This paper presents an application of the optical character recognition, the interpretation of traffic signs from digital video images. Individual sign objects are segmented and normalized using image processing and coding approaches. An OCR-module based on probabilistic neural network and fuzzy logic is developed for isolation recognition. The extracted and identified sign objects are automatically converted to CAD form. A rule-based interpretation system is proposed and implemented for understanding traffic signs. An experiment was conducted on 97 highway signs and successful recognition and interpretation results are achieved. Such a system is required to assist drivers and for guidance and control of autonomous vehicles on highways.
Interpretation of traffic signs from digital video images
Die Interpretation von Verkehrszeichen aus digitalen Videobildern
1998
4 Seiten, 3 Bilder, 6 Quellen
Aufsatz (Konferenz)
Englisch
RECOGNITION OF SUPPLEMENTARY SIGNS FOR CORRECT INTERPRETATION OF TRAFFIC SIGNS
British Library Conference Proceedings | 2013
|Traffic Safety Evaluation of Video Advertising Signs
Transportation Research Record | 2005
|Traffic Safety Evaluation of Video Advertising Signs
British Library Conference Proceedings | 2005
|Traffic Safety Evaluation of Video Advertising Signs
Online Contents | 2005
|