Multi-class Vehicle Type Recognition System

XAVIER CLADY; PABLO NEGRI; MAURICE MILGRAM; RAPHAEL POULENARD

Neural Networks in Pattern Recognition

Lecture Notes in Computer Science 5064, Springer Berlin / Heidelberg

Lugar: Berlin; Año: 2008; p. 228 - 239

This paper presents a framework for multiclass vehicle type (Make and Model) identi cation based on oriented contour points. A method to construct a model from several frontal vehicle images is presented. Employing this model, three voting algorithms and a distance error allows to measure the similarity between an input instance and the data bases classes. These scores could be combined to design a discriminant function. We present too a second classi cation stage that employ scores like vectors. A nearest-neighbor algorithm is used to determine the vehicle type. This method have been tested on a realistic data set (830 images containing 50 di erent vehicle classes) obtaining similar results for equivalent recognition frameworks with di erent features selections. The system also shows to be robust to partial occlusions.