Patents Examined by Jonathan S Lee
  • Patent number: 11068831
    Abstract: A motion pattern of a worker is evaluated in consideration of a proficiency level of the worker with respect to a work. A pattern acquisition unit (12) that acquires a motion pattern when a worker executes a work, an evaluation standard setting unit (15) that sets an evaluation standard for the motion pattern, and a pattern evaluation unit (18) that evaluates the motion pattern on the basis of the evaluation standard are provided, and the evaluation standard setting unit (18) sets the evaluation standard for the motion pattern when a certain worker executes certain work according to the number of times of execution of the certain work executed by the certain worker.
    Type: Grant
    Filed: January 26, 2017
    Date of Patent: July 20, 2021
    Assignee: Broadleaf Co., Ltd.
    Inventors: Takahide Arao, Akira Ooka
  • Patent number: 11068749
    Abstract: The present disclosure discloses a system and a method for translating, e.g., mapping, a Red-Clear-Clear-Clear (RCCC) image to a Red-Green-Blue (RGB) image. In an example implementation, the system and the method can receive, at a deep neural network, an image having a Red-Clear-Clear-Clear (RCCC) image pattern, wherein the deep neural network includes a generator and a discriminator; generate, at the generator, a Red-Green-Blue (RGB) image based on the image having the RCCC image pattern; determine, at the discriminator, whether the RGB image is machine-generated or is sourced from the real data distribution; and update at least one weight of the generator when the discriminator determines the RGB image is machine-generated.
    Type: Grant
    Filed: February 24, 2020
    Date of Patent: July 20, 2021
    Assignee: Ford Global Technologies, LLC
    Inventors: Akhil Perincherry, Kyoung Min Lee, Ishan Patel
  • Patent number: 11062417
    Abstract: Systems and methods for applying data optimization to images to meet a computer vision requirement are disclosed. According to an aspect, a method includes determining a computer vision requirement of a remote computing device. The method also includes determining, based on the computer vision requirement, a data optimization technique to apply to multiple images. Further, the method includes applying the data optimization technique to one or more of the images to generate data for communication. The method also includes communicating the data to the remote computing device.
    Type: Grant
    Filed: August 26, 2019
    Date of Patent: July 13, 2021
    Assignee: Lenovo Enterprise Solutions (Singapore) Pte. Ltd.
    Inventors: David Wayne Cosby, Jian Li, Jianbang Zhang
  • Patent number: 11062471
    Abstract: Stereo matching generates a disparity map indicating pixels offsets between matched points in a stereo image pair. A neural network may be used to generate disparity maps in real time by matching image features in stereo images using only 2D convolutions. The proposed method is faster than 3D convolution-based methods, with only a slight accuracy loss and higher generalization capability. A 3D efficient cost aggregation volume is generated by combining cost maps for each disparity level. Different disparity levels correspond to different amounts of shift between pixels in the left and right image pair. In general, each disparity level is inversely proportional to a different distance from the viewpoint.
    Type: Grant
    Filed: May 6, 2020
    Date of Patent: July 13, 2021
    Assignee: NVIDIA Corporation
    Inventors: Yiran Zhong, Wonmin Byeon, Charles Loop, Stanley Thomas Birchfield
  • Patent number: 11042990
    Abstract: Systems and techniques for automatic object replacement in an image include receiving an original image and a preferred image. The original image is automatically segmented into an original image foreground region and an original image object region. The preferred image is automatically segmented into a preferred image foreground region and a preferred image object region. A composite image is automatically composed by replacing the original image object region with the preferred image object region such that the composite image includes the original image foreground region and the preferred image object region. An attribute of the composite image is automatically adjusted.
    Type: Grant
    Filed: October 31, 2018
    Date of Patent: June 22, 2021
    Assignee: ADOBE INC.
    Inventors: I-Ming Pao, Sarah Aye Kong, Alan Lee Erickson, Kalyan Sunkavalli, Hyunghwan Byun
  • Patent number: 11042785
    Abstract: In various embodiments, training objects are classified by human annotators, psychometric data characterizing the annotation of the training objects is acquired, a human-weighted loss function based at least in part on the classification data and the psychometric data is computationally derived, and one or more features of a query object are computationally classifies based at least in part on the human-weighted loss function.
