Patents Examined by Dwayne D. Bost
  • Patent number: 11010624
    Abstract: The traffic signal recognition device includes a traffic signal recognition unit configured to perform processing for recognizing the traffic signal based on the result of imaging performed by a camera, an external situation recognition unit configured to recognize a size and position of a surrounding vehicle, and a occluded situation determination unit configured to determine whether or not the area in front of a host vehicle is in the traffic signal occluded situation, in which the line of sight from the camera to the traffic signal is blocked by the surrounding vehicle. The traffic signal recognition unit is configured not to perform the processing for recognizing the traffic signal within a difficulty zone and not to perform the processing for recognizing the traffic signal if it is determined that the area in front of the host vehicle is in the traffic signal occluded situation.
    Type: Grant
    Filed: December 18, 2018
    Date of Patent: May 18, 2021
    Inventors: Yusuke Hayashi, Nobuhide Kamata
  • Patent number: 10977558
    Abstract: In a method and apparatus for training a computer system for use in classification of an image by processing image data representing the image, image data are compressed and then loaded into a programmable quantum annealing device that includes a Restricted Boltzmann Machine. The Restricted Boltzmann Machine is trained to act as a classifier of image data, thereby providing a trained Restricted Boltzmann Machine; and, the trained Restricted Boltzmann Machine is used to initialize a neural network for image classification thereby providing a trained computer system for use in classification of an image.
    Type: Grant
    Filed: February 1, 2019
    Date of Patent: April 13, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Mark Herbster, Peter Mountney, Sebastien Piat, Simone Severini
  • Patent number: 10977818
    Abstract: A method for deriving an image sensor's 3D pose estimate from a 2D scene image input includes at least one Machine Learning algorithm trained a priori to generate a 3D depth map estimate from the 2D image input, which is used in conjunction with physical attributes of the source imaging device to make an accurate estimate of the imaging device 3D location and orientation relative to the 3D content of the imaged scene. The system may optionally employ additional Machine Learning algorithms to recognize objects within the scene to further infer contextual information about the scene, such as the image sensor pose estimate relative to the floor plane or the gravity vector. The resultant refined imaging device localization data can be applied to static (picture) or dynamic (video), 2D or 3D images, and is useful in many applications, most specifically for the purposes of improving the realism and accuracy of primarily static, but also dynamic Augmented Reality (AR) applications.
    Type: Grant
    Filed: February 23, 2018
    Date of Patent: April 13, 2021
    Assignee: Manor Financial, Inc.
    Inventors: Taylor Clark, Andrew Kemendo, Mark Shanks
  • Patent number: 10957566
    Abstract: A system and method for wafer-level inspection using on-valve inspection detectors to detect defects on a semiconductor wafer surfaces during a semiconductor device manufacturing process is disclosed herein. In some exemplary embodiments, a method for wafer-level inspection includes: transporting a semiconductor wafer through a transfer port of a processing chamber; scanning a surface of the semiconductor wafer automatically using at least one on-valve inspection detector arranged on a vacuum valve providing access through the transfer port; generating at least one surface image of the surface of the semiconductor wafer; and analyzing the at least one surface image to detect defects on the surface of the semiconductor wafer.
    Type: Grant
    Filed: April 12, 2018
    Date of Patent: March 23, 2021
    Assignee: Taiwan Semiconductor Manufacturing Co., Ltd.
    Inventors: Mu-Lung Che, Fu Chiang Hsu
  • Patent number: 10949682
    Abstract: A method for ascertaining a piece of topological information of an intersection, including locating a vehicle with lane accuracy when negotiating the intersection; ascertaining data by the vehicle when negotiating the intersection; transmitting the data to a processing unit; and ascertaining a connectivity of lane-roadway combinations of the intersection from the data with the aid of the processing unit.
    Type: Grant
    Filed: February 26, 2019
    Date of Patent: March 16, 2021
    Assignee: Robert Bosch GmbH
    Inventor: Philip Wette
  • Patent number: 10921409
    Abstract: A magnetic resonance imaging apparatus according to an embodiment includes a display, an input interface, and processing circuitry. The display displays at least a locator image and a reference image. The input interface sets a region of interest on the locator image displayed on the display. The processing circuitry scans a subject to obtain three dimensional data, generates a locator image from the three dimensional data and displaying the locator image on the display, generates a reference image corresponding to the location of the region of interest from the three dimensional data and displaying the reference image on the display, and makes, when a size or position of the region of interest on one of the locator image and the reference image is changed by the input interface, adjustments to correspondingly change the display magnification or position of the other one of the locator image and the reference image.
