Lane Detection System for Intelligent Vehicles using Lateral Fisheye Cameras

The need for safety on roads has made the development of autonomous driving one of the most important topics for Computer Vision research. This thesis focuses on the lane detection problem using images obtained with lateral fisheye cameras, firstly by studying the state-of-the-art and the spherical model, then by developing two methods to solve this task. While the first is based on traditional Computer Vision, the second makes use of a Convolutional Neural Network. Results are then compared.