Patents by Inventor Ryan Kottenstette

Ryan Kottenstette 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).

  • Publication number: 20200226373
    Abstract: Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.
    Type: Application
    Filed: March 27, 2020
    Publication date: July 16, 2020
    Inventors: Ryan Kottenstette, Peter Lorenzen, Suat Gedikli
  • Patent number: 10643072
    Abstract: Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.
    Type: Grant
    Filed: March 14, 2019
    Date of Patent: May 5, 2020
    Assignee: Cape Analytics, Inc.
    Inventors: Ryan Kottenstette, Peter Lorenzen, Suat Gedikli
  • Patent number: 10366288
    Abstract: Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.
    Type: Grant
    Filed: March 14, 2019
    Date of Patent: July 30, 2019
    Assignee: CAPE ANALYTICS, INC.
    Inventors: Ryan Kottenstette, Peter Lorenzen, Suat Gedikli
  • Publication number: 20190213413
    Abstract: Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.
    Type: Application
    Filed: March 14, 2019
    Publication date: July 11, 2019
    Inventors: Ryan KOTTENSTETTE, Peter LORENZEN, Suat GEDIKLI
  • Publication number: 20190213412
    Abstract: Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.
    Type: Application
    Filed: March 14, 2019
    Publication date: July 11, 2019
    Inventors: Ryan KOTTENSTETTE, Peter LORENZEN, Suat GEDIKLI
  • Patent number: 10311302
    Abstract: Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.
    Type: Grant
    Filed: August 31, 2016
    Date of Patent: June 4, 2019
    Assignee: Cape Analytics, Inc.
    Inventors: Ryan Kottenstette, Peter Lorenzen, Suat Gedikli
  • Publication number: 20170076438
    Abstract: Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.
    Type: Application
    Filed: August 31, 2016
    Publication date: March 16, 2017
    Inventors: Ryan KOTTENSTETTE, Peter LORENZEN, Suat GEDIKLI
  • Publication number: 20120045670
    Abstract: Provided are novel electrochemical cells that include positive electrodes, negative electrodes containing high capacity active materials such as silicon, and auxiliary electrodes containing lithium. An auxiliary electrode is provided in the cell at least prior to its formation cycling and is used to supply lithium to the negative electrode. The auxiliary electrode may be then removed from the cell prior or after formation. The transfer of lithium to the negative electrode may be performed using a different electrolyte, a higher temperature, and/or a slower rate than during later operational cycling of the cell. After this transfer, the negative electrode may remain pre-lithiated during later cycling at least at a certain predetermined level. This pre-lithiation helps to cycle the cell at more optimal conditions and to some degree maintain this cycling performance over the operating life of the cell. Also provided are methods of fabricating such cells.
    Type: Application
    Filed: September 26, 2011
    Publication date: February 23, 2012
    Applicant: AMPRIUS, INC.
    Inventors: Constantin I. Stefan, Rainer J. Fasching, Gregory Alan Roberts, Ryan Kottenstette, Song Han, Ghyrn E. Loveness