Automatic vehicle trajectory data reconstruction at scale
12/2022
2022
Vehicle trajectory data has received increasing research attention over the past decades. With the technological sensing improvements such as high-resolution video cameras, in-vehicle radars and lidars, abundant individual and contextual traffic data is now available. However, though the data quantity is massive, it is by itself of limited utility for traffic research because of noise and systematic sensing errors, thus necessitates proper processing to ensure data quality. We draw particular attention to extracting high-resolution vehicle trajectory data from video cameras as traffic monitoring cameras are becoming increasingly ubiquitous. We explore methods for automatic trajectory data reconciliation, given "raw" vehicle detection and tracking information from automatic video processing algorithms. We propose a pipeline including a) an online data association algorithm to match fragments that are associated to the same object (vehicle), which is formulated as a min-cost network flow problem of a graph, and b) a trajectory reconciliation method formulated as a quadratic program to enhance raw detection data. The pipeline leverages vehicle dynamics and physical constraints to associate tracked objects when they become fragmented, remove measurement noise on trajectories and impute missing data due to fragmentations. The accuracy is benchmarked on a sample of manually-labeled data, which shows that the reconciled trajectories improve the accuracy on all the tested input data for a wide range of measures. An online version of the reconciliation pipeline is implemented and will be applied in a continuous video processing system running on a camera network covering a 4-mile stretch of Interstate-24 near Nashville, Tennessee.
I-24 Open Road Testbed
04/2020
Charlotte, North Carolina2021

We describe the I-24 MOTION open road testbed led by the Tennessee Department of Transportation on Interstate 24 near Nashville, TN. The purpose of the testbed is to provide an open road experimental facility for testing traffic management and automated vehicle technologies in real freeway traffic. The testbed consists of pole-mounted 4K resolution video cameras providing uninterrupted coverage of the roadway. Video data is processed in real time into vehicle trajectories for all vehicles passing through the testbed. The current length of the testbed is approximately 1600 feet and upon its completion will stretch 6 miles. Testbed specifications, hardware, and design decisions are discussed, as well as the future of the testbed construction.

Interstate-24 MOTION: Closing the Loop on Smart Mobility
03/2020
Sydney, Australia2020

We introduce the I-24 Mobility Technology Interstate Observation Network (MOTION), a transportation cyberphysical systems testbed under development in Tennessee. It consists of a six-mile freeway segment instrumented with 400 4K resolution cameras, processed by a real-time compute system to enable continuous performance monitoring of freeway traffic. The testbed is being developed to support next generation connected and autonomous vehicle technologies and advanced traffic management. When complete, the testbed will be the longest continuously observed freeway segment in the world. This article introduces the testbed, discusses the core design choices, and outlines the preliminary work conducted to support the design.