Patents by Inventor Lukas Ewecker

Lukas Ewecker has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 12536741
    Abstract: A computer-implemented method is provided for creating a three-dimensional virtual model of an environment (2) of a motor vehicle (1). The method includes capturing images of the environment (2); determining a plurality of regions (3; 4; 5; 6; 7; 8; 9) in each of the images and calculating a region entropy for each of the regions (3; 4; 5; 6; 7; 8; 9). The method then proceeds by selecting at least one region (4; 9) that has a higher region entropy than other regions (3; 5; 6; 7; 8); and generating the three-dimensional virtual model by first ascertaining three-dimensional coordinates for the selected at least one region (4; 9) and only thereafter ascertaining three-dimensional coordinates for the unselected regions (3; 5; 6; 7; 8). The three-dimensional virtual model includes the three-dimensional coordinates of all regions (3; 4; 5; 6; 7; 8; 9).
    Type: Grant
    Filed: November 17, 2023
    Date of Patent: January 27, 2026
    Assignee: DR. ING. H.C. F. PORSCHE AKTIENGESELLSCHAFT
    Inventors: Stefan Roos, Robin Schwager, Tim Bruehl, Lukas Ewecker
  • Patent number: 12483658
    Abstract: A method for dynamically adjusting a volume level in an online meeting. The method includes step a. holding an online meeting in which participants can have a conversation with one another. In step b. using an AI algorithm, monitoring and recognizing content of a conversation of the participants in the online meeting and assigning content scores to the content, wherein each participant portion of the participants is assigned a recognized sub-content in the conversation based on the content scores. In step c. using the AI algorithm, recognizing a first intersection of content scores from a plurality of sub-contents, and recognizing a second or more intersections of content scores from other multiple sub-contents. In step d. adjusting volume levels of individual participants, by raising or lowering the volume level of a participant portion for such other participants having one or no intersection with the participant portion.
    Type: Grant
    Filed: September 26, 2023
    Date of Patent: November 25, 2025
    Assignee: Dr. Ing. h.c. F. Porsche Aktiengesellschaft
    Inventors: Robin Schwager, Stefan Roos, Lukas Ewecker, Tim Brühl
  • Publication number: 20240169668
    Abstract: A computer-implemented method is provided for creating a three-dimensional virtual model of an environment (2) of a motor vehicle (1). The method includes capturing images of the environment (2); determining a plurality of regions (3; 4; 5; 6; 7; 8; 9) in each of the images and calculating a region entropy for each of the regions (3; 4; 5; 6; 7; 8; 9). The method then proceeds by selecting at least one region (4; 9) that has a higher region entropy than other regions (3; 5; 6; 7; 8); and generating the three-dimensional virtual model by first ascertaining three-dimensional coordinates for the selected at least one region (4; 9) and only thereafter ascertaining three-dimensional coordinates for the unselected regions (3; 5; 6; 7; 8). The three-dimensional virtual model includes the three-dimensional coordinates of all regions (3; 4; 5; 6; 7; 8; 9).
    Type: Application
    Filed: November 17, 2023
    Publication date: May 23, 2024
    Inventors: Stefan Roos, Robin Schwager, Tim Bruehl, Lukas Ewecker
  • Publication number: 20240155058
    Abstract: A method for dynamically adjusting a volume level in an online meeting. The method includes step a. holding an online meeting in which participants can have a conversation with one another. In step b. using an AI algorithm, monitoring and recognizing content of a conversation of the participants in the online meeting and assigning content scores to the content, wherein each participant portion of the participants is assigned a recognized sub-content in the conversation based on the content scores. In step c. using the AI algorithm, recognizing a first intersection of content scores from a plurality of sub-contents, and recognizing a second or more intersections of content scores from other multiple sub-contents. In step d. adjusting volume levels of individual participants, by raising or lowering the volume level of a participant portion for such other participants having one or no intersection with the participant portion.
    Type: Application
    Filed: September 26, 2023
    Publication date: May 9, 2024
    Applicant: Dr. Ing. h.c. F. Porsche Aktiengesellschaft
    Inventors: Robin Schwager, Stefan Roos, Lukas Ewecker, Tim Brühl
  • Publication number: 20230362468
    Abstract: An optical sensor system (1) has plural optical lens systems (2a-2n), a single imaging optical sensor (3) and plural light guides (4a-4n) corresponding to the number of optical lens systems (2a-2n). The light guides (4a-4n) extend respectively between the lens systems (2a-2n) and the optical sensor (3). Each of the lens systems (2a-2n) is associated respectively with one of the light guides (4a-4n). A switching apparatus (5) selectively switches between the light guide means (4a-4n).
    Type: Application
    Filed: May 4, 2023
    Publication date: November 9, 2023
    Inventors: Simon Isele, Stefan Roos, Lukas Ewecker