A method and a device are for identifying objects from camera images, e.g. for driver assistance systems. The method involves: capturing a series of camera images, determining corresponding features in two consecutive images, associating adjacent ones of the corresponding features with a plane in space to determine a plurality of such planes, and detecting objects while taking the determined planes into account.
Detection and validation of objects from sequential images of a camera by using homographies
2021-04-20
Patent
Electronic Resource
English
Detection and validation of objects from sequential images of a camera by using homographies
European Patent Office | 2021
|ONLINE EXTRINSIC MULTI-CAMERA CALIBRATION USING GROUND PLANE INDUCED HOMOGRAPHIES
British Library Conference Proceedings | 2013
|The geometric error for homographies
British Library Online Contents | 2005
|