In this paper a well defined case of autonomous car driving in a typical traffic jam condition is addressed. Such a situation has been faced looking at the relation between the rate of change of the area projected on the image plane by a moving object and its time-to-crash. A visual sensor has been developed which is able to detect expansions or contractions of the area shape, without any explicit computation of the optical flow field. This sensor provides the visual input of an opto-motor reflex, working in real-time (12.5 Hz), which is able to keep constant in time the distnace between the camera and a frontal obstacle. The whole methodology has been extensively tested by using a mobile platform. The performances of the reflex on real image sequences will be shown.
A real-time visual reflex for autonomous navigation
Echtzeit Sichtreflexe für autonome Navigation
1993
6 Seiten, 8 Bilder, 13 Quellen
Conference paper
English
A Real-time Visual Reflex for Autonomous Navigation
British Library Conference Proceedings | 1993
|Real-time lane detection for autonomous navigation
IEEE | 2001
|Real-Time Lane Detection for Autonomous Navigation
British Library Conference Proceedings | 2001
|British Library Online Contents | 2008
|