This article discusses a pedestrian detector for an experimental vehicle, based on visual information from a single far infrared camera. The system considers three consecutive processes for each image. Once the candidates' heads have been extracted, regions of interest are resized based on the distance to the camera and then filtered by its vertical edges symmetry. Once the bounding boxes of possible pedestrians are picked a spatial correlation with some template models takes place. Finally, detected pedestrians are tracked, contrasting their position on successive frames. The results are satisfactory, classifying correctly almost 96 % of pedestrians closer than 45 m to the vehicle.
Pedestrian detection and tracking based on far infrared visual information
Fußgängererkennung und -verfolgung basierend auf visueller Information im fernen Infrarot
2008
12 Seiten, 7 Bilder, 1 Tabelle, 13 Quellen
Aufsatz (Konferenz)
Englisch
Pedestrian Detection and Tracking in Far Infrared Images
British Library Conference Proceedings | 2005
|Pedestrian Detection by Neuromorphic Visual Information Processing
Springer Verlag | 2012
|Pedestrian Detection by Neuromorphic Visual Information Processing
Tema Archiv | 2012
|Pedestrian detection by neuromorphic visual information processing
Kraftfahrwesen | 2012
|Pedestrian tracking using thermal infrared imaging
SPIE | 2006
|