-
公开(公告)号：US10102644B2
公开(公告)日：2018-10-16
申请号：US15384615
申请日：2016-12-20
Applicant: Delphi Technologies, Inc.
Inventor： Jens Westerhoff , Stephanie Lessmann , Mirko Meuter , Jan Siegemund
Abstract: A method of estimating an orientation of a camera relative to a surface includes providing a first image and a subsequent second image captured by the camera; selecting a first point from the first image and a second point from the second image, where the first and second points represent the same object; defining a first optical flow vector connecting the first point and the second point; carrying out a first estimation step comprising estimating two components of the normal vector in the camera coordinate system by using the first optical flow vector and restricting parameter space to only the two components of the normal vector, wherein a linear equation system derived from a homography matrix that represents a projective transformation between the first image and the second image is provided and the two components of the normal vector in the camera coordinate system are estimated by solving the linear equation system; and determining the orientation of the camera relative to the surface using the results of the first estimation step.
-
2.发明申请公开(公告)号：US20170206674A1
公开(公告)日：2017-07-20
申请号：US15384615
申请日：2016-12-20
Applicant: Delphi Technologies, Inc.
Inventor： Jens Westerhoff , Stephanie Lessmann , Mirko Meuter , Jan Siegemund
CPC classification number: G06T7/70 , B60R11/04 , G06T3/20 , G06T7/60 , G06T7/97 , G06T2207/30244 , G06T2207/30252
Abstract: A method of estimating an orientation of a camera relative to a surface includes providing a first image and a subsequent second image captured by the camera; selecting a first point from the first image and a second point from the second image, where the first and second points represent the same object; defining a first optical flow vector connecting the first point and the second point; carrying out a first estimation step comprising estimating two components of the normal vector in the camera coordinate system by using the first optical flow vector and restricting parameter space to only the two components of the normal vector, wherein a linear equation system derived from a homography matrix that represents a projective transformation between the first image and the second image is provided and the two components of the normal vector in the camera coordinate system are estimated by solving the linear equation system; and determining the orientation of the camera relative to the surface using the results of the first estimation step.
-
公开(公告)号：US20170278014A1
公开(公告)日：2017-09-28
申请号：US15467684
申请日：2017-03-23
Applicant: Delphi Technologies, Inc.
Inventor： Stephanie Lessmann , Mirko Meuter , Jens Westerhoff
CPC classification number: G06N20/00 , G06K9/00791 , G06K9/6262 , G06K9/6267 , G06K9/66 , G06T5/20 , G06T7/269 , G06T7/73 , G06T2207/10016 , G06T2207/20081 , G06T2207/30244 , G06T2207/30252
Abstract: A method of generating a confidence measure for an estimation derived from images captured by a camera mounted on a vehicle includes: capturing consecutive training images by the camera while the vehicle is moving; determining ground-truth data for the training images; computing optical flow vectors from the training images and estimating a first output signal based on the optical flow vectors for each of the training images, the first output signal indicating an orientation of the camera; classifying the first output signal for each of the training images as a correct signal or a false signal depending on how good the first output signal fits to the ground-truth data; determining optical flow field properties for each of the training images derived from the training images; and generating a separation function that separates the optical flow field properties into two classes based on the classification of the first output signal.
-
-
Search Results
3
records
(took 0.013 seconds)