    Type: Grant
    Filed: November 28, 2017
    Date of Patent: February 16, 2021
    Inventors: Ye Liu, Bin Fu, Bing Li, Jinbiao Zhang, Xiaofei Sun
  • Patent number: 10922801
    Abstract: Systems and methods for generating a binary image from a color image are disclosed. A method includes: acquiring a color image; generating a first grayscale image from a first color channel in the color image and a second grayscale image from a second color channel in the color image; and generating a binary image using at least the first grayscale image and the second grayscale image.
    Type: Grant
    Filed: July 19, 2017
    Date of Patent: February 16, 2021
    Assignee: Lockheed Martin Corporation
    Inventor: Chadwick M. Coleman
  • Patent number: 10909969
    Abstract: Domain-specific language understanding models that may be built, tested and improved quickly and efficiently are provided. Methods, systems and devices are provided that enable a developer to build user intent detection models, language entity extraction models, and language entity resolution models quickly and without specialized machine learning knowledge. These models may be built and implemented via single model systems that enable the models to be built in isolation or in an end-to-end pipeline system that enables the models to be built and improved in a simultaneous manner.
    Type: Grant
    Filed: September 25, 2019
    Date of Patent: February 2, 2021
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Jason Douglas Williams, Nobal Bikram Niraula, Pradeep Dasigi, Aparna Lakshmiratan, Geoffrey G. Zweig, Andrey Kolobov, Carlos Garcia Jurado Suarez, David Maxwell Chickering
  • Patent number: 10878268
    Abstract: In the case where a character on an object is read by using a mobile terminal having a camera function, an image suitable to OCR is acquired in a short time. An information processing apparatus including a camera, which acquires a moving image by capturing a character string on an object by the camera, sets, for each frame making up the acquired moving image, a search area for character recognition for each character making up the character string, detects a candidate character from the search area, determines whether an evaluation value indicating likelihood of the detected candidate character is stable, and outputs a frame of the acquired moving image in response to the evaluation value is determined to be stable.
    Type: Grant
    Filed: March 23, 2018
    Date of Patent: December 29, 2020
    Inventor: Katsuhiro Wada
  • Patent number: 10874361
    Abstract: Aspects of the invention are directed to systems and methods for generating spectral computed tomography data for spectral X-ray image reconstruction using of pixelated k-edge apertures. A method is provided for generating a spectral computed tomography. The method includes the steps of generating a plurality of X-ray beams; encoding the plurality of X-ray beams by transmitting the plurality of beams through a pixelated K-edge coded aperture structure; detecting the encoded plurality of X-ray beams; and reconstructing a spectral CT image from the encoded plurality of X-ray beams.
    Type: Grant
    Filed: December 11, 2018
    Date of Patent: December 29, 2020
    Assignee: University Of Delaware
    Inventors: Angela Cuadros, Gonzalo Arce
  • Patent number: 10867417
    Abstract: Systems, computer-implemented methods, and computer readable media for generating a synthetic image of an anatomical portion based on an origin image of the anatomical portion acquired by an imaging device using a first imaging modality are disclosed. These systems may be configured to receive the origin image of the anatomical portion acquired by the imaging device using the first imaging modality, receive a convolutional neural network model trained for predicting the synthetic image based on the origin image, and convert the origin image to the synthetic image through the convolutional neural network model. The synthetic image may resemble an imaging of the anatomical portion using a second imaging modality differing from the first imaging modality.
    Type: Grant
    Filed: July 14, 2017
    Date of Patent: December 15, 2020
    Assignee: Elekta, Inc.
    Inventor: Xiao Han
  • Patent number: 10861175
    Abstract: A comparator may automatically detect and quantify subtle and/or microscopic variance to a feature of a three-dimensional (ā€œ3Dā€) object in a reproducible manner based on point cloud imaging of that 3D object. The comparator may isolate a first set of data points, that represent the object feature at a first time, in a reference point cloud, and may isolate a second set of data points, that represent the same but altered object feature at a different second time, in a non-reference point cloud. The comparator may detect variance between positional values and visual characteristic values of the second set of data points and the corresponding positional values and visual characteristic values of the first set of data points, and may quantify a change occurring to the object feature between the first time and the second time based on a mapping of the variance to a particular unit of measure.
    Type: Grant
    Filed: May 29, 2020
    Date of Patent: December 8, 2020
    Assignee: Illuscio, Inc.
    Inventors: Robert Monaghan, Joseph Bogacz
  • Patent number: 10853925
    Abstract: Implementations of the disclosure provide for methods, systems, and machine-readable media for image processing. In some embodiments, a method for image processing includes: generating, by a processor, a first histogram and a first parameter set for a first image; constructing, by the processor, a model representative of a second histogram of a second image based on an adjustment parameter set and the first parameter set; generating the second histogram based on the model; and generating a second image based on the first image and the second histogram. In some embodiments, the first histogram is a two-dimensional histogram.
