Patents Examined by Tom Y. Lu
  • Patent number: 11069081
    Abstract: In an aspect, a computer implemented method receives, for a volume within a building, a set of images captured from corresponding locations within the volume, each image taken at a corresponding location, and each image having data specifying the corresponding location from which the image was captured; receiving a three-dimensional point cloud of the volume; detects, using one or more computer vision processing techniques, items of interest within the images; for each item of interest in each image, determines, based on the point cloud and the data specifying the corresponding locations from which the images were captured, a coordinate for the item of interest, the coordinate specifying a location within the volume that corresponds to the item of interest in the image; and stores the data specifying each item of interest and, for each item of interest, its determined coordinate, in a data storage.
    Type: Grant
    Filed: January 27, 2020
    Date of Patent: July 20, 2021
    Assignee: Google LLC
    Inventor: Juergen Sturm
  • Patent number: 11064111
    Abstract: An alignment guide may be provided in the field of view of a camera associated with a mobile device used to capture an image of a check. When the image of the check is within the alignment guide in the field of view, an image may be taken by the camera and provided from the mobile device to a financial institution. The alignment guide may be adjustable at the mobile device. The image capture may be performed automatically by the camera or the mobile device as soon as the image of the check is determined to be within the alignment guide. The check may be deposited in a user's bank account based on the image. Any technique for sending the image to the financial institution may be used.
    Type: Grant
    Filed: September 10, 2019
    Date of Patent: July 13, 2021
    Assignee: United Services Automobile Association (USAA)
    Inventors: Bharat Prasad, Minya Liang, Reynaldo Medina, III
  • Patent number: 11062446
    Abstract: A method of analyzing a perovskite structure using machine learning, the method comprising the steps of: (a) obtaining an atomic image using an atomic structure simulator; (b) making a CNN model learn the atomic image; and (c) obtaining an atomic image of an actual substance using a TEM or a STEM and then applying the image to the learnt CNN model.
    Type: Grant
    Filed: September 27, 2019
    Date of Patent: July 13, 2021
    Assignee: Rostech Academy-Industry Foundation
    Inventors: Si-Young Choi, Gi-Yeop Kim, Kyoung-June Ko, Jin-Hyuk Jang
  • Patent number: 11051722
    Abstract: Apparatus comprises an acceleration unit, a processing unit and a display for continuous real time monitoring. The acceleration unit is attached or held by a body region of a mammal comprises a 3D-acceleration sensor and a wireless transmitter for transmitting a measurement signal provided by the acceleration sensor continuously. The processing unit processes the measurement signal continuously in a band of a medically defined movement of the body region, forms a movement index on the basis of a norm of values of acceleration in a first time window, and forms a value(s) of amplitude, and/or a value of frequency of the spatial movement of the body region on the basis of a power spectral density in second time window of a known duration. The display displays said movement index with said value of amplitude, and/or said value of frequency of the spatial movement continuously in real time.
    Type: Grant
    Filed: October 28, 2019
    Date of Patent: July 6, 2021
    Inventors: Jani Katisko, Ossi Kumpula
  • Patent number: 11049256
    Abstract: An image processing apparatus including: one or more hardware processors; and a memory for storing instructions to be executed by the hardware processors, wherein when the instructions stored in the memory are executed by the hardware processors, the apparatus functions as: an acquiring unit configured to acquire image data; a derivation unit configured to derive an occurrence rate of a value corresponding to pixel data on a first region in each of a plurality of images corresponding to the image data acquired by the acquiring unit; and a determining unit configured to determine a value of the first region in a background image corresponding to the image data based on a plurality of values including a value on which a highest occurrence rate is derived by the derivation unit and a value on which an occurrence rate lower than the highest occurrence rate is derived by the derivation unit.
