Patent №
US 11,763,518
Granted
2023-09-19
Filed 2020
Owner
ZIVID AS
Lab
—
AI components
1
vision
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
16956191
A method for generating a three-dimensional image of an object, comprising receiving a set of input point cloud data from an imaging system, the set of input point cloud data comprising two or more input point clouds, determining, for each point in the respective input point clouds, a value of a quality parameter that reflects a degree of uncertainty in the three dimensional coordinates as specified for that point, generating an output point cloud for generating a three-dimensional representation of the object surface, wherein, for each point in the output point cloud, the coordinates of the respective point are computed based on the coordinate values of the points in the input point clouds, wherein the extent to which the coordinate values in the respective input point clouds are taken into consideration in the computation is determined based on the values of the quality parameter associated with those respective points.
AI classification
Ownership
ZIVID AS
assignment · 551490408