A system for traffic sign detection, tracking, and recognition using color, shape, and motion information

Abstract

This paper describes a computer vision based system for real-time robust traffic sign detection, tracking, and recognition. Such a framework is of major interest for driver assistance in an intelligent automotive cockpit environment. The proposed approach consists of two components. First, signs are detected using a set of Haar wavelet features obtained from Ada-Boost training. Compared to previously published approaches, our solution offers a generic, joint modeling of color and shape information without the need of tuning free parameters. Once detected, objects are efficiently tracked within a temporal information propagation framework. Second, classification is performed using Bayesian generative modeling. Making use of the tracking information, hypotheses are fused over multiple frames. Experiments show high detection and recognition accuracy and a frame rate of approximately 10 frames per second on a standard PC.

Traffic Sign Recognition Using Discriminative Local Features

“…1, obtained real-time classification error rate does not exceed 7%, making our method comparable to the recently published ones [9,10]. However, it should be noted that our template database contains significantly more signs than in any of the previous studies.…”

Standardization of Road Danger Signs in the European Union

“…The method used to compare the graphic characteristics of the signs is inspired by the real perception of images, which is a multi-stage process taking into account several aspects, such as colour, form, border, background, etc. [19,20,21,22,23].…”

Automatic Collection of Fuel Prices from a Network of Mobile Cameras

“…4. Recognition and detection of road signs from digital images is a mature area of research [10][11][12]. However, a road sign differs significantly from a fuel price board as evidenced by comparing Fig.3(a) and Fig.3(b).…”

“…However, our work differs from existing work in vehicular WSNs and Participatory Sensing in that we focus on the challenges in automatically collecting consumer pricing data. Detection and recognition of objects from digital images: Automatic detection of road traffic signs is a mature area of research [12,[23][24][25]. There have also been several recent successful attempts at detecting text from a diverse set of digital sources such as video, newspapers, advertisements and photographs [26].…”