    Type: Grant
    Filed: December 21, 2018
    Date of Patent: June 29, 2021
    Inventor: Kina Itakura
  • Patent number: 11049260
    Abstract: Provided is a technique for extracting information with which it is possible to track an object to be tracked, even if it happens that the object to be tracked is hidden or the like. This image processing device is provided with: a moving region identification unit which identifies, in a video, the image region associated with a moving object shown in the video; a stationary region identification unit which identifies, in the video, the image region associated with a stationary object shown in the video; and an extraction unit which extracts a feature of a partial image that is included in the image region associated with the stationary object, and that does not overlap the image region associated with the moving object.
    Type: Grant
    Filed: October 19, 2016
    Date of Patent: June 29, 2021
    Inventor: Ryo Kawai
  • Patent number: 11035870
    Abstract: A model-based method of determining characteristics of a specimen container cap to identify the container cap. The method includes providing a specimen container including a container cap; capturing backlit images of the container cap taken at different exposures lengths and using a plurality of different nominal wavelengths; selecting optimally-exposed pixels from the images at different exposure lengths at each nominal wavelength to generate optimally-exposed image data for each nominal wavelength; classifying the optimally-exposed pixels as at least being one of a tube, a label or a cap; and identifying a shape of the container cap based upon the optimally-exposed pixels classified as being the cap and the image data for each nominal wavelength. Quality check modules and specimen testing apparatus adapted to carry out the method are described, as are numerous other aspects.
    Type: Grant
    Filed: July 7, 2017
    Date of Patent: June 15, 2021
    Assignee: Siemens Healthcare Diagnostics Inc.
    Inventors: Stefan Kluckner, Yao-Jen Chang, Terrence Chen, Benjamin S. Pollack
  • Patent number: 11037296
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining a subset of brain data of a patient. One of the methods comprises providing connectivity data for presentation to a user, the connectivity data characterizing, for each pair of parcellations comprising a first parcellation and a second parcellation from a plurality of parcellations, a degree of correlation between the brain activity of the first parcellation and the brain activity of the second parcellation in the brain of a patient; determining one or more elements of interest in the connectivity data; determining one or more parcellations associated with elements of interest in the connectivity data; obtaining brain atlas data; determining a subset of the brain atlas data associated with the determined parcellations; and providing the subset of the brain atlas data to a user device for rendering the subset to the user.
    Type: Grant
    Filed: August 7, 2020
    Date of Patent: June 15, 2021
    Assignee: Omniscient Neurotechnology Pty Limited
    Inventors: Michael Edward Sughrue, Stephane Philippe Doyen
  • Patent number: 11030456
    Abstract: A method and system for geo-localization in sensor-deprived or sensor-limited environments includes receiving an image file for geo-localization of a location depicted by the image file in a sensor-deprived environment; applying a plurality of geo-localization modules to the image file; generating, by each of the plurality of geo-localization modules, a module output, each module output including a module geolocation for the location and a module confidence score for the module geolocation; generating an ensemble geolocation output, the ensemble geolocation output including an ensemble geolocation for the location and an ensemble confidence score for the ensemble geolocation, the ensemble geolocation output being a weighted combination of the module outputs; and displaying the ensemble geolocation output to a display.
    Type: Grant
    Filed: January 29, 2021
    Date of Patent: June 8, 2021
    Inventors: Courtney Crosby, Jessica Yang, Adam Letcher, Alec McLean
  • Patent number: 11023718
    Abstract: A living body detection method and a living body detection system are provided. A radio-frequency signal reflected by an experiment living body is received, and raw sampling data of the RF signal are obtained. A feature extraction process is performed to generate initial training features of sampling datasets, wherein the initial training features respectively correspond to feature generation rules. A classification prediction model is established according to a posture of the experiment living body and the initial training features, and correlation feature weightings respectively corresponding to the initial training features are obtained. Preferred features corresponding to at least one of the feature generation rules are selected from the initial training features according to the correlation feature weightings.
