Automatic Vehicle Identification Technology-Based Freeway Incident Detection

• Published in: Transportation research record Vol. 1727; no. 1; pp. 142 - 153
• Main Authors: Hellinga, Bruce, Knapp, Geoff
• Format: Journal Article Conference Proceeding
• Language: English
• Published: Los Angeles, CA SAGE Publications 2000; National Research Council
• Subjects: Applied sciences; Exact sciences and technology; Ground, air and sea transportation, marine construction; Road transportation and traffic; Transportation planning, management and economics; Performance evaluation; Speed; Travel time; Mishap; International conference; Performance characteristic; Confidence limit; Algorithm; False alarm rate; Automated processing; Vehicle identification; Freeway; Numerical simulation; Road traffic; Detection; Comparative study
• ISSN: 0361-1981; 2169-4052
• DOI: 10.3141/1727-18

The recent emergence of automatic vehicle identification technology (AVI) for use in electronic toll collection has provided an opportunity to develop automatic incident detection (AID) methods that rely on individual vehicle travel time data instead of loop detector data. The performances of three AVI-based AID algorithms are examined. Travel time data for testing of the algorithms were obtained by simulating a 12-km section of the collector facility of Highway 401 in Toronto, Ontario, Canada. The performances of the three AVI-based AID algorithms are compared with the performance of a leading loop detector–based algorithm, which was independently tested with similar simulated data. The AID performance results indicate that AVI-based AID algorithms can provide incident detection performance similar to that of existing loop detector-based AID methods.