Alexandre Bargeton

TL;DR: This paper presents robust visual speed limit signs detection and recognition systems for American and European signs, both variants of the same modular traffic signs recognition architecture, with a sign detection step based only on shape-detection, which makes them insensitive to color variability and quite robust to illumination variations.

TL;DR: An improved European speed-limit sign recognition system based on an original ldquoglobal number segmentationrdquo (inside detected circles) before digit segmentation and recognition, which is intrinsically insensitive to colour variability and quite robust to illumination variations.

TL;DR: A new modular traffic signs recognition system, successfully applied to both American and European speed limit signs, based only on shape-detection, which enables it to work on grayscale images, contrary to most European competitors, which eases robustness to illumination conditions.

TL;DR: In this paper, a method of circle detection in images for round traffic sign identification was proposed, including two stages: a first stage of detection (101) to detect centers of a group of candidates circles in an image by calculating the edges on said image, applying a Hough transform on said edges to identify the centers of the candidates circles, and a second stage of validation (102) where a circle is selected from said group of candidate circles, characterized in that in said second stage, a dispersion gradient criterion measuring the luminance gradient dispersion is calculated for each candidate circle

TL;DR: To the team's knowledge, this is the first team presenting results on detection and recognition of supplementary signs below speed signs, which is a crucial feature for a reliable Speed Limit Support.