    Type: Grant
    Filed: August 2, 2018
    Date of Patent: December 1, 2020
    Inventors: Bin Xiao, Guoyin Wang, Weisheng Li
  • Patent number: 10853640
    Abstract: This disclosure relates generally to document processing, and more particularly to extracting information from hand-marked industrial inspection sheets. In an embodiment, the system performs localization of text as well as arrows in the inspection sheet, and identifies text that matches each arrow. Further by identifying machine zone each arrow is pointing to, the system assigns corresponding text to the appropriate machine zone; thus facilitating digitization of the inspection sheets.
    Type: Grant
    Filed: March 28, 2018
    Date of Patent: December 1, 2020
    Assignee: Tata Consultancy Services Limited
    Inventors: Gaurav Gupta, Swati, Monika Sharma, Lovekesh Vig
  • Patent number: 10846541
    Abstract: An electronic device is described. The electronic device includes a memory and a processor in communication with the memory. The memory is configured to store precalibration data for a camera mounted on a vehicle, the precalibration data including a camera height determined relative to a road plane the vehicle is configured to contact during operation. The processor is configured to receive a plurality of images. The processor is also configured to classify one or more features in the plurality of images as road features based on the precalibration data.
    Type: Grant
    Filed: June 21, 2017
    Date of Patent: November 24, 2020
    Assignee: QUALCOMM Incorporated
    Inventors: Avdhut Joshi, Arvind Ramanandan, Murali Chari
  • Patent number: 10839198
    Abstract: There are provided an object recognition unit of recognizing a target object in sequentially acquired images, a tracking unit of performing tracking on the sequentially acquired images for the recognized target object, and a storage controller of controlling so as to store in a first storage device the sequentially acquired images. The tracking unit further performs tracking for the target object on stored images, that are acquired before the target object is recognized by the object recognition unit in the sequentially acquired images, and are stored in the first storage device. The storage controller controls so as to store in a second storage device different from the first storage device, images in which the target object is tracked by the tracking unit of the sequentially acquired images, and images in which the target object is tracked by the tracking unit of the stored images.
    Type: Grant
    Filed: March 26, 2018
    Date of Patent: November 17, 2020
    Inventor: Daisuke Gunji
  • Patent number: 10832453
    Abstract: Systems and methods for providing clipping paths for variable data publishing are disclosed. A clipping path element is part of a graphic editor that allows a user to define a clipping path in any shape including non-rectangular shapes and shapes made with curved segments. The original graphic is preserved and the clipping frame defines the portion of the image that is displayed or printed. A plurality of clipping paths can be defined and stored to a library. Rules based on nonvariable or variable data publishing data may be used to retrieve the clipping paths from the library. A new document is composed and rendered that includes a clipping path applied to a portion of an image or the text.
    Type: Grant
    Filed: March 26, 2018
    Date of Patent: November 10, 2020
    Assignee: PTI Marketing Technologies Inc.
    Inventor: Douglas Neal Cogan
  • Patent number: 10825184
    Abstract: Embodiments of the present disclosure provide a maximum connected domain marking method, a target tracking method and an AR (Augmented Reality)/VR (Virtual Reality) apparatus, and relate to the field of image processing technology, and can obtain the maximum connected domain. A maximum connected domain marking method comprises: marking connected domains of pixels of a binary image and recording equivalent relationships; merging the equivalent connected domains according to the equivalent relationships, for pixels with the equivalent relationships in the marked results; counting the number of pixels in each merged connected domain; determining a connected domain label for the maximum connected domain according to the counted number of pixels in each connected domain; and determining coordinates of boundary pixels in the maximum connected domain based on the connected domain label.
    Type: Grant
    Filed: March 19, 2018
    Date of Patent: November 3, 2020
    Inventors: Zhenkun Song, Quan Yang, Hongzhen Xue
  • Patent number: 10810446
    Abstract: A method of detecting a frame line of a parking space from a captured image acquired by a camera includes detecting the frame line when the value of a parameter used for detection of the frame line falls within a first threshold range, estimating the position of an undetected frame line on the basis of the position of the detected frame line, and setting a threshold range used for detecting the frame line at the estimated position of the frame line to a second threshold range wider than the first threshold range.
    Type: Grant
    Filed: October 22, 2015
    Date of Patent: October 20, 2020
    Assignee: Nissan Motor Co., Ltd.
    Inventor: Yasuhisa Hayakawa
  • Patent number: 10810465
    Abstract: An auto-encoder is configured to verify character detection and/or classification results generated by an automated optical character recognition system. The auto-encoder may be trained to reconstruct visual representations of the detected character, and a determination of whether the character detection result comprises a true positive or false positive may be based on a reconstruction error between the image data in which the character was detected and a reconstructed image generated by the auto-encoder.
    Type: Grant
    Filed: July 1, 2018
    Date of Patent: October 20, 2020
    Assignee: DATALOGIC USA, INC.
    Inventors: Luis Goncalves, Mauro Belgiovine