Lin, Wei (IUPUI), QIU, MEI (University), Chien, Stanley (Indiana University-Purdue University Indianapolis), Christopher, Lauren (Purdue University), Chen, Yaobin (Purdue School of Engineering and Technology, IUPUI)

A Method for Analyzing Highway Vehicle Weaving Problem

Scheduled for presentation during the Regular Session "Road Traffic Control II" (ThAT11), Thursday, September 26, 2024, 11:30−11:50, Salon 19/20

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on December 26, 2024

Abstract

Highway vehicle weaving analysis aims to determine the percentage and number of vehicles changing lanes from their origin to destination on a highway segment. Vehicle weaving often slows down traffic, causes jams, and increases safety concerns. Quantitative analysis of lane-based highway weaving patterns are crucial for traffic management and road improvement. However, there is currently no cost-effective tool to obtain lane-based vehicle weaving data. This paper describes a method combining machine learning with convenient user verification to achieve accurate weaving analysis using field camera videos. The effectiveness of this approach has been demonstrated in experimental results, and a software tool has been deployed to the Indiana Department of Transportation.