Comparison and Analysis Tool for Automatic Incident Detection

A new test bed for automatic incident detection (AID) systems uses real-time traffic video and data feeds from the Ontario, Canada, Ministry of Transportation COMPASS advanced traffic management system. This new test bed, called the AID comparison and analysis tool (AID CAAT), consists largely of a data warehouse storing a significant amount of traffic video, the corresponding traffic data, and an accurate log of incident start and end times. Also presented is a proof-of-concept field evaluation whereby the AID CAAT is used to calibrate and then analyze the performance of three AID algorithms: California Algorithm 8, the McMaster algorithm, and the genetic adaptive incident detection algorithm. In the calibration and testing process, nuisance rate and false normal rate are introduced as two new performance measures to supplement the three traditional measures (detection rate, false alarm rate, and mean time to detection). Further, the pilot evaluation shows the considerable advantages of AID CAAT in its ability to investigate the impact of freeway geometry, traffic flow rate, and traffic sensor spacing on the performance of the three AID algorithms. This work represents the first stage in a series of further tests to develop a set of AID algorithm deployment guidelines.

[1]  Yong Shi,et al.  ON-LINE TESTING OF THE MCMASTER INCIDENT DETECTION ALGORITHM UNDER RECURRENT CONGESTION , 1993 .

[2]  Xiao Liu,et al.  ARTIFICIAL NEURAL NETWORKS FOR FREEWAY INCIDENT DETECTION , 1995 .

[3]  Ruey Long Cheu,et al.  Neural Network Models For Automated Detection Of Non-recurring Congestion , 1993 .

[4]  Fred L. Hall,et al.  DISTINGUISHING BETWEEN INCIDENT CONGESTION AND RECURRENT CONGESTION: A PROPOSED LOGIC , 1989 .

[5]  Panos G Michalopoulos,et al.  COMPARATIVE PERFORMANCE EVALUATION OF INCIDENT DETECTION ALGORITHMS , 1992 .

[6]  S C Tignor,et al.  IMPROVED FREEWAY INCIDENT DETECTION ALGORITHMS , 1977 .

[7]  J A Martin,et al.  AUTOMATIC INCIDENT DETECTION - TRRL ALGORITHMS HIOCC AND PATREG , 1979 .

[8]  Samir A. Ahmed,et al.  Discrete dynamic models for freeway incident detection systems , 1982 .

[9]  R D Jacobson,et al.  AUTOMATIC INCIDENT DETECTION THROUGH VIDEO IMAGE PROCESSING , 1993 .

[10]  Baher Abdulhai,et al.  Enhancing the universality and transferability of freeway incident detection using a Bayesian-based neural network , 1999 .

[11]  Samuel C Tignor,et al.  FREEWAY INCIDENT-DETECTION ALGORITHMS BASED ON DECISION TREES WITH STATES , 1978 .

[12]  Bhagwant Persaud,et al.  CONGESTION IDENTIFICATION ASPECTS OF THE MCMASTER INCIDENT DETECTION ALGORITHM , 1990 .

[13]  J-M Morin,et al.  Video Image Processing Application: Automatic Incident Detection on Freeways , 1993 .

[14]  Carroll J Messer,et al.  Incident detection on urban freeways , 1974 .

[15]  Stephen L M Hockaday,et al.  EVALUATION OF VIDEO IMAGE PROCESSING SYSTEMS FOR TRAFFIC DETECTION (ABRIDGMENT) , 1992 .