INCIDENT DETECTION ALGORITHM EVALUATION

This research examines a range of incident detection technologies to determine a recommended combination of approaches for use in the Utah Department of Transportation's (UDOT) Advanced Traffic Management System (ATMS). The technologies that were examined are computer-based Automatic Incident Detection (AID), Video Image Processing (VIP), and detection by cellular telephone call-ins. This project was originally scoped to include a rigorous testing of several computer-based algorithms. The projects Technical Advisory Committee, however, redirected this work to look more closely at the impact of cellular telephones in incident detection. Cellular telephone technology will continue to impact the power and speed with which incidents are detected. The Federal Communications Commission has mandated that all cellular telephone service providers give the name, number, and location of a cellular telephone caller to the Public Safety Answering Point by October 2001, for when that caller dials 911. This information will be helpful to identify locations of traffic incidents. The number of cellular telephones in use is also increasing. Incident detection by cellular telephones will continue to be the primary means of incident detection. Because the ATMS already possesses the All-Purpose Incident Detection (APID) and Double Exponential Smoothing (DES) algorithms as part of the Navigator software, they should be enabled and calibrated as a secondary form of incident detection. Other forms of incident detection can be evaluated from the ATMS. The neural network method and the video image processing method likely could be modified to work with existing ATMS equipment.

• Record URL:
  https://www.ugpti.org/resources/reports/details.php?id=367
• 
• Record URL:
  https://rosap.ntl.bts.gov/view/dot/64713
• Corporate Authors:

  Mountain-Plains Consortium

  North Dakota State University
  Fargo, ND  United States  58108
• Authors:
  • Martin, P T
  • Perrin, J
  • Hansen, B
  • Kump, R
  • Moore, David
• Publication Date: 2001-3

Language

• English

Media Info

• Features: Figures; References; Tables;
• Pagination: 54 p.

Subject/Index Terms

• TRT Terms: Advanced traffic management systems; Algorithms; Cellular telephones; Evaluation; Image processing; Incident detection; Location; Neural networks; Video imaging detectors
• Identifier Terms: Public Safety Answering Point (Communications); U.S. Federal Communications Commission
• Subject Areas: Highways; Operations and Traffic Management; I73: Traffic Control;

Filing Info

• Accession Number: 00811889
• Record Type: Publication
• Report/Paper Numbers: MPC Report No. 01-122
• Files: NTL, TRIS
• Created Date: Jun 26 2001 12:00AM