    Type: Grant
    Filed: April 7, 2020
    Date of Patent: June 22, 2021
    Assignee: PRESIDENT AND FELLOWS OF HARVARD COLLEGE
    Inventors: David Cox, Walter Scheirer, Samuel Anthony, Ken Nakayama
  • Patent number: 11037291
    Abstract: A system (100), method and computer program product for determining plant diseases. The system includes an interface module (110) configured to receive an image (10) of a plant, the image (10) including a visual representation (11) of at least one plant element (1). A color normalization module (120) is configured to apply a color constancy method to the received image (10) to generate a color-normalized image. An extractor module (130) is configured to extract one or more image portions (11e) from the color-normalized image wherein the extracted image portions (11e) correspond to the at least one plant element (1).
    Type: Grant
    Filed: April 19, 2017
    Date of Patent: June 15, 2021
    Assignee: BASF SE
    Inventors: Alexander Johannes, Till Eggers, Artzai Picon, Aitor Alvarez-Gila, Amaya Maria Ortiz Barredo, Ana Maria Diez-Navajas
  • Patent number: 11030755
    Abstract: Systems, methods, and computer-readable for multi-spatial scale object detection include generating one or more object trackers for tracking at least one object detected from on one or more images. One or more blobs are generated for the at least one object based on tracking motion associated with the at least one object. One or more tracklets are generated for the at least one object based on associating the one or more object trackers and the one or more blobs, the one or more tracklets including one or more scales of object tracking data for the at least one object. One or more uncertainty metrics are generated using the one or more object trackers and an embedding of the one or more tracklets. A training module for detecting and tracking the at least one object using the embedding and the one or more uncertainty metrics is generated using deep learning techniques.
    Type: Grant
    Filed: January 15, 2020
    Date of Patent: June 8, 2021
    Assignee: CISCO TECHNOLOGY, INC.
    Inventors: Hugo Mike Latapie, Franck Bachet, Enzo Fenoglio, Sawsen Rezig, Carlos M. Pignataro, Guillaume Sauvage De Saint Marc
  • Patent number: 11017501
    Abstract: A method is applied to an electronic device including a color camera and a monochrome camera, and the color camera and the monochrome camera are disposed in parallel on the electronic device, includes: obtaining a to-be-processed color image obtained after the color camera photographs a target scenario, and extracting a first luminance component of the to-be-processed color image; obtaining a monochrome image obtained after the monochrome camera collects the target scenario at the same moment, and extracting a second luminance component of the monochrome image; performing registration on the first luminance component and the second luminance component by using a preset algorithm, to generate a third luminance component; extracting a chrominance component of the to-be-processed color image based on the third luminance component; and compositing a color output image based on the extracted chrominance component of the to-be-processed color image and the third luminance component.
    Type: Grant
    Filed: December 28, 2016
    Date of Patent: May 25, 2021
    Assignee: Huawei Technologies Co., Ltd.
    Inventors: Gang Chen, Wei Luo
  • Patent number: 11017219
    Abstract: This invention relates to a method and a device for human body gender detection in a microwave image. The structure feature of a human body itself as well as the constructed vertical direction spatial distribution histogram and horizontal direction spatial distribution histogram are used to accurately locate the chest position and the crotch position of the human body. A human body chest subimage is extracted according to the chest position, and a human body crotch subimage is extracted according to the crotch position. Then, the feature values of the human body chest subimage and the human body crotch subimage are respectively extracted by a feature value extraction algorithm, and the human body gender is automatically identified according to the feature values. The technical solution of this invention is simple, and after experimental verification, can be effectively applied in actual microwave security check system.
