Vision-based target detection in road environments

This paper describes a target detection system on road environments based on Support Vector Machine (SVM) and monocular vision. The final goal is to provide car-to-car time gap. The challenge is to use a single camera as input, in order to achieve a low cost final system that meets the requirements needed to undertake serial production in automotive industry. The basic feature of the detected objects are first located in the image using vision and then combined with a SVM-based classifier. An intelligent learning approach is proposed in order to better deal with objects variability, illumination conditions, partial occlusions and rotations. A large database containing thousands of object examples extracted from real road images has been created for learning purposes. The classifier is trained using SVM in order to be able to classify cars and trucks. In addition, the vehicle detection system described in this paper provides early detection of passing cars and assigns lane to target vehicles. In the paper, we present and discuss the results achieved up to date in real traffic conditions.