01555330

Component

It has been previously proved that GPS data can be used to distinguish passenger cars from large trucks. In this study, a machine learning approach is proposed to use GPS data to identify multiple vehicle classes: including passenger cars, single unit trucks, and multi-trailer trucks. The method is acceleration and deceleration-based since it considers the variations of accelerations and decelerations as the most effective features to classify vehicles. The overall classification result for the three vehicle classes is about 75%. The major challenge is to distinguish single unit trucks from multi-trailer trucks. It is found that the classification results are not very sensitive to the sampling frequency of GPS data, as long as the data are collected frequent enough to capture major acceleration and deceleration processes of the vehicles.

This paper was sponsored by TRB committee ABJ35 Highway Traffic Monitoring.

01550057

15-5291

English

13p

2015

Transportation Research Board 94th Annual Meeting

Digital/other

Figures; References; Tables

Acceleration (Mechanics); Automatic vehicle classification; Deceleration; Global Positioning System; Machine learning; Passenger vehicles; Statistical sampling; Trucks

Support vector machines

Data and Information Technology; Freight Transportation; I72: Traffic and Transport Planning

Transportation Research Board Annual Meeting 2015 Paper #15-5291

TRIS, TRB, ATRI

Dec 30 2014 1:46PM