Patents Examined by Carol Wang
  • Patent number: 10482609
    Abstract: A generative adversarial network (GAN) system includes a generator sub-network configured to examine images of an object moving relative to a viewer of the object. The generator sub-network also is configured to generate one or more distribution-based images based on the images that were examined. The system also includes a discriminator sub-network configured to examine the one or more distribution-based images to determine whether the one or more distribution-based images accurately represent the object. A predicted optical flow of the object is represented by relative movement of the object as shown in the one or more distribution-based images.
    Type: Grant
    Filed: April 4, 2017
    Date of Patent: November 19, 2019
    Assignee: GENERAL ELECTRIC COMPANY
    Inventors: Ser Nam Lim, Mustafa Devrim Kaba, Mustafa Uzunbas, David Diwinsky
  • Patent number: 10475190
    Abstract: The present disclosure describes a method of foreground segmentation and nucleus ranking for scoring dual ISH images. The method has been developed to better identify those nuclei, within a selected field of view, that meet the criteria for dual ISH scoring.
    Type: Grant
    Filed: July 25, 2017
    Date of Patent: November 12, 2019
    Assignee: VENTANA MEDICAL SYSTEMS, INC.
    Inventors: Anindya Sarkar, Jim Martin
  • Patent number: 10474893
    Abstract: An electronic device, an iris recognition method and a non-volatile computer-readable medium are provided. A processor in the electronic device obtains a first and second iris images, and calculates a plurality of first and second feature mark boxes that are non-uniformly arranged according to the first and second iris images. The processor uses the first feature mark boxes to obtain a first and second image features from the first and second iris images respectively, and compares the first and second image features to obtain a first recognition result. The processor uses the second feature mark boxes to obtain a third and fourth image features from the second and first iris images respectively, and compares the third and fourth image features to obtain a second recognition result. The processor determines a similarity degree of the first and second iris images according to the first and second recognition results.
    Type: Grant
    Filed: April 24, 2018
    Date of Patent: November 12, 2019
    Assignee: Industrial Technology Research Institute
    Inventors: Wen-Hung Ting, Hian-Kun Tenn, Duan-Li Liao, Chia-Chang Li, Po-Lung Chen
  • Patent number: 10473469
    Abstract: An industrial vehicle is provided comprising a drive mechanism, a steering mechanism, a vehicle controller, a camera, and a navigation module. The camera is communicatively coupled to the navigation module, the vehicle controller is responsive to commands from the navigation module, and the drive mechanism and the steering mechanism are responsive to commands from the vehicle controller. The camera is configured to capture an input image of a warehouse ceiling comprising elongated skylights characterized by different rates of image intensity change along longitudinal and transverse axial directions, and ceiling lights characterized by a circularly symmetric rate of image intensity change. The navigation module is configured to distinguish between the ceiling lights and the skylights and send commands to the vehicle controller for localization, or to navigate the industrial vehicle through the warehouse based upon valid ceiling light identification, valid skylight identification, or both.
    Type: Grant
    Filed: November 2, 2018
    Date of Patent: November 12, 2019
    Assignee: Crown Equipment Corporation
    Inventor: Mark Bell
  • Patent number: 10470510
    Abstract: Disclosed are systems and methods for full body measurements extraction using a mobile device camera.
    Type: Grant
    Filed: August 10, 2019
    Date of Patent: November 12, 2019
    Assignee: Bodygram, Inc.
    Inventors: Chong Jin Koh, Kyohei Kamiyama
  • Patent number: 10467745
    Abstract: In a preparation stage, an abnormality detection device detects a first characteristic amount from each first frame contained in video data and stores the first characteristic amount in a storage unit. In an abnormality detection stage, the abnormality detection device detects a second characteristic amount from each second frame contained in video data obtained by imaging a work operation of the robot and stores the first characteristic amount in the storage unit. The abnormality detection device compares the second characteristic mount of the second frame and the first characteristic amount of each of the first frames and specifies the first characteristic amount that is the closest to the second characteristic amount. The abnormality detection device determines whether the work operation of the robot in the abnormality detection stage is abnormal on the basis of the specified first characteristic amount and the second characteristic amount.
    Type: Grant
    Filed: May 15, 2017
    Date of Patent: November 5, 2019
    Assignee: FUJITSU LIMITED
    Inventors: Takashi Fuse, Tetsuo Koezuka
  • Patent number: 10460435
    Abstract: A pattern inspection method includes calculating a first coefficient of a filter function by using data of optical images of plural small regions selected and data of developed images of the plural small regions based on design data; calculating a second coefficient of a filter function by using data of an optical image of a reference small region selected and data of a developed image of the reference small region selected; and determining, for each pixel, whether there exists a pixel for which a difference, between a first temporary reference image to be compared with the optical image of the reference small region generated using the filter function in which the first coefficient is defined and a second temporary reference image to be compared with the optical image of the reference small region generated using the filter function in which the second coefficient is defined, is larger than a threshold.