    Type: Grant
    Filed: June 3, 2019
    Date of Patent: June 1, 2021
    Assignee: Wistron Corporation
    Inventors: Zhao-Yuan Lin, Yao-Tsung Chang, Zhe-Yu Lin
  • Patent number: 11022685
    Abstract: A tracking system and method for constructing pictures of tracks of moving targets on a scene from electro-optical (EO) detections are described. The system includes EO sensors, and an EO tracker constructing pictures of the tracks of the targets. The EO tracker includes a pre-processing system for receiving EO detections of the targets and locating the targets on a world map, a candidate track selection system for finding candidate tracks, a track initializing module for receiving the EO detections and initializing a new track, an assigning system for assigning the EO detections to the candidate tracks, a data updating system for updating the candidate tracks after the assigning, and for generating an ambiguity set of tracks and an exclusion set of tracks, a picture providing system for receiving the ambiguity set and the exclusion set to generate a picture, and a tracker database for storing the updated tracks.
    Type: Grant
    Filed: November 19, 2019
    Date of Patent: June 1, 2021
    Assignee: ELTA SYSTEMS LTD.
    Inventors: Akiva Novoselsky, Benjamin Kupfer, Merav Shomrony-Danieli
  • Patent number: 11023841
    Abstract: A worksite risk analysis and documentation system and method defines, captures, categorizing, and documents, while analyzing functional physical demands of a plurality of jobs at various worksites, including environmental health and safety risks/opportunities as well as ergonomic risks/opportunities. The system and method prioritizes risk and body part injury based on individual injury costs associated with each body part used in various tasks at the worksite. The system and method creates a report which includes a catalog of engineered solutions and administrative control solutions to various issues and ergonomic risks/opportunities.
    Type: Grant
    Filed: January 15, 2018
    Date of Patent: June 1, 2021
    Assignee: Ergonomics International, LLC
    Inventors: Samuel Bradbury, Mark Heidebrecht
  • Patent number: 11010912
    Abstract: Method that merges two or more point clouds captured from a scene, eliminates redundant points, and retains points that best represent the scene. The method may generally include a detection step, which locates points from different clouds that are close and thus potentially redundant, followed by a selection step that identifies preferred points. Clouds may be represented as range images, which may simplify both steps. Closeness testing may be optimized by dividing range images into tiles and testing tile bounding volumes for intersections between clouds. Selection of preferred points may incorporate user input, or it may be fully or partially automated. User selection may be performed using 2D drawing tools on range images to identify images with preferred views of a scene. Automated selection may assign a quality measure to points based for example on the surface resolution of each point cloud scan at overlapping points.
    Type: Grant
    Filed: July 3, 2019
    Date of Patent: May 18, 2021
    Assignee: Nurulize, Inc.
    Inventors: Tobias Anderberg, Malik Williams
  • Patent number: 11004227
    Abstract: An identification apparatus includes a first one-vs.-rest identifier, a second one-vs.-rest identifier, and a corrector. The first one-vs.-rest identifier identifies a first class among a plurality of classes. The second one-vs.-rest identifier identifies a second class different from the first class among the plurality of classes. The corrector corrects an identification result provided by the first one-vs.-rest identifier using the identification result provided by the second one-vs.-rest identifier.
    Type: Grant
    Filed: January 25, 2018
    Date of Patent: May 11, 2021
    Assignee: CASIO COMPUTER CO., LTD.
    Inventor: Kazuhisa Matsunaga
  • Patent number: 11004204
    Abstract: A computer-implemented method includes: obtaining a sample picture and corresponding mark data, in which the mark data includes a first damage mark outline, and in which the first damage mark outline frames a damaged object in the sample picture; determining a segmentation type for a plurality of pixels in the sample picture based on the first damage mark outline, to generate segmentation mark data; inputting the sample picture to a weak segmentation damage detection model, in which the weak segmentation damage detection model includes an outline prediction branch and a segmentation prediction branch, in which the outline prediction branch outputs outline prediction data including a damage prediction outline, the damage prediction outline framing a predicted damaged object in the sample picture, and in which the segmentation prediction branch includes segmentation prediction data including a predicted segmentation type of each pixel of the plurality of pixels.
