A pattern recognition algorithm for assessing trajectory completeness

Vehicular trajectories are widely used for car-following (CF) model calibration and validation, as they embody characteristics of individual driving behaviour (each trajectory reflects an individual driver). Previous studies have highlighted that the trajectories should contain all the major vehicular interactions (driving regimes) between the leader and the follower for reliable CF model calibration and validation. Based on Dynamic Time Warping and Bottom-Up algorithms, this paper develops a pattern recognition algorithm for vehicle trajectories (PRAVT) to objectively, accurately, and automatically differentiate different driving regimes in a trajectory and then select the most complete trajectories (i.e. trajectories containing a maximum number of regimes). PRAVT is rigorously tested using synthetic data and then applied to the NGSIM data. We have observed that the NGSIM data are dominated by the trajectories which contain only three regimes, namely acceleration, deceleration, and following, 77% of the trajectories lack the standstill regime, and no trajectory in the NGSIM data is complete. These findings’ impact on how to properly utilize NGSIM data can be profound. Given the extensive use of the NGSIM data in the traffic flow community, this paper also provides insights about the types of regimes contained in each trajectory of the NGSIM data.

[1]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[2]  Richard J. Beckman,et al.  A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output From a Computer Code , 2000, Technometrics.

[3]  Serge P. Hoogendoorn,et al.  Wiedemann Revisited , 2011 .

[4]  Nikolaos Geroliminis,et al.  Empirical observations of capacity drop in freeway merges with ramp control and integration in a first-order model , 2013 .

[5]  E. Caiani,et al.  Warped-average template technique to track on a cycle-by-cycle basis the cardiac filling phases on left ventricular volume , 1998, Computers in Cardiology 1998. Vol. 25 (Cat. No.98CH36292).

[6]  Soyoung Ahn,et al.  Microscopic traffic hysteresis in traffic oscillations : a behavioral perspective , 2012 .

[7]  Serge P. Hoogendoorn,et al.  Car-Following Behavior Analysis from Microscopic Trajectory Data , 2005 .

[8]  Eamonn J. Keogh,et al.  Derivative Dynamic Time Warping , 2001, SDM.

[9]  Marcello Montanino,et al.  Can Results of car-following Model Calibration Based on Trajectory Data be Trusted? , 2012 .

[10]  Marcello Montanino,et al.  Do We Really Need to Calibrate All the Parameters? Variance-Based Sensitivity Analysis to Simplify Microscopic Traffic Flow Models , 2015, IEEE Transactions on Intelligent Transportation Systems.

[11]  Thamara Vieira da Rocha,et al.  Does traffic-related calibration of car-following models provide accurate estimations of vehicle emissions? , 2015 .

[12]  Simon Washington,et al.  Revisiting the Task-Capability interface model for incorporating human factors into car-following models , 2015 .

[13]  Xuesong Zhou,et al.  Simplified, data-driven, errorable car-following model to predict the safety effects of distracted driving , 2012, 2012 15th International IEEE Conference on Intelligent Transportation Systems.

[14]  Byungkyu Park,et al.  Development and Evaluation of a Procedure for the Calibration of Simulation Models , 2005 .

[15]  Bin Ran,et al.  Cycle-by-Cycle Queue Length Estimation for Signalized Intersections Using Sampled Trajectory Data , 2011 .

[16]  P. G. Gipps,et al.  A MODEL FOR THE STRUCTURE OF LANE-CHANGING DECISIONS , 1986 .

[17]  Eamonn J. Keogh,et al.  An Enhanced Representation of Time Series Which Allows Fast and Accurate Classification, Clustering and Relevance Feedback , 1998, KDD.

[18]  Marcello Montanino,et al.  Trajectory data reconstruction and simulation-based validation against macroscopic traffic patterns , 2015 .

[19]  Peter Wagner,et al.  Analyzing fluctuations in car-following , 2012 .

[20]  Haris N. Koutsopoulos,et al.  Integrated driving behavior modeling , 2007 .

[21]  Marcello Montanino,et al.  Calibration of microscopic traffic flow models against time-series data , 2012, 2012 15th International IEEE Conference on Intelligent Transportation Systems.

[22]  Eamonn J. Keogh,et al.  Segmenting Time Series: A Survey and Novel Approach , 2002 .

[23]  Hani S. Mahmassani,et al.  Driver Car-Following Behavior: From Discrete Event Process to Continuous Set of Episodes , 2008 .

[24]  Martin Treiber,et al.  How Much Does Traffic Congestion Increase Fuel Consumption and Emissions? Applying Fuel Consumption Model to NGSIM Trajectory Data , 2008 .

[25]  Christine Buisson,et al.  Estimating Individual Speed-Spacing Relationship and Assessing Ability of Newell's Car-Following Model to Reproduce Trajectories , 2008 .

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

[27]  Vincenzo Punzo,et al.  How Parameters of Microscopic Traffic Flow Models Relate to Traffic Dynamics in Simulation , 2009 .

