Automatic Vehicle Trajectory Data Reconstruction at Scale

作     者：Wang, Yanbing Gloudemans, Derek Ji, Junyi Teoh, Zi Nean Liu, Lisa Zachár, Gergely Barbour, William Work, Daniel 

作者机构：Department of Civil and Environmental Engineering Vanderbilt University United States Institute for Software Integrated Systems Vanderbilt University United States Department of Computer Science Vanderbilt University United States Department of Electrical Engineering Vanderbilt University United States 

出 版 物：《SSRN》 

年 卷 期：2023年

核心收录：

主　　题：Pipelines 

摘      要：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 set of microsimulation datasets as well as two samples 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. A real-time 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. © 2023, The Authors. All rights reserved.