Patents by Inventor Jan Hendrik HOSANG

Jan Hendrik HOSANG 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).

  • System and method for detecting objects in a digital image, and system and method for rescoring object detections
    Patent number: 11715281
    Abstract: The invention relates to a system for detecting objects in a digital image. The system comprises a neural network which is configured to generate candidate windows indicating object locations, and to generate for each candidate window a score representing the confidence of detection. Generating the scores comprises: generating a latent representation for each candidate window, updating the latent representation of each candidate window based on the latent representation of neighboring candidate windows, and generating the score for each candidate window based on its updated latent representation The invention further relates to a system for rescoring object detections in a digital image and to methods of detecting objects and rescoring objects.
    Type: Grant
    Filed: December 27, 2021
    Date of Patent: August 1, 2023
    Assignees: TOYOTA MOTOR EUROPE, MAX-PLANCK-GESELLSCHAFT ZUR FORDERUNG DER WISSENSCHAFTEN E.V.
    Inventors: Daniel Olmeda Reino, Bernt Schiele, Jan Hendrik Hosang, Rodrigo Benenson
  • SYSTEM AND METHOD FOR DETECTING OBJECTS IN A DIGITAL IMAGE, AND SYSTEM AND METHOD FOR RESCORING OBJECT DETECTIONS
    Publication number: 20220129701
    Abstract: The invention relates to a system for detecting objects in a digital image. The system comprises a neural network which is configured to generate candidate windows indicating object locations, and to generate for each candidate window a score representing the confidence of detection. Generating the scores comprises: generating a latent representation for each candidate window, updating the latent representation of each candidate window based on the latent representation of neighboring candidate windows, and generating the score for each candidate window based on its updated latent representation The invention further relates to a system for rescoring object detections in a digital image and to methods of detecting objects and rescoring objects.
    Type: Application
    Filed: December 27, 2021
    Publication date: April 28, 2022
    Applicants: TOYOTA MOTOR EUROPE, MAX-PLANCK-GESELLSCHAFT ZUR FORDERUNG DER WISSENSCHAFTEN E.V.
    Inventors: Daniel OLMEDA REINO, Bernt Schiele, Jan Hendrik Hosang, Rodrigo Benenson
  • SYSTEM AND METHOD FOR DETECTING OBJECTS IN A DIGITAL IMAGE, AND SYSTEM AND METHOD FOR RESCORING OBJECT DETECTIONS
    Publication number: 20200193225
    Abstract: The invention relates to a system for detecting objects in a digital image. The system comprises a neural network which is configured to generate candidate windows indicating object locations, and to generate for each candidate window a score representing the confidence of detection. Generating the scores comprises: generating a latent representation for each candidate window, updating the latent representation of each candidate window based on the latent representation of neighboring candidate windows, and generating the score for each candidate window based on its updated latent representation The invention further relates to a system for rescoring object detections in a digital image and to methods of detecting objects and rescoring objects.
    Type: Application
    Filed: April 28, 2017
    Publication date: June 18, 2020
    Applicants: Toyota Motor Europe, Max-Planck-Gesellschaft zur Förderung der Wissenschaften e.V.
    Inventors: Daniel OLMEDA REINO, Bernt SCHIELE, Jan Hendrik HOSANG, Rodrigo BENENSON