01517517

Component

Vehicle classification data is essential to almost all types of transportation engineering and management applications. Vehicular length based vehicle classification methods are widely applied due the available traffic monitoring stations such as inductive loop and radar detector stations. Axle based vehicle classification schemes are usually limited by the capital cost issues of its deployment. In practice, locations using axle based vehicle classification is often restricted to places where significant truck volumes are observed. This research proposed a prototype of video-base vehicle classification system: Rapid Video-based Vehicle Identification System (RVIS) using axle parameters extracted from image processing techniques. By design, the RVIS has video acquisition, vehicle axle parameters extraction, feature-based vehicle classification and the calibration and validation modules. The axle-based classification is based on the number of axles, axle groups and distances between axles extracted. The preliminary results succeeded on detecting and extracting the axle parameters as defined by Federal Highway Administration (FHWA) class 1 to 13 vehicles. The RVIS is proved to be a powerful tool for extracting vehicle classification from ground truth data. It provides optional to current vehicle classification data is available.

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

01503729

14-3239

English

18p

2014

Transportation Research Board 93rd Annual Meeting

Digital/other

Figures; References

Automatic vehicle detection and identification systems; Axles; Computer vision; Detection and identification systems; Image processing

Data and Information Technology; Highways; I72: Traffic and Transport Planning

Transportation Research Board Annual Meeting 2014 Paper #14-3239

TRIS, TRB, ATRI

Jan 27 2014 3:07PM