    Type: Grant
    Filed: July 31, 2020
    Date of Patent: May 11, 2021
    Assignee: Advanced New Technologies Co., Ltd.
    Inventors: Wei Zhang, Wei Chu
  • Patent number: 10990839
    Abstract: An anti-counterfeit method for assisting in face recognition includes the following steps: capturing a dynamic image of an object; filtering a plurality of time-varying signals from the dynamic image to obtain a plurality of filter signals; and comparing the filter signals and preset biological information that corresponds to the object, to output a determining result. When the dynamic image of the object is captured, according to this method, at least one region is interest is set in the dynamic image, and each time-varying signal corresponds to a time-varying gray-scale value of at least one pixel of the dynamic image in the region of interest. An anti-counterfeit system is also provided.
    Type: Grant
    Filed: January 23, 2019
    Date of Patent: April 27, 2021
    Inventors: Wei-Hua Hao, Nien-Chih Wang
  • Patent number: 10977390
    Abstract: Disclosed is a computer-implemented method for generating an anonymized medical image of an anatomical body part of a patient, a corresponding computer program, a program storage medium storing such a program and a computer for executing the program, as well as a medical system comprising an electronic data storage device and the aforementioned computer. The disclosed method encompasses establishing a mapping from a patient image onto an atlas, changing that mapping, and applying the inverse of the changed mapping to the atlas in order to transform image content from the atlas to the patient image in order to achieve a deformed and thereby anonymised appearance of the patient image.
    Type: Grant
    Filed: February 28, 2019
    Date of Patent: April 13, 2021
    Assignee: BRAINLAB AG
    Inventors: Andreas Blumhofer, Jens Schmaler
  • Patent number: 10974537
    Abstract: A method for identifying a certification includes: determining a target verification mode for verifying a certificate, wherein the target verification mode comprises one or more pieces of movement information of movements performed by a designated body part with respect to the certificate, and the one or more pieces of movement information include information of holding the certificate in one or more designated holding postures; obtaining one or more images of the certificate; verifying whether a first image of the one or more images of the certificate comprises the designated body part; in response to that the first image comprises the designated body part, analyzing, whether the first image comprises the one or more pieces of movement information to generate an analysis result; and determining, based on the analysis result, whether the certificate is a forged certificate.
    Type: Grant
    Filed: May 20, 2020
    Date of Patent: April 13, 2021
    Inventors: Wei Xu, Jidong Chen
  • Patent number: 10970533
    Abstract: Embodiments for finding elements in optical character recognition (OCR) documents are provided. An indication of a selected portion of document is received. Salient pixels in the selected portion of the document are determined. Properties of the salient pixels in the selected portion of the document are identified. The properties of the salient pixels in the selected portion of the document are compared to properties of pixels in each of a plurality of portions of an OCR-converted version of the document. A cognitive analysis is utilized to select at least some of the plurality of portions of the OCR-converted version of the document as suspected matches to the selected portion of the document.
    Type: Grant
    Filed: July 2, 2019
    Date of Patent: April 6, 2021
    Inventors: Christopher Phipps, Edward Katz, Charles Beller
  • Patent number: 10963675
    Abstract: Technologies are provided herein for selecting one or more subimages to be processed from a plurality of images received. A subset of images is identified, from the plurality of images received, that include a face image. The face image is assessed to generate assessment information regarding one or more of a size of the face image, a pose of the face in the face image, sharpness of the face image, and contrast quality of the face image. Each aspect of the assessment information is compared with corresponding criteria and, as a result of determining that the assessment information satisfies the criteria, facial recognition processing is performed on the face image.
    Type: Grant
    Filed: January 30, 2019
    Date of Patent: March 30, 2021
    Assignee: REALNETWORKS, INC.
    Inventor: Milko Boic