Traffic density estimation under heterogeneous traffic conditions using data fusion

Data fusion is one of the recent approaches in traffic analysis for the accurate estimation and prediction of traffic parameters. In this approach, the parameters are estimated using the data from more than one source for better accuracy. This paper discusses a model based approach to estimate the parameters of heterogeneous traffic using both location data and spatial data using data fusion. The proposed method uses the Kalman filtering technique for the estimation of traffic density. Traffic density is a spatial parameter which is difficult to measure directly from field and can be measured only using aerial photography. Hence, it is usually estimated from other easily measurable parameters such as speed, flow, etc., or from a combination of such parameters. The present study estimates density using the flow values measured from video and the travel time obtained from Global Positioning System (GPS) equipped vehicles. The study also reports density estimation using flow and Space Mean Speed (SMS) obtained from location based data alone without fusing with spatial data, using the Extended Kalman filter technique. The estimates are corroborated using actual values and the results show data fusion performing better while estimating density.

[1]  John N. Ivan.  Neural network representations for arterial street incident detection data fusion 1 1 The contents o , 1997 .

[2]  Donald J Dailey,et al.  ITS DATA FUSION , 1996 .

[3]  Alexandre M. Bayen,et al.  Evaluation of traffic data obtained via GPS-enabled mobile phones: The Mobile Century field experiment , 2009 .

[4]  Zhipeng Li,et al.  An Approach to Urban Traffic State Estimation by Fusing Multisource Information , 2009, IEEE Transactions on Intelligent Transportation Systems.

[5]  So Young Sohn,et al.  Data fusion, ensemble and clustering to improve the classification accuracy for the severity of road traffic accidents in Korea , 2003 .

[6]  Kay W. Axhausen,et al.  Optimization of Large Transport Networks Using the Ant Colony Heuristic , 2009, Comput. Aided Civ. Infrastructure Eng..

[7]  Greg Welch,et al.  An Introduction to Kalman Filter , 1995, SIGGRAPH 2001.

[8]  El Faouzi Nour-Eddin.  Bayesian and Evidential Approaches for Traffic Data Fusion: Methodological Issues and Case Study , 2006 .

[9]  Lelitha Vanajakshi,et al.  Location-Based Data for Estimated Traffic on Urban Arterial in Heterogeneous Traffic Conditions , 2011 .

[10]  Serge P. Hoogendoorn,et al.  A Robust and Efficient Method for Fusing Heterogeneous Data from Traffic Sensors on Freeways , 2010, Comput. Aided Civ. Infrastructure Eng..

[11]  Martin Treiber,et al.  Reconstructing the Traffic State by Fusion of Heterogeneous Data , 2009, Comput. Aided Civ. Infrastructure Eng..

[12]  Lawrence A. Klein,et al.  Sensor and Data Fusion: A Tool for Information Assessment and Decision Making , 2004 .

[13]  Xiaoyan Zhang,et al.  Short-term travel time prediction , 2003 .

[14]  Peter J. Bickel,et al.  Day-to-Day Travel-Time Trends and Travel-Time Prediction from Loop-Detector Data , 2000 .

[15]  Adolf D. May,et al.  Traffic Flow Fundamentals , 1989 .

[16]  L. Chu.  Adaptive Kalman Filter Based Freeway Travel time Estimation , 2004 .

[17]  Nour-Eddin El Faouzi,et al.  Improving Travel Time Estimates from Inductive Loop and Toll Collection Data with Dempster–Shafer Data Fusion , 2009 .

[18]  Lawrence A. Klein.  Data Fusion Algorithms and Architectures , 2004 .

[19]  Lelitha Vanajakshi,et al.  Estimation of Traffic Density under Indian Traffic Conditions , 2010 .