Automatic road marking recognition is a key problem within the domain of automotive vision that lends support to both autonomous urban driving and augmented driver assistance such as situationally aware navigation systems. Here a methodology for the automatic recognition of on road markings is presented that operates, under varying test conditions, with approximately 81-85 % success based on the data sets available for classifier training. This approach has been shown to work within a viable real-time constraint (11-15 fps) both in daylight and at night. Prior work in this area is very limited and no prior work on the recognition of on-road textual words has been carried out. Extensive results are shown under varying conditions, vehicle speeds and environmental conditions. The approach is based on the construction of an IPM transformed image of the roadway derived from an initial calibration of automatic vanishing point detection. This top down roadway view forms the input to robust feature extraction supported by a unique illumination resistant multithreshold. A trained single layer neural network classifier is then used for individual glyph classification prior to glyph word/pattern construction via a simple post-processing matching methodology.
Automatic real-time road marking recognition using a feature driven approach
Ein automatisches Echtzeit-Straßenmarkierung-Erkennung mittels eines Eigenschafts-getrriebenen Verfahrens
Machine Vision and Applications ; 23 , 1 ; 123-133
2012
11 Seiten, 11 Bilder, 2 Tabellen, 32 Quellen
Aufsatz (Zeitschrift)
Englisch
Fahrerassistenzsystem , Computer-Vision , Echtzeitanalyse , Echtzeitbetrieb , Echtzeit , erweiterte virtuelle Realität , Fahrzeugnavigationssystem , Straßenbegrenzung , Klassifizierung , digitale Bilderkennung , digitale Bildverarbeitung , Kalibrieren (Abgleichen) , Merkmalextraktionsverfahren , Neurocomputing , mobiler Roboter
Automatic real-time road marking recognition using a feature driven approach
British Library Online Contents | 2012
|ROAD MARKING RECOGNITION DEVICE AND ROAD MARKING RECOGNITION PROGRAM
Europäisches Patentamt | 2015
|A model-driven approach for real-time road recognition
British Library Online Contents | 2001
|A model-driven approach for real-time road recognition
Tema Archiv | 2001
|