In this paper a system is presented for real time recognition of the traffic signs. Sign detection is done by a method of adaptively growing window. Classification is based on matching of the modulo-shifted phase histograms. These are built from the stick component of the structural tensor rather than from an edge detector. To cope with inherent rotations of signs a novel measure is proposed for matching of the modulo-shifted histograms that also boosts responses of highly probable values. The method is tolerant of small translations, rotations and symmetrical changes of scale. It works also well under different lighting conditions and tolerates noise and small occlusions.
A real-time vision system for traffic signs recognition invariant to translation, rotation and scale
Ein Echtzeit-Vision-System für die Verkehrszeichenerkennung unabhängig von Translation, Rotation und Skalierung
2008
12 Seiten, 7 Bilder, 1 Tabelle, 17 Quellen
Conference paper
English
An Efficient Real-Time Speed Limit Signs Recognition Based on Rotation Invariant Feature
British Library Conference Proceedings | 2011
|Real-Time Recognition of Blue Traffic Signs Designating Directions
Springer Verlag | 2010
|Real-time detection and recognition of road traffic signs
Online Contents | 2012
|Lane departure warning and real-time recognition of traffic signs
Tema Archive | 2009
|