Image-based localization of vehicle parts guided by visual attention

The automated servicing of vehicles is becoming more and more a reality in today´s world. While certain operations, such as car washing, require only a rough model of the surface of a vehicle, other operations, such as changing of a wheel or filling the gas tank, require correct localization of the different parts of the vehicle on which operations are to be performed. The paper describes an image-based approach to roughly localize vehicle parts over the surface of a vehicle with a bounding box approach based on a model of human visual attention. The proposed method is automatically adapted for different views of a vehicle and obtains average localization rates for different vehicle parts of over 95% for a dataset of 120 vehicles belonging to three categories, namely sedan, SUV and wagon.