Vehicle type classification from visual-based dimension estimation

Author

Lai, Andrew H S ; Fung, George S K ; Yung, Nelson H. C.

Author_Institution

Lab. for Intelligent Transp. Syst. Res., Univ. of Hong Kong, China

fYear

2001

fDate

2001

Firstpage

201

Lastpage

206

Abstract

This paper presents a visual-based dimension estimation method for vehicle type classification. Our method extracts moving vehicles from traffic image sequences and fits them with a simple deformable vehicle model. Using a set of coordination mapping functions derived from a calibrated camera model and relying on a shadow removal method, vehicle´s width, length and height are estimated. Our experimental tests show that the modeling method is effective and the estimation accuracy is sufficient for general vehicle type classification

Keywords

image classification; image sequences; object recognition; road traffic; traffic engineering computing; calibrated camera model; coordination mapping functions; deformable vehicle model; moving vehicle extraction; shadow removal method; traffic image sequences; vehicle height estimation; vehicle length estimation; vehicle type classification; vehicle width estimation; visual-based dimension estimation; Axles; Calibration; Cameras; Deformable models; Image sequences; Intelligent transportation systems; Surveillance; Testing; Traffic control; Vehicles;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Transportation Systems, 2001. Proceedings. 2001 IEEE

Conference_Location

Oakland, CA

Print_ISBN

0-7803-7194-1

Type

conf

DOI

10.1109/ITSC.2001.948656

Filename

948656