[28]  Hariharan Subramanian,et al.  Estimation of car-following models , 1996 .

[29]  Vincenzo Punzo,et al.  Analysis and Comparison of Microscopic Traffic Flow Models with Real Traffic Microscopic Data , 2005 .

[30]  Pavel Senin,et al.  Dynamic Time Warping Algorithm Review , 2008 .

[31]  Serge Hoogendoorn,et al.  Calibration of microscopic traffic-flow models using multiple data sources , 2010, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[32]  Donald J. Berndt,et al.  Using Dynamic Time Warping to Find Patterns in Time Series , 1994, KDD Workshop.

[33]  Soyoung Ahn,et al.  Verification of a simplified car-following theory , 2004 .

[34]  Soyoung Ahn,et al.  The effects of lane-changing on the immediate follower : anticipation, relaxation, and change in driver characteristics , 2013 .

[35]  Henry X. Liu,et al.  Real-time queue length estimation for congested signalized intersections , 2009 .

[36]  Alexandre M. Bayen,et al.  Traffic flow reconstruction using mobile sensors and loop detector data , 2007 .

[37]  Rahim F Benekohal,et al.  Linear Acceleration Car-Following Model Development and Validation , 1998 .

[38]  P. G. Gipps,et al.  A behavioural car-following model for computer simulation , 1981 .

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

[40]  Eamonn J. Keogh,et al.  Exact indexing of dynamic time warping , 2002, Knowledge and Information Systems.

[41]  Punzo Vincenzo,et al.  The Calibration of Traffic Simulation Models : Report on the assessment of different Goodness of Fit measures and Optimization AlgorithmsMULTITUDE Project – COST Action TU0903 , 2012 .

[42]  K. Ahmed.  Modeling drivers' acceleration and lane changing behavior , 1999 .

[43]  Simon Washington,et al.  Understanding the mechanism of traffic hysteresis and traffic oscillations through the change in task difficulty level , 2017 .

[44]  Romain Billot,et al.  Calibration, Estimation, and Sampling Issues of Car-Following Parameters , 2014 .

[45]  Soyoung Ahn,et al.  Freeway traffic oscillations : microscopic analysis of formations and propagations using Wavelet Transform , 2011 .

[46]  Klaus Gollmer,et al.  Detection of distorted pattern using dynamic time warping algorithm and application for supervision , 1995 .

[47]  Zuduo Zheng,et al.  Recent developments and research needs in modeling lane changing , 2014 .

[48]  Ludovic Leclercq,et al.  A mechanism to describe the formation and propagation of stop-and-go waves in congested freeway traffic , 2010, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[49]  Carlos F. Daganzo,et al.  Lane-changing in traffic streams , 2006 .

[50]  Serge P. Hoogendoorn,et al.  Validity of Trajectory-Based Calibration Approach of Car-Following Models in Presence of Measurement Errors , 2008 .

[51]  Peter Wagner,et al.  Calibration and Validation of Microscopic Traffic Flow Models , 2004, SimVis.

[52]  Paul R. Cohen,et al.  Learned models for continuous planning , 1999, AISTATS.

[53]  Martin Treiber,et al.  Microscopic Calibration and Validation of Car-Following Models – A Systematic Approach , 2013, 1403.4990.

[54]  M. Treiber,et al.  Estimating Acceleration and Lane-Changing Dynamics from Next Generation Simulation Trajectory Data , 2008, 0804.0108.

[55]  Soyoung Ahn,et al.  Applications of wavelet transform for analysis of freeway traffic : bottlenecks, transient traffic, and traffic oscillations , 2011 .

[56]  Carlos Agón,et al.  Time-series data mining , 2012, CSUR.

[57]  Kazuya Takeda,et al.  A Stochastic Approach for Modeling Lane-Change Trajectories , 2012 .

[58]  Katsuhiro Nishinari,et al.  Traffic Flow Dynamics: Data, Models and Simulation , 2014 .

[59]  Xuesong Zhou,et al.  Method for investigating intradriver heterogeneity using vehicle trajectory data: A Dynamic Time Warping approach , 2015 .

[60]  Vincenzo Punzo,et al.  On the assessment of vehicle trajectory data accuracy and application to the Next Generation SIMulation (NGSIM) program data , 2011 .

[61]  Ashish Bhaskar,et al.  Is more always better? The impact of vehicular trajectory completeness on car-following model calibration and validation , 2019, Transportation Research Part B: Methodological.

[62]  Gordon F. Newell,et al.  A simplified car-following theory: a lower order model , 2002 .

[63]  H Ozaki,et al.  REACTION AND ANTICIPATION IN THE CAR-FOLLOWING BEHAVIOR. , 1993 .

[64]  Soyoung Ahn,et al.  On the periodicity of traffic oscillations and capacity drop : the role of driver characteristics , 2014 .

[65]  Hussein Dia,et al.  Neural Agent Car-Following Models , 2007, IEEE Transactions on Intelligent Transportation Systems.