A Real-Time Road Sign Detection Using Bilateral Chinese Transform

Abstract

Abstract. We present a real-time approach for circular and polygonal road signs detection 1 in still images, regardless of their pose and orientation. Object detection is done using a pairwise gradient-based symmetry transform able to detect circles and polygons indistinctly. This symmetry transform of gradient orientation, the so-called Bilateral Chinese Transform BCT, decomposes an object into a set of parallel contours with opposite gradients, and models this gradient field symmetry using an accumulation of radial symmetry evidences. On a test database of 89 images 640x480 containing 92 road signs, 79 are correctly detected (86%) with 25 false positives using the BCT approach in about 30 ms/image.

Détection des panneaux de signalisation routière par accumulation bivariée

“…In the BCT approach (Belaroussi et al, 2009b), object detection is done using a pairwise gradient-based symmetry transform able to detect circles and polygons indistinctly. The BCT seeks the symmetry of shape in the gradient orientation : it decomposes an object into a set of parallel contours with opposite gradients, and models this gradient field symmetry using an accumulation of radial symmetry evidences.…”

“…Elle est capable de dé-tecter les axes et centres de symétrie des panneaux circulaires et rectangulaires comme le montre la figure 1. Nous proposons ici une variante de la TC appelée transformation chinoise bilatérale TCB (Belaroussi et al, 2009b) pour la détection de panneaux circulaires et polygonaux (non triangulaires). Contrairement à la TC standard, la TCB permet de détecter des objets sans hypothèse a priori sur leur contraste clair/sombre ou sombre/clair.…”

“…Elle est aussi plus précise que la TSG car elle est spécialisée sur les paires de points ayant des gradients symétriques par rapport à leur milieu. Cette méthode a fait l'objet d'une publication dans les actes de la conférence ISVC 2009 (Belaroussi et al, 2009b).…”

“…To progress towards better algorithms, we focus in this article on the first stage of the process, namely road sign detection. We focus our work on a feature-based approach to build geometrical models of various kind of shapes : triangle on the one hand, square, diamond, octagon and circle on the other hand.We introduce two cumulative bivariate transformations :-the Bilateral Chinese Transform BCT, tailored for the detection of circular and polygonal road signs with four or more sides.-The Vertex and Bisector Transformation VBT, dedicated to the detection of triangular traffic signs.In the BCT approach (Belaroussi et al, 2009b), object detection is done using a pairwise gradient-based symmetry transform able to detect circles and polygons indistinctly. The BCT seeks the symmetry of shape in the gradient orientation : it decomposes an object into a set of parallel contours with opposite gradients, and models this gradient field symmetry using an accumulation of radial symmetry evidences.…”

Road Sign Detection in Images: A Case Study

“…• Pair-Wise Pixels Voting (PWPV) schemes, as the Bilateral Chinese Transform (BCT) for circular and rectangular signs [6] or the Vertex and Bisector Transform (VBT) for triangular signs [5].…”