Early detection of moving obstacles is an important goal for many vision based driver assistance systems. In order to protect pedestrians, in particular children, in inner city traffic, the authors are using stereo vision and motion analysis in order to manage those situations. The flow/depth constraint combines both methods in an elegant way and leads to a robust and powerful detection scheme. Pyramidal Opt. Flow computation together with compensation of rotational camera ego-motion expands the measurement range, enabling them to use the system also at higher speeds.
Real time fusion of motion and stereo using flow/depth constraint for fast obstacle detection
Echtzeitfusion von Bewegung und Stereo mit Hilfe von Fluß-/Tiefebeschränkung für die schnelle Erkennung von Hindernissen
2002
8 Seiten, 3 Bilder, 13 Quellen
Conference paper
English
Fast obstacle detection using flow/depth constraint
IEEE | 2002
|Fast Obstacle Detection using Flow/Depth constraint
British Library Conference Proceedings | 2003
|An Obstacle Detection Method by Fusion of Radar and Motion Stereo
British Library Online Contents | 2002
|An Obstacle Detection Method by Fusion of Radar and Motion Stereo
British Library Conference Proceedings | 2002
|