Method for Predicting a Motion of an Object, Method for Calibrating a Motion Model, Method for Deriving a Predefined Quantity and Method for Generating a Virtual Reality View

Patent type: Property right

Process state: patent applied

Patent number: WO2019129355A1

Registration date: Dec. 29, 2017

Approval date: July 4, 2019

Abstract

A method for predicting a motion of an object is provided. The method includes determining a position of the object based on first time-series data of a position sensor mounted to the object and determining an orientation of the object based on second time-series data of at least one inertial sensor mounted to the object. Further, the method includes extrapolating a motion trajectory of the object based on a motion model using the position of the object and the orientation of the object, wherein the motion model uses a first weighting factor for the position of the object and a second weighting factor for the orientation of the object. Still further aspects of the present disclosure relate to determining ground truth moments in sensor streams and optimizing virtual reality views for a user.

Invention

Verfahren zur Vorhersage einer Bewegung eines Objekts, Verfahren zur Kalibrierung eines Bewegungsmodells, Verfahren zum Ableiten einer Vordefinierten Menge und Verfahren zur Erzeugung einer Ansicht der Virtuellen Realität Tobias Feigl, Christopher Mutschler

Patent holder(s)

Tobias Feigl Lehrstuhl für Informatik 2 (Programmiersysteme) Dr.-Ing. Christopher Mutschler Department Artificial Intelligence in Biomedical Engineering (AIBE), Lehrstuhl für Informatik 14 (Machine Learning and Data Analytics), Lehrstuhl für Informatik 2 (Programmiersysteme)