DEVELOPMENT AND TESTING OF INCIDENT DETECTION ALGORITHMS, VOLUME 2: RESEARCH METHODOLOGY AND DETAILED RESULTS

The development and testing of incident detection algorithms was based on Los Angeles and Minneapolis freeway surveillance data. Algorithms considered were based on times series and pattern recognition techniques. Attention was given to the effects of geometrics, sensor configuration and weather, and methods were developed for detecting malfunctioning sensors and for identifying the lane of an incident. The second volume describes the methodology used for evaluating and calibrating incident detection algorithms, the specific time series techniques examined (exponential smoothing and traffic correlation) and the decision tree structure for algorithms. Detailed results and discussions pertaining to all aspects of this study are presented here. /FHWA/

Record URL:
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/isbn/31C3502
Supplemental Notes:
- This volume is the second of four. The other are: Vol. 1, RD-76-10, Summary of Results; Vol. 3, RD-76-21, User Guidelines; Vol. 4, RD-76-22, Program Documentation for Evaluation, Calbration and Implementation.
Corporate Authors:
Technology Service Corporation

2811 Wilshire Boulevard
Santa Monica, CA United States 90403
Authors:
- Payne, H J
- Helfenbein, E D
- Knobel, H C
Publication Date: 1976-4

Media Info

Pagination: 316 p.

Subject/Index Terms

TRT Terms: Algorithms; Highway design; Pattern recognition systems; Research; Time series; Traffic incidents; Traffic lanes; Vehicle detectors; Weather
Uncontrolled Terms: Incidents
Subject Areas: Highways; Operations and Traffic Management; Research;

Filing Info

Accession Number: 00144116
Record Type: Publication
Source Agency: Federal Highway Administration
ISBN: 31C3-502
Report/Paper Numbers: FHWA-RD-76- 20 Final Rpt., FCP 31C3-502
Contract Numbers: DOT-FH-11-8278
Files: NTL, TRIS, USDOT
Created Date: Dec 15 1976 12:00AM