    Type: Grant
    Filed: April 5, 2017
    Date of Patent: October 29, 2019
    Assignee: NuFlare Technology, Inc.
    Inventor: Takafumi Inoue
  • Patent number: 10460181
    Abstract: In order to process sensor data for a driver assistance system oriented towards the driver's comfort, sensor data that is sensed by a sensor device and describes objects is preprocessed such that a distinction is made between a driving zone and a non-driving zone, where the driving zone is designated as an object driving zone. The object driving zone is delimited by a boundary line. Since the sensor data is processed for a comfort-oriented driver assistance system, it does not have to describe the entire theoretical driving zone. Rather, the boundary line is used to delimit the driving zone within which the vehicle can normally be expected to drive. Based thereon, it is easy to determine an appropriate boundary line and significantly reduce the volume of data to be transmitted from the sensor device to a central control device of the comfort-oriented driver assistance system in order to describe the sensed objects.
    Type: Grant
    Filed: August 4, 2017
    Date of Patent: October 29, 2019
    Assignee: Bayerische Motoren Werke Aktiengesellschaft
    Inventor: Christoph Mayser
  • Patent number: 10452916
    Abstract: A marker tracking system configured to detect light patterns (e.g., infrared light patterns) generated by one or more markers is described. A given marker is configured with a code which identifies the marker in a motion tracking camera field of view. Motion tracking camera(s) record the emitted infrared light and are configured to directly, or in conjunction with an associated computing device, computationally distinguish a given marker with high accuracy and efficiently.
    Type: Grant
    Filed: September 20, 2018
    Date of Patent: October 22, 2019
    Assignee: WorldViz, Inc.
    Inventors: Andrew C. Beall, Matthias Pusch
  • Patent number: 10453189
    Abstract: There is provided a computer-implemented method for detecting and measuring stomata present in the epidermis of a plant leaf, the method comprising obtaining an image of the epidermis of a plant leaf; detecting valid stomata candidates within the image; determining physical dimensions of the valid stomata candidates; and determining vital functions of the plant based on the physical dimensions of the valid stomata candidates. There is also provided a computing device capable of measuring leaf stomata.
    Type: Grant
    Filed: December 15, 2015
    Date of Patent: October 22, 2019
    Assignee: UNITED ARAB EMIRATES UNIVERSITY
    Inventors: Falah Awwad, Synan Abuqamar, Taoufik Ksiksi, Saleh Thaker, Ayman Abdul Rahman Rabee
  • Patent number: 10453210
    Abstract: Provided is an apparatus and method for determining an interpupillary distance (IPD), the method and apparatus may determine the IPD of a user by analyzing an image of the user gazing at a display to which a predetermined pattern is output, wherein the image may be obtained by the apparatus for determining the IPD or may be received from an external terminal.
    Type: Grant
    Filed: December 21, 2016
    Date of Patent: October 22, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Hyoseok Hwang, Hyun Sung Chang, DongKyung Nam
  • Patent number: 10431107
    Abstract: A device for providing feedback includes an imaging device configured to capture an image of a subject, a feedback device, and a controller communicatively coupled to the imaging device and the feedback device. The controller includes at least one processor and at least one memory storing computer readable and executable instructions that, when executed by the processor, cause the controller to determine one or more identifying characteristics of the subject, set one or more parameters for determining a facial expression of the subject in the image based on the one or more identifying characteristics of the subject, determine the facial expression of the subject in the image based on the one or more parameters, and provide the feedback with the feedback device based on the determined facial expression.
    Type: Grant
    Filed: March 7, 2017
    Date of Patent: October 1, 2019
    Assignee: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.
    Inventor: Suhas E. Chelian
  • Patent number: 10426143
    Abstract: Systems and methods for object enumeration in a culture tank. The methods comprise: obtaining an array of two dimensional images of an illuminated scene in a culture tank; correcting non-uniform background illumination in the two dimensional images; improving a color contrast between a background and object edges shown in the two dimensional images; performing a defocus analysis using the two dimensional images to generate a focus map image; generating a modified focus map image by eliminating isolated spots shown in the focus map image and merging relatively small spots with adjacent relatively large objects in the focus map image; classifying each object shown in the modified focus map image as an object of interest or an object of no interest; and counting the number of objects classified as objects of interest.
    Type: Grant
    Filed: January 23, 2018
    Date of Patent: October 1, 2019
    Assignee: FLORIDA ATLANTIC UNIVERSITY BOARD OF TRUSTEES
    Inventors: Bing Ouyang, Paul S. Wills, Fraser Dalgleish, Anni Dalgleish
  • Patent number: 10424079
    Abstract: A trained feature network receives an image captured under low illumination conditions and pose data corresponding to the image. The trained feature network identifies a feature within the image and analyzes the image to extract feature information corresponding to the feature from the image. Based on the image and the pose data, geo-location information corresponding to the feature is determined. The geo-location information is appended to the extracted feature information. The feature information is stored as part of a feature map layer of a digital map. At least a portion of the digital map is provided to a routing and navigation system, for example, for performing vehicle localization under the particular condition.
