Patents by Inventor Attila Borcs

Attila Borcs 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).

  • Device and method for automatic image enhancement in vehicles
    Patent number: 11195258
    Abstract: A device and method for automatic image enhancement in vehicles, in particular land vehicles, including a camera to record a primary-image, and an image-processing-module to determine a resulting-image from the primary-image.
    Type: Grant
    Filed: September 19, 2019
    Date of Patent: December 7, 2021
    Assignee: Robert Bosch GmbH
    Inventors: Attila Borcs, Kornel Istvan Kis, Levente Kis, Peter Korosi-Szabo
  • System for assessing an image, operating assistance method, control unit for a working device, and working device
    Patent number: 11087171
    Abstract: A system for assessing and/or adapting an image recorded with a camera, based on a deep neural network. The deep neural network undergoes a training, the training of the deep neural network is carried out based on a loss function as a metric, the loss function is based on a structural similarity index, and the structural similarity index in the training is ascertained based on at least one input image of the underlying camera, an output image of the deep neural network, and in particular an adaptation method via the deep neural network and a target image as default.
    Type: Grant
    Filed: August 16, 2019
    Date of Patent: August 10, 2021
    Assignee: Robert Bosch GmbH
    Inventors: Peter Korosi-Szabo, Attila Borcs, Kornel Istvan Kis, Levente Kis
  • DEVICE AND METHOD FOR AUTOMATIC IMAGE ENHANCEMENT IN VEHICLES
    Publication number: 20200098095
    Abstract: A device and method for automatic image enhancement in vehicles, in particular land vehicles, including a camera to record a primary-image, and an image-processing-module to determine a resulting-image from the primary-image.
    Type: Application
    Filed: September 19, 2019
    Publication date: March 26, 2020
    Inventors: Attila Borcs, Kornel Istvan, Levente Kis, Peter Korosi-Szabo
  • SYSTEM FOR ASSESSING AN IMAGE, OPERATING ASSISTANCE METHOD, CONTROL UNIT FOR A WORKING DEVICE, AND WORKING DEVICE
    Publication number: 20200065622
    Abstract: A system for assessing and/or adapting an image recorded with a camera, based on a deep neural network. The deep neural network undergoes a training, the training of the deep neural network is carried out based on a loss function as a metric, the loss function is based on a structural similarity index, and the structural similarity index in the training is ascertained based on at least one input image of the underlying camera, an output image of the deep neural network, and in particular an adaptation method via the deep neural network and a target image as default.
    Type: Application
    Filed: August 16, 2019
    Publication date: February 27, 2020
    Inventors: Peter Korosi-Szabo, Attila Borcs, Kornel Istvan Kis, Levente Kis
  • Method and system for generating a three-dimensional model
    Patent number: 10163256
    Abstract: The invention is a method for generating a three-dimensional model, said method comprising generating (S100), by means of a scanning device, a point set corresponding to a scene comprising at least one object shape, dividing (S120) the point set corresponding to the scene into a foreground point set corresponding to a foreground of the scene, and comprising a subset corresponding to the at least one object shape of the point set corresponding to the scene, and a background point set corresponding to a background of the scene, separating (S130) from the foreground point set, at least one object shape subset corresponding to each of the at least one object shape, respectively, generating (S140) a background three-dimensional model on the basis of the background point set, generating (S150) from optical recordings a three-dimensional model of at least one substituting object shape assignable to each of the at least one object shape, respectively, and generating (S160) a combined three-dimensional model on the ba
    Type: Grant
    Filed: February 14, 2014
    Date of Patent: December 25, 2018
    Assignee: MTA Szamitastechnikai Es Automatizalasi Kutato Intezet
    Inventors: Csaba Benedek, Dmitrij Csetverikov, Zsolt Janko, Tamas Sziranyi, Attila Borcs, Oszkar Jozsa, Ivan Eichhardt
  • Method And System For Generating A Three-Dimensional Model
    Publication number: 20160093101
    Abstract: The invention is a method for generating a three-dimensional model, said method comprising generating (S100), by means of a scanning device, a point set corresponding to a scene comprising at least one object shape, dividing (S120) the point set corresponding to the scene into a foreground point set corresponding to a foreground of the scene, and comprising a subset corresponding to the at least one object shape of the point set corresponding to the scene, and a background point set corresponding to a background of the scene, separating (S130) from the foreground point set, at least one object shape subset corresponding to each of the at least one object shape, respectively, generating (S140) a background three-dimensional model on the basis of the background point set, generating (S150) from optical recordings a three-dimensional model of at least one substituting object shape assignable to each of the at least one object shape, respectively, and generating (S160) a combined three-dimensional model on the ba
    Type: Application
    Filed: February 14, 2014
    Publication date: March 31, 2016
    Applicant: MTA Szamitastechnikai Es Automatizalasi Kutato Intezet
    Inventors: Csaba Benedek, Dmitrij Csetverikov, Zsolt Janko, Tamas Sziranyi, Attila Borcs, Oszkar Jozsa, Ivan Eichhardt