Patents by Inventor Friedrich FRAUNDORFER
Friedrich FRAUNDORFER 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: 11797724Abstract: Systems and techniques are provided for determining environmental layouts. For example, based on one or more images of an environment and depth information associated with the one or more images, a set of candidate layouts and a set of candidate objects corresponding to the environment can be detected. The set of candidate layouts and set of candidate objects can be organized as a structured tree. For instance, a structured tree can be generated including nodes corresponding to the set of candidate layouts and the set of candidate objects. A combination of objects and layouts can be selected in the structured tree (e.g., based on a search of the structured tree, such as using a Monte-Carlo Tree Search (MCTS) algorithm or adapted MCTS algorithm). A three-dimensional (3D) layout of the environment can be determined based on the combination of objects and layouts in the structured tree.Type: GrantFiled: November 8, 2021Date of Patent: October 24, 2023Assignee: QUALCOMM IncorporatedInventors: Shreyas Hampali, Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit
-
Patent number: 11769278Abstract: Vectorization of an image begins by receiving a two-dimensional rasterized image and returning a descriptor for each pixel in the image. Corner detection returns coordinates for all corners in the image. The descriptors are filtered using the corner positions to produce corner descriptors for the corner positions. A score matrix is extracted using the corner descriptors in order to produce a permutation matrix that indicates the connections between all of the corner positions. The corner coordinates and the permutation matrix are used to perform vector extraction to produce a machine-readable vector file that represents the two-dimensional image. Optionally, the corner descriptors may be refined before score extraction and the corner coordinates may be refined before vector extraction. A three-dimensional or N-dimensional image may also be input.Type: GrantFiled: November 7, 2022Date of Patent: September 26, 2023Assignee: Blackshark.ai GmbHInventors: Stefano Zorzi, Shabab Bazrafkan, Friedrich Fraundorfer, Stefan Habenschuss
-
Publication number: 20230146018Abstract: Vectorization of an image begins by receiving a two-dimensional rasterized image and returning a descriptor for each pixel in the image. Corner detection returns coordinates for all corners in the image. The descriptors are filtered using the corner positions to produce corner descriptors for the corner positions. A score matrix is extracted using the corner descriptors in order to produce a permutation matrix that indicates the connections between all of the corner positions. The corner coordinates and the permutation matrix are used to perform vector extraction to produce a machine-readable vector file that represents the two-dimensional image. Optionally, the corner descriptors may be refined before score extraction and the corner coordinates may be refined before vector extraction. A three-dimensional or N-dimensional image may also be input.Type: ApplicationFiled: November 7, 2022Publication date: May 11, 2023Inventors: Stefano ZORZI, Shabab BAZRAFKAN, Friedrich FRAUNDORFER, Stefan HABENSCHUSS
-
Publication number: 20220156426Abstract: Systems and techniques are provided for determining environmental layouts. For example, based on one or more images of an environment and depth information associated with the one or more images, a set of candidate layouts and a set of candidate objects corresponding to the environment can be detected. The set of candidate layouts and set of candidate objects can be organized as a structured tree. For instance, a structured tree can be generated including nodes corresponding to the set of candidate layouts and the set of candidate objects. A combination of objects and layouts can be selected in the structured tree (e.g., based on a search of the structured tree, such as using a Monte-Carlo Tree Search (MCTS) algorithm or adapted MCTS algorithm). A three-dimensional (3D) layout of the environment can be determined based on the combination of objects and layouts in the structured tree.Type: ApplicationFiled: November 8, 2021Publication date: May 19, 2022Inventors: Shreyas HAMPALI, Sinisa STEKOVIC, Friedrich FRAUNDORFER, Vincent LEPETIT
-
Patent number: 11328476Abstract: Techniques are provided for determining one or more environmental layouts. For example, one or more planes can be detected in an input image of an environment. The one or more planes correspond to one or more objects in the input image. One or more three-dimensional parameters of the one or more planes can be determined. One or more polygons can be determined using the one or more planes and the one or more three-dimensional parameters of the one or more planes. A three-dimensional layout of the environment can be determined based on the one or more polygons.Type: GrantFiled: March 31, 2020Date of Patent: May 10, 2022Assignee: QUALCOMM IncorporatedInventors: Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit
-
Patent number: 11205074Abstract: A method detects the image of an obstacle-free region surrounding a photograph-capturing unit. A photograph of a portion of the environment of the photograph-capturing unit is created by the photograph-capturing unit and a digital picture is created. The digital picture is examined for the presence of possible boundaries of an obstacle-free region, a boundary indicator value being determined for each individual pixel of the digital picture in accordance with the picture data of the digital picture within an environment of the pixel in question. The picture data being defined pixel by pixel, the boundary indicator value indicating the probability that the image of the boundary of an obstacle-free region is located within a specified pixel environment. A coordinate parameterization having two parameters is specified for the digital picture, which coordinate parameterization corresponds in particular to the pixel coordinates.Type: GrantFiled: September 24, 2018Date of Patent: December 21, 2021Assignee: Tec-Innovation GmbHInventors: Markus Raffer, Kevin Pajestka, Friedrich Fraundorfer, David Schinagl
-
Publication number: 20210150805Abstract: Techniques are provided for determining one or more environmental layouts. For example, one or more planes can be detected in an input image of an environment. The one or more planes correspond to one or more objects in the input image. One or more three-dimensional parameters of the one or more planes can be determined. One or more polygons can be determined using the one or more planes and the one or more three-dimensional parameters of the one or more planes. A three-dimensional layout of the environment can be determined based on the one or more polygons.Type: ApplicationFiled: March 31, 2020Publication date: May 20, 2021Inventors: Sinisa STEKOVIC, Friedrich FRAUNDORFER, Vincent LEPETIT
-
Publication number: 20200293776Abstract: A method detects the image of an obstacle-free region surrounding a photograph-capturing unit. A photograph of a portion of the environment of the photograph-capturing unit is created by the photograph-capturing unit and a digital picture is created. The digital picture is examined for the presence of possible boundaries of an obstacle-free region, a boundary indicator value being determined for each individual pixel of the digital picture in accordance with the picture data of the digital picture within an environment of the pixel in question. The picture data being defined pixel by pixel, the boundary indicator value indicating the probability that the image of the boundary of an obstacle-free region is located within a specified pixel environment. A coordinate parameterization having two parameters is specified for the digital picture, which coordinate parameterization corresponds in particular to the pixel coordinates.Type: ApplicationFiled: September 24, 2018Publication date: September 17, 2020Inventors: Markus RAFFER, Kevin PAJESTKA, Friedrich FRAUNDORFER, David SCHINAGL