Detection Technology Testbed on I 475: Technology Feasibility Study

US Transportation Collection2020PDFTech ReportGuin, AngshumanHunter, MichaelKim, Han GyolChoudhary, NishuGeorgia Tech Research CorporationGeorgia. Dept. of Transportation. Office of Performance-Based Management and ResearchUnited States. Department of Transportation. Federal Highway AdministrationGeorgia. Dept. of TransportationGeorgiaUnited StatesAutomatic incident detectionCrowdsourcingData collectionMachine learningNoise (Communications)SmartphonesTraffic delaysThe Infra-Red Traffic Logger (TIRTL)Incident Delay EstimationFHWA-GA-21-1720PI#0015715Final; August 2017 \u2013 October 2020This project evaluates the feasibility of use and potential benefits of a video-based automatic incident detection (AID) technology relative to existing detection via the Georgia 511 (NaviGAtor) incident reports and transportation management center operators\u2019 manual observations. This study proposes a clustering machine learning framework for developing consolidation strategies and filters that will eliminate most noncritical alarms and associate confidence values with the alerts, thereby allowing for a focus on higher confidence alerts during busy periods. The project also investigates the potential of crowdsourced smartphone app-based incident detection and notification, in reducing the time to detection. Finally, the project reviews several of the conventional methods of incident delay estimation, evaluates their accuracy in the presence of noisy data, and develops a new regression-based method to quantify impact of traffic incidents in terms of vehicle delay.120