neural Network , 2018, IEEE Transactions on Intelligent Transportation Systems.

[2]  Andreas Hegyi,et al.  An unscented Kalman filter for freeway traffic estimation , 2006 .

[3]  Yiannis Kamarianakis,et al.  Space-time modeling of traffic flow , 2002, Comput. Geosci..

[4]  Eleni I. Vlahogianni,et al.  Short‐term traffic forecasting: Overview of objectives and methods , 2004 .

[5]  L. H. Immers,et al.  An Extended Kalman Filter Application for Traffic State Estimation Using CTM with Implicit Mode Switching and Dynamic Parameters , 2007, 2007 IEEE Intelligent Transportation Systems Conference.

[6]  Chao Zhang,et al.  Multiple sources and multiple measures based traffic flow prediction using the chaos theory and support vector regression method , 2017 .

[7]  Yong Wang,et al.  Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction , 2017, Sensors.

[8]  Yunpeng Wang,et al.  Long short-term memory neural network for traffic speed prediction using remote microwave sensor data , 2015 .

[9]  Jen-Tzung Chien,et al.  Image-text dual neural network with decision strategy for small-sample image classification , 2019, Neurocomputing.

[10]  Muhammad Tayyab Asif,et al.  Spatiotemporal Patterns in Large-Scale Traffic Speed Prediction , 2014, IEEE Transactions on Intelligent Transportation Systems.

[11]  Wenhao Huang,et al.  Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning , 2014, IEEE Transactions on Intelligent Transportation Systems.

[12]  David Zhang,et al.  Moving Vehicle Detection for Automatic Traffic Monitoring , 2007, IEEE Transactions on Vehicular Technology.

[13]  Yunpeng Wang,et al.  A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting , 2016 .

[14]  Jan-Ming Ho,et al.  Travel time prediction with support vector regression , 2003, Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems.

[15]  Dali Wei,et al.  An Adaptive-Margin Support Vector Regression for Short-Term Traffic Flow Forecast , 2013, J. Intell. Transp. Syst..

[16]  Matthew G. Karlaftis,et al.  A multivariate state space approach for urban traffic flow modeling and prediction , 2003 .

[17]  Haitham Al-Deek,et al.  Predictions of Freeway Traffic Speeds and Volumes Using Vector Autoregressive Models , 2009, J. Intell. Transp. Syst..

[18]  Su Yang,et al.  On feature selection for traffic congestion prediction , 2013 .

[19]  Bart De Schutter,et al.  A comparison of filter configurations for freeway traffic state estimation , 2006, 2006 IEEE Intelligent Transportation Systems Conference.

[20]  Chao Chen,et al.  Short‐Term Traffic Speed Prediction for an Urban Corridor , 2017, Comput. Aided Civ. Infrastructure Eng..

[21]  Billy M. Williams,et al.  Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis and Empirical Results , 2003, Journal of Transportation Engineering.

[22]  Yinhai Wang,et al.  Short-Term Speed Prediction Using Remote Microwave Sensor Data: Machine Learning versus Statistical Model , 2016 .

[23]  C. Daganzo.  THE CELL TRANSMISSION MODEL.. , 1994 .

[24]  Keemin Sohn,et al.  Artificial intelligence for traffic signal control based solely on video images , 2018, J. Intell. Transp. Syst..

[25]  Bin Ran,et al.  A Comparison of Traffic Flow Prediction Methods Based on DBN , 2016 .

[26]  Simon P. Wilson,et al.  Multivariate Short-Term Traffic Flow Forecasting Using Bayesian Vector Autoregressive Moving Average Model , 2012 .

[27]  한보형,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015 .

[28]  P. Abbeel,et al.  Short – Term Traffic Forecasting : Modeling and Learning Spatio – Temporal Relations in Transportation Networks Using Graph Neural Networks by Behrooz Shahsavari Research Project , 2015 .

[29]  Quoc V. Le,et al.  On optimization methods for deep learning , 2011, ICML.

[30]  Yunpeng Wang,et al.  Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks , 2017, Sensors.

[31]  Jin Wang,et al.  Short-term traffic speed forecasting hybrid model based on Chaos–Wavelet Analysis-Support Vector Machine theory , 2013 .

[32]  Jun Guo,et al.  Cross-modal subspace learning for fine-grained sketch-based image retrieval , 2017, Neurocomputing.

[33]  Xiuwen Yi,et al.  DNN-based prediction model for spatio-temporal data , 2016, SIGSPATIAL/GIS.

[34]  Steven I-Jy Chien,et al.  DYNAMIC TRAVEL TIME PREDICTION WITH REAL-TIME AND HISTORICAL DATA , 2003 .

[35]  Fei-Yue Wang,et al.  Traffic Flow Prediction With Big Data: A Deep Learning Approach , 2015, IEEE Transactions on Intelligent Transportation Systems.