Computer Engineering Paper Massimo Bertozzi, Alberto Broggi, Marcello Carletti, Alessandra Fascioli, Thorsten Graf, Paolo Grisleri, and Michael Meinecke, IR Pedestrian Detection for Advanced Driver Assistance Systems, In Procs. 25th Pattern Recognition Symposium, volume 2781, pages 582-590, Magdeburg, Germany, September 2003. Springer-Verlag,
Download the paper in PDF format


This paper describes a system for pedestrian detection in infrared images implemented and tested on an experimental vehicle. A specific stabilization procedure is applied after image acquisition and before processing to cope with vehicle movements affecting the camera calibration. The localization of pedestrians is based on the search for warm symmetrical objects with specific size and aspect ratio. A set of filters is used to reduce false detections. The final validation process relies on the human shape s morphological characteristics.

For more information send email to broggi@CE.UniPR.IT