Robust traffic signs detection by means of vision and V2I communications

This paper presents a complete traffic sign recognition system, including the steps of detection, recognition and tracking. The Hough transform is used as detection method from the information extracted in contour images, while the proposed recognition system is based on Support Vector Machines (SVM), and is able to recognize up to one hundred of the main road signs. Besides a novel solution to the problem of discarding detected signs that do not pertain to the host road is proposed, for that purpose vehicle-to-infrastructure (V2I) communication and stereo information is used. This paper presents plenty of tests in real driving conditions, both day and night, in which a high success rate and low number of false negatives and true positives were obtained, and an average runtime of 35 ms, allowing real-time performance.