|
Title: Monitoring Signalized Intersection Performance with Bluetooth and Wifi Duration Data
Accession Number: 01622569
Record Type: Component
Abstract: Estimating intersection performance or delay has traditionally relied on extensive offline mathematical models operating on a number of assumptions. The advent of new technologies such as Bluetooth and WiFi signal sensors, may provide practitioners the ability to automatically estimate intersection delay in real-time. This study attempts to validate Bluetooth / WiFi duration times of drivers from one approach at two intersections in downtown Montreal, Canada, with ground truth GPS and video data. All data were collected over four days in May and June 2016. The GPS delay ground truth data was prepared by first isolating GPS points around a certain distance of the study intersections and then determining the time spent for each trip. The video data was collected from one camera placed at a study intersection and another placed at its adjacent upstream intersection. The travel times between the two camera locations were determined by matching vehicles based on colour and shape. Average delay times from the video and sensor data were then computed for 15, 30 and 60 minute intervals. First-order regression models from the GPS data reveal fairly high fit scores of 68–96 % indicating that the sensor duration times do match actual driver delay. Similarly, regression models between the video and duration data resulted in fairly high fit scores of 70 % at the 15 minute level indicating that the sensors can competently monitor the temporal variation of delay.
Supplemental Notes: This paper was sponsored by TRB committee ABJ50 Standing Committee on Information Systems and Technology.
Monograph Title: Monograph Accession #: 01618707
Report/Paper Numbers: 17-02160
Language: English
Corporate Authors: Transportation Research Board 500 Fifth Street, NW Authors: Romancyshyn, TarasLesani, AsadMiranda-Moreno, LuisPagination: 17p
Publication Date: 2017
Conference:
Transportation Research Board 96th Annual Meeting
Location:
Washington DC, United States Media Type: Digital/other
Features: Figures; References; Tables
TRT Terms: Geographic Terms: Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management
Source Data: Transportation Research Board Annual Meeting 2017 Paper #17-02160
Files: TRIS, TRB, ATRI
Created Date: Dec 8 2016 10:47AM
|