Computer Vision System for Automatic Vehicle Classification

Abstract

In the present paper, a computer vision system composed of five models is proposed for vehicle classification. The five models are: (1) The perspective projection model; (2) the length measurement model; (3) the width and height estimation model; (4) the profile character extraction model; and (5) the tree‐type classification model. As a significant feature, the third model provides an effective way to estimate width and height of vehicles from video images. This capability is not available in loop detector systems at present. The fourth model provides an approach to obtain two important profile characters of vehicle namely: (1) The front shape of a vehicle: flat front of projecting front; and (2) the number of units of which a vehicle is composed. With these characters, not only can buses be differentiated from trucks, but also vans can be separated from cars. Therefore, common drawbacks of present vehicle‐classification systems are remedied. Experimental results and suggestions for the future improvements are also discussed.