Car type recognition with Deep Neural Networks

In this paper we study automatic recognition of cars of four types: Bus, Truck, Van and Small car. For this problem we consider two data driven frameworks: a deep neural network and a support vector machine using SIFT features. The accuracy of the methods is validated with a database of over 6500 images, and the resulting prediction accuracy is over 97 %. This clearly exceeds the accuracies of earlier studies that use manually engineered feature extraction pipelines.

I. Introduction

Traffic counting is a central tool for traffic planning and analysis for intelligent traffic. In many cases the desire is to increase the level of details by additional categorization of vehicle types. This allows a more fine-grained analysis and more accurate profiling of users of the transportation infrastructure, which is necessary for assessing the effects of possible modifications in the traffic system.