Vehicle identification using distance-based appearance model

Nowadays, electronic toll collection (ETC) is used extensively in many countries and places, but many drivers evade detection by covering, altering or otherwise obscuring their license plates. In order to detect vehicles attempting to evade paying tolls, this study aims to identify vehicles without requiring the license plate information. Unlike traditional vehicle license plate recognition, in this study vehicles are matched according to the vehicles´ appearance information. The proposed system builds a complete vehicle model using the training database. In the experiments, we demonstrate the robustness of the proposed system for the highway ETC application.