Almotive Kft.

Aimotive Kft.

Zoltán Fegyver

László Babay

Kristóf Várszegi

The invention is a method for camera misalignment detection by means of processing images of a camera fixed to a vehicle and having a field of view containing a vehicle image area () imaging a portion of the vehicle and a remaining area (), wherein in said processing step a plurality of reference locations () within an input image are used, said reference locations () being determined as edge locations along a boundary of the vehicle image area () in a reference image, and said processing step comprises checking at the reference locations () within the input image whether said reference locations () are edge locations by ascertaining at each reference location () whether a magnitude of an image gradient is above a gradient threshold limit, and alerting misalignment depending on an ascertained subset of the reference locations () where the gradient threshold limit is not reached. The invention also relates to a camera system, a computer program product and a computer-readable medium embodying the method.

Method, camera system, computer program product and computer-readable medium for camera misalignment detection

The invention provides a method, a system and a computer-readable medium for calibrating a camera by using a multi-pattern calibration rig, each pattern being repetitive and comprising calibration shapes, wherein the following steps are carried out: capturing an image of the multi-pattern calibration rig with the camera, segmenting contours of the imaged calibration shapes, building groups of coherent contours based on the similarity of their shapes and their distances from each other, and identifying the positions of the patterns in the image based on the contour groups.

Growing community of inventors

Budapest, Hungary

Zoltán Fegyver