Automatic Incident Detection at Intersections with Use of Telematics

Abstract While there are many examples of Intelligent Transport System deployments in Poland, more attention should be paid to traffic incident management and detection on dual-carriageways and urban street networks. One of the aims of CIVITAS DYN@MO, a European Union funded project, is to use TRISTAR (an Urban Transport Management System) detection modules to detect incidents at junctions equipped with traffic signals. First part of paper provides an overview of urban incident detection methods and algorithms. Second part of paper describes how the TRISTAR system infrastructure and software are currently used for detecting incidents on urban artery sections (with higher speed limit). Because the need to detect incidents on other arteries was identified, research were undertaken that will lead to the development of algorithms for the detection of incidents on the streets equipped with traffic signals. The initial results of simulation studies (using VISSIM software) are presented in the third part of the paper. Their objective was to initially select parameters for detecting incidents at junctions equipped with traffic signals. Further research will look at a fusion of variables and possible other variables that may develop the algorithms.

[1]  Katsushi Ikeuchi,et al.  Traffic monitoring and accident detection at intersections , 2000, IEEE Trans. Intell. Transp. Syst..

[2]  Jaume Barceló,et al.  A Kalman Filter Approach for Exploiting Bluetooth Traffic Data When Estimating Time-Dependent OD Matrices , 2013, J. Intell. Transp. Syst..

[3]  Stephen G. Ritchie,et al.  A NEW METHODOLOGY FOR INCIDENT DETECTION AND CHARACTERIZATION ON SURFACE STREETS , 1998 .

[4]  A. Ash Incident detection in urban areas controlled by SCOOT , 1997 .

[5]  J A Lindley,et al.  URBAN FREEWAY CONGESTION: QUANTIFICATION OF THE PROBLEM AND EFFECTIVENESS OF POTENTIAL SOLUTIONS , 1987 .

[6]  John Yen,et al.  Fuzzy-logic-based incident detection for signalized diamond interchanges , 1998 .

[7]  Stephen G. Ritchie,et al.  STATISTICAL AND NEURAL CLASSIFIERS TO DETECT TRAFFIC OPERATIONAL PROBLEMS ON URBAN ARTERIALS , 1998 .

[8]  Sergio A. Velastin,et al.  A Review of Computer Vision Techniques for the Analysis of Urban Traffic , 2011, IEEE Transactions on Intelligent Transportation Systems.

[9]  Stephen G. Ritchie,et al.  Vehicle Reidentification using multidetector fusion , 2004, IEEE Transactions on Intelligent Transportation Systems.

[10]  William C. Taylor,et al.  Application of a Dynamic Model for Arterial Street Incident Detection , 1999, J. Intell. Transp. Syst..

[11]  Lee D. Han,et al.  AUTOMATIC DETECTION OF TRAFFIC OPERATIONAL PROBLEMS ON URBAN ARTERIALS , 1989 .

[12]  Huairui Guo,et al.  Travel time estimation using correlation analysis of single loop detector data , 2004 .

[13]  April Armstrong,et al.  Traffic Incident Management Handbook , 2010 .

[14]  Kaan Ozbay,et al.  INCIDENT MANAGEMENT IN INTELLIGENT TRANSPORTATION SYSTEMS , 1999 .

[15]  Y Zhang,et al.  Automated accident detection at intersections. , 2004 .

[16]  Kun Zhang,et al.  TOWARDS TRANSFERABLE INCIDENT DETECTION ALGORITHMS , 2005 .

[17]  Joseph L. Schofer,et al.  Arterial incident detection using fixed detector and probe vehicle data , 1995 .

[18]  Yong-Kul Ki Accident Detection System using Image Processing and MDR , 2007 .

[19]  Mike McDonald,et al.  Intelligent transport systems in Europe : opportunities for future research , 2006 .