Authors:
Rahul Sengupta
;
Tania Banerjee
;
Ke Chen
;
Yashaswi Karnati
;
Sanjay Ranka
and
Anand Rangarajan
Affiliation:
Department of Computer and Information Science & Engineering, University of Florida, Gainesville, FL, U.S.A.
Keyword(s):
Simulation, Modeling, Data Mining, Data Analysis, Modeling, Simulation, Control of Pedestrians, Cyclists.
Abstract:
Most traffic authorities across the US usually collect high-resolution (10 Hz) loop detector and signal state data and video data. The multiple modalities of data that are readily available can be utilized for better traffic operations management and improving safety. In this work, we show that the fusion of widely deployed loop detector data with trajectory information collected through video cameras can augment intersection safety and operational efficiency analysis. The additional information that can be extracted from the object’s (vehicle and pedestrian) trajectory derived from video data when fused with signal state data leads to several interesting safety analyses. Data analysis shows a significant variance in turn-movement counts, pedestrian behaviors, vehicle composition, etc., temporally (hour-of-day, day-of-week, etc.) and spatially (approach-wise). We present a simulation-based approach for customizing signal timing plans based on the traffic behavior at the intersections
at various times. When used to drive simulations in demand generation, we show that the fused data calibrating the simulation parameters can lead to potential improvements in existing signal timing plans that match reality and can greatly help improve intersection safety and operational efficiency by providing planners with data-driven insights.
(More)