Citation

Parkany E, Bernstein D. Transp. Res. Rec. 1995; 1494: 67-74.

Copyright

(Copyright © 1995, Transportation Research Board, National Research Council, National Academy of Sciences USA, Publisher SAGE Publishing)

DOI

unavailable

PMID

unavailable

Abstract

Incident detection methods for the automatic recognition of accidents and other freeway events requiring emergency responses have existed for over twenty years. Most of the developed and implemented algorithms rely on inductive loop data. Inductive loops are the most commonly used traffic sensor and collect data such as volume and occupancy at a point. However, the implemented algorithms using inductive loop data work with mixed success. Recently, there has been renewed interest in incident detection algorithms partly because of new sensors for obtaining traffic information. One of these new sensors is vehicle-to-roadside communications (VRC), which consists of electronic "tags" on the vehicles and readers along the roadway. These obtain counts, headways, travel times, lane switches, and other information about vehicles between subsequent readers. This paper explores the use of VRC data for incident detection. After a discussion of the use of VRC as a surveillance tool for incident detection, a few example pattern-based algorithms are described. Preliminary results of these algorithms suggest that VRC is a viable sensor to use for incident detection. The final section discusses further directions for this type of research.

Record URL:
http://onlinepubs.trb.org/Onlinepubs/trr/1995/1494/1494-008.pdf

Language: en

Keywords

Highway accidents; Traffic signals; Algorithms; Sensors; Highway engineering; Highway traffic control; Information technology; Highway systems