01659937

Component

https://doi.org/10.1177/0361198118775840

This paper presents a vibration-based vehicle classification system using distributed optical vibration sensing (DOVS) technology and describes a comprehensive classification method including signal processing and feature extraction. With low maintenance costs, this system can collect vehicle classification data in a larger scale. At first, it utilizes an embedded sensing fiber as a distributed sensor to collect traffic-induced vibration signals, and then extracts several features from the raw signals to estimate axle configurations and identify vehicle categories. At the same time, an empirical mode decomposition (EMD)-based method is applied to reconstruct signals for features extraction, and then several extraction algorithms are proposed to obtain the axle configuration, moving speed, and frequency-domain feature of each vehicle. When all features are extracted, a multi-step classifier is designed to categorize vehicles into different classes. In addition, to evaluate the classification performance of this system, a prototype system was installed on a relief road in Shanghai, China using precast concrete pavement technology. With an overall accuracy of 89%, the test results show a good performance of this classification system.

18-00201

English

pp 12-23

2018-12

Transportation Research Record: Journal of the Transportation Research Board

Digital/other

Figures (8) ; Photos; References (16) ; Tables (3)

Automatic vehicle classification; Axles; Distributed processing; Fourier transforms; Frequency domain analysis; Optical detectors; Precast concrete pavements; Prototype tests; Sensors; Signal processing; Traffic surveillance; Vibration

Shanghai (China)

Data and Information Technology; Highways; Operations and Traffic Management; Pavements; Vehicles and Equipment

TRIS, TRB, ATRI

Jan 8 2018 10:04AM

• Annual Average Nonmotorized Traffic Estimates from Manual Counts: Quantifying Error
• Application of Trajectory Data for Investigating Vehicle Behavior in Mixed Traffic Environment
• Automated Validation and Interpolation of Long-Duration Bicycle Counting Data
• Challenges in Monitoring Regional Trail Traffic
• Comparison of Pedestrian Count Expansion Methods: Land Use Groups versus Empirical Clusters
• Coupled Approximation of U.S. Driving Speed and Volume Statistics using Spatial Conflation and Temporal Disaggregation
• Development of Statewide Annual Average Daily Traffic Estimation Model from Short-Term Counts: A Comparative Study for South Carolina
• Estimating Annual Average Daily Bicycle Traffic without Permanent Counter Stations
• Evaluating the Reliability, Coverage, and Added Value of Crowdsourced Traffic Incident Reports from Waze
• How Accurately Can We Measure from Video? Practical Considerations and Enhancements of the Camera Calibration Procedure
• Incorporating the Effect of Special Events into Continuous Count Site Selection for Pedestrian Traffic
• Method for Imputing Missing Data using Online Calibration for Urban Freeway Control
• Methods for Estimating Axle Factors and Axle Classes from Vehicle Length Data