    Type: Grant
    Filed: May 17, 2017
    Date of Patent: May 25, 2021
    Assignees: SHENZHEN VICTOOTH TERAHERTZ TECHNOLOGY CO., LTD, CHINA COMMUNICATION TECHNOLOGY CO., LTD
    Inventors: Chunchao Qi, Zhiquan Li, Hanjiang Chen, Guangsheng Wu, Shukai Zhao, Qing Ding
  • Patent number: 11013425
    Abstract: Systems and methods are disclosed for determining individual-specific blood flow characteristics. One method includes acquiring, for each of a plurality of individuals, individual-specific anatomic data and blood flow characteristics of at least part of the individual's vascular system; executing a machine learning algorithm on the individual-specific anatomic data and blood flow characteristics for each of the plurality of individuals; relating, based on the executed machine learning algorithm, each individual's individual-specific anatomic data to functional estimates of blood flow characteristics; acquiring, for an individual and individual-specific anatomic data of at least part of the individual's vascular system; and for at least one point in the individual's individual-specific anatomic data, determining a blood flow characteristic of the individual, using relations from the step of relating individual-specific anatomic data to functional estimates of blood flow characteristics.
    Type: Grant
    Filed: July 31, 2020
    Date of Patent: May 25, 2021
    Assignee: HeartFlow, Inc.
    Inventors: Timothy A. Fonte, Gilwoo Choi, Leo Grady, Michael Singer
  • Patent number: 11010926
    Abstract: Techniques and systems are described to recolor a group of images for color consistency. Techniques include extracting color palettes for images of the group of images and generating a group theme color palette based on the color palettes for the images. Image color palettes are then mapped to the group theme color palette and the images are modified in response to the mapping. In some examples, the mapping includes discouraging multiple colors of a single color palette from mapping to a single color of the group theme color palette. Additionally, or alternatively, the mapping includes discouraging a forced mapping of a dissimilar color of an image color palette from mapping to the group theme color palette.
    Type: Grant
    Filed: April 10, 2019
    Date of Patent: May 18, 2021
    Assignee: Adobe Inc.
    Inventors: Scott D. Cohen, Brian L. Price
  • Patent number: 11010596
    Abstract: An apparatus includes processor in communication with a memory and a communication interface. The processor is configured to receive, via a network and the communication interface, at least one image and to analyze the at least one image via facial recognition to define an analyzed data set. The processor is configured to (1) identify a user based on data included in user profile data structure, (2) identify a set of people connected to the user based on user connection data from at least one connection database, (3) compare the analyzed data set to facial image data of a person connected to the user, and (4) define a confidence level based on the comparison. When the confidence level satisfies a criterion, the processor can send to a client device a signal indicative of a notification that the person is within a predetermined proximity of the user.
    Type: Grant
    Filed: March 7, 2019
    Date of Patent: May 18, 2021
    Assignee: 15 SECONDS OF FAME, INC.
    Inventor: Gregg Donnenfeld
  • Patent number: 11003926
    Abstract: A method and an apparatus for recognizing a boundary of a traffic sign are provided. The method includes: acquiring at least one initial boundary point of a traffic sign in a to-be-processed image, the initial boundary point being used to mark a boundary of the traffic sign; dividing the to-be-processed image into at least one image segmentation area based on the at least one initial boundary point, the image segmentation area including at least one initial boundary point; importing, for an image segmentation area in the at least one image segmentation area, the image segmentation area into a pre-trained traffic sign boundary point recognition model to obtain an update boundary point corresponding to the image segmentation area; and determining a boundary point of the traffic sign based on all the update boundary point corresponding to the image segmentation area.
    Type: Grant
    Filed: December 13, 2019
    Date of Patent: May 11, 2021
    Assignee: Baidu Online Network Technology (Beijing) Co., Ltd.
    Inventor: Xu Duan
  • Patent number: 10997464
    Abstract: Digital image layout training is described using wireframe rendering within a generative adversarial network (GAN) system. A GAN system is employed to train the generator module to refine digital image layouts. To do so, a wireframe rendering discriminator module rasterizes a refined digital training digital image layout received from a generator module into a wireframe digital image layout. The wireframe digital image layout is then compared with at least one ground truth digital image layout using a loss function as part of machine learning by the wireframe discriminator module. The generator module is then trained by backpropagating a result of the comparison.
    Type: Grant
    Filed: November 9, 2018
    Date of Patent: May 4, 2021
    Assignee: Adobe Inc.
