A Deep Learning-Based Framework for Intersectional Traffic Simulation and Editing

Most of existing traffic simulation methods have been focused on simulating vehicles on freeways or city-scale urban networks. However, relatively little research has been done to simulate intersectional traffic to date despite its broad potential applications. In this paper, we propose a novel deep learning-based framework to simulate and edit intersectional traffic. Specifically, based on an in-house collected intersectional traffic dataset, we employ the combination of convolution network (CNN) and recurrent network (RNN) to learn the patterns of vehicle trajectories in intersectional traffic. Besides simulating novel intersectional traffic, our method can be used to edit existing intersectional traffic. Through many experiments as well as comparative user studies, we demonstrate that the results by our method are visually indistinguishable from ground truth, and our method can outperform existing methods.

[1]  Xiaogang Jin,et al.  Detailed traffic animation for urban road networks , 2012, Graph. Model..

[2]  Irfan A. Essa,et al.  Gaussian process regression flow for analysis of motion trajectories , 2011, 2011 International Conference on Computer Vision.

[3]  Albert S. Huang,et al.  A Bayesian nonparametric approach to modeling motion patterns , 2011, Auton. Robots.

[4]  Sai-Keung Wong,et al.  Generating Believable Mixed-Traffic Animation , 2016, IEEE Transactions on Intelligent Transportation Systems.

[5]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[6]  G. F. Newell Nonlinear Effects in the Dynamics of Car Following , 1961 .

[7]  Qiang Meng,et al.  Classification and Regression Tree Approach for Predicting Drivers’ Merging Behavior in Short-Term Work Zone Merging Areas , 2012 .

[8]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[9]  G. Whitham,et al.  Linear and Nonlinear Waves , 1976 .

[10]  Alberto Del Bimbo,et al.  Context-Aware Trajectory Prediction , 2017, 2018 24th International Conference on Pattern Recognition (ICPR).

[11]  Fei-Fei Li,et al.  Socially-Aware Large-Scale Crowd Forecasting , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Silvio Savarese,et al.  Social LSTM: Human Trajectory Prediction in Crowded Spaces , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  V Shvetsov,et al.  Macroscopic dynamics of multilane traffic. , 1999, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[14]  Xiaogang Jin,et al.  Video-based personalized traffic learning , 2013, Graph. Model..

[15]  Eduard H. Hovy,et al.  End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF , 2016, ACL.

[16]  Jörg Stückler,et al.  Semi-Supervised Deep Learning for Monocular Depth Map Prediction , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Taesoo Kwon,et al.  Interactive manipulation of large-scale crowd animation , 2014, ACM Trans. Graph..

[18]  Harold J Payne,et al.  MODELS OF FREEWAY TRAFFIC AND CONTROL. , 1971 .

[19]  Hua Wang,et al.  An efficient lane model for complex traffic simulation , 2015, Comput. Animat. Virtual Worlds.

[20]  Martial Hebert,et al.  The Pose Knows: Video Forecasting by Generating Pose Futures , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[21]  Giuseppe Iazeolla,et al.  Simulation model building of traffic intersections , 2009, Simul. Model. Pract. Theory.

[22]  Michael Lam,et al.  Unsupervised Video Summarization with Adversarial LSTM Networks , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Silvio Savarese,et al.  Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[24]  Praveen Edara,et al.  Modeling Mandatory Lane Changing Using Bayes Classifier and Decision Trees , 2014, IEEE Transactions on Intelligent Transportation Systems.

[25]  G. Srinivasaraghavan,et al.  Human Trajectory Prediction using Spatially aware Deep Attention Models , 2017, ArXiv.

[26]  Rahul Narain,et al.  Implicit crowds , 2017, ACM Trans. Graph..

[27]  Alejandra Medina Flintsch,et al.  A rule-based neural network approach to model driver naturalistic behavior in traffic , 2013 .

[28]  Bohyung Han,et al.  Learning Multi-domain Convolutional Neural Networks for Visual Tracking , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Martin Treiber,et al.  Calibrating Car-Following Models by Using Trajectory Data , 2008, 0803.4063.

[30]  Ming C. Lin,et al.  Continuum Traffic Simulation , 2010, Comput. Graph. Forum.

[31]  Martial Hebert,et al.  Activity Forecasting , 2012, ECCV.

[32]  Zhanyi Hu,et al.  Learning Depth From Single Images With Deep Neural Network Embedding Focal Length , 2018, IEEE Transactions on Image Processing.

[33]  Jean Oh,et al.  Social Attention: Modeling Attention in Human Crowds , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[34]  Ming C. Lin,et al.  City-scale traffic animation using statistical learning and metamodel-based optimization , 2017, ACM Trans. Graph..

[35]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[36]  Rob Fergus,et al.  Depth Map Prediction from a Single Image using a Multi-Scale Deep Network , 2014, NIPS.

[37]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[38]  Kyunglyul Hyun,et al.  Synchronized multi-character motion editing , 2009, SIGGRAPH 2009.

[39]  Ming C. Lin,et al.  Flow reconstruction for data-driven traffic animation , 2013, ACM Trans. Graph..

[40]  Michael Schreckenberg,et al.  A cellular automaton model for freeway traffic , 1992 .

[41]  Taku Komura,et al.  Spatial relationship preserving character motion adaptation , 2010, SIGGRAPH 2010.

[42]  Zhigang Deng,et al.  AA‐FVDM: An accident‐avoidance full velocity difference model for animating realistic street‐level traffic in rural scenes , 2014, Comput. Animat. Virtual Worlds.

[43]  Julien Pettré,et al.  Imperceptible relaxation of collision avoidance constraints in virtual crowds , 2011, ACM Trans. Graph..

[44]  Dinesh Manocha,et al.  Virtualized Traffic: Reconstructing Traffic Flows from Discrete Spatio-Temporal Data , 2009, 2009 IEEE Virtual Reality Conference.

[45]  Dirk Helbing,et al.  Microsimulations of Freeway Traffic Including Control Measures , 2002, cond-mat/0210096.

[46]  Helbing,et al.  Congested traffic states in empirical observations and microscopic simulations , 2000, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[47]  Zhigang Deng,et al.  Realistic Data-Driven Traffic Flow Animation Using Texture Synthesis , 2018, IEEE Transactions on Visualization and Computer Graphics.

[48]  Dirk Helbing,et al.  General Lane-Changing Model MOBIL for Car-Following Models , 2007 .

[49]  Shenghua Gao,et al.  Encoding Crowd Interaction with Deep Neural Network for Pedestrian Trajectory Prediction , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[50]  Linsen Chong,et al.  Simulation of Driver Behavior with Agent-Based Back-Propagation Neural Network , 2011 .

[51]  Daniel Krajzewicz,et al.  Recent Development and Applications of SUMO - Simulation of Urban MObility , 2012 .

[52]  Ming C. Lin,et al.  WarpDriver: context-aware probabilistic motion prediction for crowd simulation , 2016, ACM Trans. Graph..

[53]  Zhigang Deng,et al.  A data-driven model for lane-changing in traffic simulation , 2016, Symposium on Computer Animation.

[54]  Zhigang Deng,et al.  Vehicle–pedestrian interaction for mixed traffic simulation , 2015, Comput. Animat. Virtual Worlds.