Fraunhofer-Gesellschaft Zur Foerderung Der Angewandten Forschung E.V.

Huawei Technologies Co., Limited

Cariad Se

Christian Riechert

Peter Kauff

Frederik Zilly

Marcus Bernd Mueller

Shan Gao

Oliver Schreer

Ingo Feldmann

Wolfgang Waizenegger

Yadong Lu

Marcus Müller

Marcus MÜLLER

A method for determining the orientation of a surface of an object in a detection region before or behind a vehicle by means of a camera of the vehicle comprises the following steps: detecting a first image of the detection region by means of the camera, detecting a second image of the detection region following in time on the detecting of the first image and by means of the camera, generating of first image data corresponding to the first image and second image data corresponding to the second image, determining of eight image coordinates of four pixels each in the first image and the second image, corresponding to four points on the surface of the object, by means of the first image data and the second image data, determining of a normal vector of the surface of the object by means of the eight image coordinates, determining of the orientation of the surface of the object by means of the normal vector.

Method and device for determining the orientation of a surface of an object

The present disclosure discloses an image registration method and apparatus. The method includes: determining a target plane; orthogonally projecting the optical center of each of the cameras in the planar camera array onto the target plane, to obtain a projected point of the optical center of each of the cameras; generating a rectangular grid on the target plane according to the projected points of the optical centers of the cameras in the planar camera array; obtaining a target grid point of each of the cameras according to the rectangular grid; determining a target camera coordinate system of each of the cameras; and registering, images collected by the cameras in the planar camera array. In embodiments of the present disclosure a target camera coordinate system of a camera is determined again, thereby greatly reducing complexity of subsequent image registration.

Image registration method and apparatus

A filter structure for filtering a disparity map includes a first filter, a second filter, and a filter selector. The first filter is for filtering a contemplated section of the disparity map according to a first measure of central tendency. The second filter is for filtering the contemplated section of the disparity maps according to a second measure of central tendency. The filter selector is provided for selecting the first filter or the second filter for filtering the contemplated section of the disparity map, the selection being based on at least one local property of the contemplated section. A corresponding method for filtering a disparity map includes determining a local property of the contemplated section and selecting a filter. The contemplated section is then filtered using the first filter or the second filter depending on a result of the selection.

Spatio-temporal disparity-map smoothing by joint multilateral filtering

An apparatus for estimating a disparity map based on at least two images is provided. The apparatus includes at least two processing units, which include a pixel recursion unit configured to determine a disparity value as a pixel recursion disparity candidate based on a plurality of pixel values of the at least two images and a selector configured to select a selected disparity candidate to determine at least one of the disparity map values of the disparity map. The selector is adapted to select the selected disparity candidate from a candidate group assigned to the selector. The candidate group assigned to the selector includes the pixel recursion disparity candidate, a second disparity candidate and a third disparity candidate. Moreover, the selector is adapted to select the selected disparity candidate independently from a different selector of a different processing unit of the at least two processing units.

Apparatus and method for real-time capable disparity estimation for virtual view rendering suitable for multi-threaded execution

Growing community of inventors

Berlin, Germany

Christian Riechert