    Inventors: Jimei Yang, Jianming Zhang, Aaron Phillip Hertzmann, Jianan Li
  • Patent number: 10997435
    Abstract: In various examples, object fence corresponding to objects detected by an ego-vehicle may be used to determine overlap of the object fences with lanes on a driving surface. A lane mask may be generated corresponding to the lanes on the driving surface, and the object fences may be compared to the lanes of the lane mask to determine the overlap. Where an object fence is located in more than one lane, a boundary scoring approach may be used to determine a ratio of overlap of the boundary fence, and thus the object, with each of the lanes. The overlap with one or more lanes for each object may be used to determine lane assignments for the objects, and the lane assignments may be used by the ego-vehicle to determine a path or trajectory along the driving surface.
    Type: Grant
    Filed: August 8, 2019
    Date of Patent: May 4, 2021
    Assignee: NVIDIA Corporation
    Inventors: Josh Abbott, Miguel Sainz Serra, Zhaoting Ye, David Nister
  • Patent number: 10997434
    Abstract: A method for lane marker recognition includes: providing a filter bank with a plurality of different pairs of filters adapted to detect the left edge and the right edge of a specific type of a lane marker, respectively; receiving an image of a road; dividing the image of a road into a plurality of image segments, wherein each image segment includes at least one row of pixels of the image of a road; and for each of the image segments: applying a plurality of the pairs of filters of the filter bank to the image segment to generate a plurality of filter outputs; and determining which of the filter outputs correspond to a lane marker by using geo-metric information and appearance based information, wherein the geometric in-formation describes allowable dimensions of a determined lane marker, and the appearance based information describes allowable pixel values of a determined lane marker.
    Type: Grant
    Filed: April 2, 2019
    Date of Patent: May 4, 2021
    Assignee: Aptiv Technologies Limited
    Inventors: Jittu Kurian, Kun Zhao, Mirko Meuter
  • Patent number: 10993687
    Abstract: In hemodynamic determination in medical imaging, the classifier is trained from synthetic data rather than relying on training data from other patients. A computer model (in silico) may be perturbed in many different ways to generate many different examples. The flow is calculated for each resulting example. A bench model (in vitro) may similarly be altered in many different ways. The flow is measured for each resulting example. The machine-learnt classifier uses features from medical scan data for a particular patient to estimate the blood flow based on mapping of features to flow learned from the synthetic data. Perturbations or alterations may account for therapy so that the machine-trained classifier may estimate the results of therapeutically altering a patient-specific input feature. Uncertainty may be handled by training the classifier to predict a distribution of possibilities given uncertain input distribution.
    Type: Grant
    Filed: September 28, 2018
    Date of Patent: May 4, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Lucian Mihai Itu, Tiziano Passerini, Saikiran Rapaka, Puneet Sharma, Chris Schwemmer, Max Schoebinger, Thomas Redel, Dorin Comaniciu
  • Patent number: 10990780
    Abstract: A display device and an electronic device having the same including a display panel including a display area on which an image is displayed and a fingerprint scan area overlapped with the display area, and a fingerprint scan area compensator configured to convert a fingerprint scan image data provided to pixels included in the fingerprint scan area to a degradation compensating image data that compensates a degradation of the pixels included in the fingerprint scan area and output the degradation compensating image data in the fingerprint scan mode.
    Type: Grant
    Filed: June 13, 2018
    Date of Patent: April 27, 2021
    Assignee: Samsung Display Co., Ltd.
    Inventor: Hakgyu Kim
  • Patent number: 10984273
    Abstract: An attachable matter detection apparatus includes a controller configured to function as an extractor and a detector. The extractor extracts edge information of each pixel contained in a photographic image photographed by an imaging device. The detector detects a candidate area estimated to have a water droplet out of the photographic image based on a matching result between (i) each of the pixels converted into a predetermined data format based on the edge information extracted by the extractor and (ii) a template representing a water droplet and having the data format. The detector calculates a matching frequency with the template for a predetermined area along a contour of the candidate area, and excludes the candidate area when the candidate area satisfies a predetermined exclusion condition based on the matching frequency.
    Type: Grant
    Filed: November 14, 2019
    Date of Patent: April 20, 2021
    Assignee: DENSO TEN Limited
    Inventors: Nobuhisa Ikeda, Nobunori Asayama, Takashi Kono, Yasushi Tani, Daisuke Yamamoto, Tomokazu Oki, Teruhiko Kamibayashi