    Type: Grant
    Filed: April 5, 2017
    Date of Patent: September 24, 2019
    Assignee: HERE GLOBAL B.V.
    Inventor: Anirudh Viswanathan
  • Patent number: 10410322
    Abstract: An image and/or temporal sequence of images is received. The image and/or sequence of images was captured by an image capturing device of a vehicle apparatus onboard a vehicle and was down-sampled thereby. A scale of the image(s) is determined. An up-sampling network receives the image(s) and the scale. The up-sampling network determines appropriate network weights based on the scale. Based on the appropriate network weights, the up-sampling network generates a higher resolution image having a pre-defined scale.
    Type: Grant
    Filed: April 5, 2017
    Date of Patent: September 10, 2019
    Assignee: HERE GLOBAL B.V.
    Inventors: Anirudh Viswanathan, Peter Christian
  • Patent number: 10401298
    Abstract: A system for quantitative detection and analysis of the interactions of molecules with molecular receptors on the surfaces of biological cells based on detecting a mechanical deformation in the membrane of a cell associated with the molecular interactions, which works for both large and small molecules. The mechanical deformation can be detected with high precision in real time from an optical image of the cell with a differential detection method. The system can be also used to detect the electrical activities, such as ion channel opening and closing, as well as action potential propagation in neuronal cells.
    Type: Grant
    Filed: January 23, 2018
    Date of Patent: September 3, 2019
    Assignee: ARIZONA BOARD OF REGENTS ON BEHALF OF ARIZONA STATE UNIVERSITY
    Inventors: Nongjian Tao, Yan Guan
  • Patent number: 10402998
    Abstract: A position estimation apparatus which estimates a position of a mobile object in a space includes: a measurement unit which measures, for each of points in a local space in proximity to the mobile object, a position and an attribute; an extractor which extracts position information and attribute information from a result of the measuring by the measurement unit, for each measurement voxel in a group of measurement voxels arrayed three-dimensionally in association with the local space; a map manager which manages position information and attribute information, for each map voxel in a group of map voxels arrayed three-dimensionally in association with the space represented by a map; and a position estimator which estimates a position of the mobile object, based on a position information approximation degree and an attribute information approximation degree.
    Type: Grant
    Filed: September 27, 2017
    Date of Patent: September 3, 2019
    Assignee: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.
    Inventor: Tomohide Ishigami
  • Patent number: 10397505
    Abstract: One embodiment provides a method, including: receiving a plurality of communication events associated with a pixel of an imaging device; identifying a frequency associated with the communication events, wherein the identifying a frequency comprises determining a number of communication events occurring within a predetermined time interval or determining a mean time interval between the communication events; determining, from a plurality of pixels neighboring the pixel, a frequency range comprising an upper frequency limit and a lower frequency limit; resolving, from the identified frequency and the determined frequency range, whether the pixel comprises a non-conforming pixel; and masking, if the pixel comprises a non-conforming pixel, subsequent communication events from the non-conforming pixel. Other aspects are described and claimed.
    Type: Grant
    Filed: March 8, 2019
    Date of Patent: August 27, 2019
    Assignee: KROMEK GROUP, PLC
    Inventors: Rolf Martin Clajus, Franklin Dean Walker, James William Hugg, Brian William Harris
  • Patent number: 10376165
    Abstract: Systems and methods are described for the compositing together of model-linked vascular data from a plurality of sources, including at least one 2-D angiography image, for display in a frame of reference of the at least one angiography image. In some embodiments, a linking model comprises a data structure configured to link locations of angiographic images to corresponding elements of non-image vascular parameter data. The linking data structure is traversed to obtain a mapping to the frame of reference of one or more of the angiographic images.
    Type: Grant
    Filed: March 2, 2018
    Date of Patent: August 13, 2019
    Assignee: Cathworks LTD
    Inventors: Ifat Lavi, Guy Lavi
  • Patent number: 10380755
    Abstract: A technique for estimating a whole object surface area and volume of a micro-scale three-dimensional model with a partially visible surface includes receiving a single-view stereoscopic image of an object of interest and an unconstrained three-dimensional point cloud of the object, generating a constrained three-dimensional point cloud using the image, the unconstrained three-dimensional point cloud, and a digital elevation model (DEM) of the object generated from the image, generating, using the constrained three-dimensional point cloud, a three-dimensional mesh representing an estimate of the surface of the object, calculating a partial surface area and/or partial volume of the object using the three-dimensional mesh, estimating an extent of a visible surface of the object, and calculating a whole surface area and/or a whole volume of the object based on the partial surface area of the object and the estimated extent of the visible surface of the object.
    Type: Grant
    Filed: November 21, 2017
    Date of Patent: August 13, 2019
    Assignee: University of New Hampshire
    Inventors: Gopal Mulukutla, Alexander Prusevich