Patents Examined by Andrew W. Johns
  • Patent number: 11029699
    Abstract: Systems and methods are provided for navigating an autonomous vehicle. In one implementation, a system for navigating a vehicle includes at least one processing device programmed to receive, from an image capture device, a plurality of images associated with an environment of the vehicle, analyze at least one of the plurality of images to identify a navigable region in the environment of the vehicle, identify, based on the at least one of the plurality of images, at least one barrier associated with an edge of the navigable region, and determine a type of the at least one barrier. The at least one processing device is also programmed to determine a navigational path of the vehicle based on the determined type of the at least one barrier, and cause the vehicle to travel on at least a portion of the determined navigational path.
    Type: Grant
    Filed: April 30, 2020
    Date of Patent: June 8, 2021
    Assignee: MOBILEYE VISION TECHNOLOGIES LTD.
    Inventor: Barak Cohen
  • Patent number: 11024001
    Abstract: A system and methods for attaining optimal precision digital image stereoscopic direction and ranging through air and across a refractive boundary separating air from a liquid or plasma using stereo-cameras, and employing a minimum variance sub-pixel registration method for determining precise estimates of the parallax angle between left and right stereo images. The system and methods can also track measurement and estimation variances as they propagate through the system in order to provide a comprehensive precision analysis of all estimated quantities.
    Type: Grant
    Filed: December 16, 2018
    Date of Patent: June 1, 2021
    Inventor: Sadiki Pili Fleming-Mwanyoha
  • Patent number: 11024045
    Abstract: Embodiments of the present disclosure provide a method and an apparatus for generating three-dimensional data, a device, and a storage medium. The method comprises: obtaining a profile information annotation result for a target object in a two-dimensional image; calculating depth of field of the target object and a three-dimensional orientation of the target object according to the profile information annotation result and a standard three-dimensional size of the target object; determining a three-dimensional coordinate of a reference two-dimensional image point in the target object according to a two-dimensional coordinate of the reference two-dimensional image point in the two-dimensional image and the depth of field; and generating three-dimensional data matching the target object according to the three-dimensional coordinate of the reference two-dimensional image point and the three-dimensional orientation of the target object.
    Type: Grant
    Filed: September 5, 2019
    Date of Patent: June 1, 2021
    Assignee: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.
    Inventors: Yucheng Wang, Xun Sun, Tian Xia
  • Patent number: 11023708
    Abstract: A computer-implemented method for determining whether images of faces contained in a document correspond to each other. The method comprises acquiring image data pertaining to the document and performing facial detection on the image data to detect one or more facial representations existing within the document. If two or more facial representations are detected, a first facial representation and a second facial representation are selected, and determination of whether the image of a face of the first facial representation corresponds to the image of a face of the second facial representation is performed.
    Type: Grant
    Filed: June 21, 2019
    Date of Patent: June 1, 2021
    Inventors: Christos Sagonas, Joao Silva Gomes, Jacques Cali
  • Patent number: 11022539
    Abstract: The current invention relates to the task of masking, i.e. determination of boundaries in an image of biological particles and/or elements or parts of biological particles in image cytometry. Methods for masking of a biological particle or element or region of a biological particle in a sample are provided which include staining a first element or region of the biological particle with a first fluorescent dye, staining a second element or region of the biological particle with a second fluorescent dye, recording an image of the fluorescent light signal emitted from the sample, and determining boundaries of the biological particle or element or region of the biological particle based on the fluorescent light signal in the image.
    Type: Grant
    Filed: January 22, 2018
    Date of Patent: June 1, 2021
    Assignee: ChemoMetec A/S
    Inventors: Rune Troelsgaard Pedersen, Søren Kjærulff
  • Patent number: 11022320
    Abstract: The invention relates to a method for calculating three-dimensional information of food received within a cavity of a food preparation entity, the method comprising the steps of: capturing at least one image of said food received within the cavity by a plenoptic camera, said image comprising information regarding the light intensity and the direction of light rays traveling in space; or capturing at least two images of said food received within the cavity, said images being taken from different positions during movement of a camera; or capturing at least two images of said food received within the cavity using a camera, said images comprising different focus points; and processing the at least one image in order to establish three-dimensional information of said food received within the cavity.
    Type: Grant
    Filed: January 8, 2018
    Date of Patent: June 1, 2021
    Assignee: Electrolux Appliances Aktiebolag
    Inventors: Christoph Luckhardt, Fabienne Reinhard-Herrscher
  • Patent number: 11007015
    Abstract: Provided are apparatus and methods for tracking a volume of interest in three dimensions in real time, using fewer than 6 DOF tracking information together with an external 6 DOE coordinate system. The apparatus and methods described herein provide more accurate, smaller, and less expensive tracking systems than prior approaches based on full 6 DOF tracking comprising translation and full orientation information. Embodiments may be used in applications such as surgical navigation, gaming, robotics, motion capture, and training.
    Type: Grant
    Filed: January 29, 2019
    Date of Patent: May 18, 2021
    Assignee: Queen's University at Kingston
    Inventors: Thomas Vaughan, Andras Lasso, Gabor Fichtinger, Tamas Ungi
  • Patent number: 11010641
    Abstract: A mobile computing device receives an image from a camera physically located within a vehicle. The mobile computing device inputs the image into a convolutional model that generates a set of object detections and a set of segmented environment blocks in the image. The convolutional model includes subsets of encoding and decoding layers, as well as parameters associated with the layers. The convolutional model relates the image and parameters to the sets of object detections and segmented environment blocks. A server that stores object detections and segmented environment blocks is updated with the sets of object detections and segmented environment blocks detected in the image.
    Type: Grant
    Filed: March 14, 2019
    Date of Patent: May 18, 2021
    Assignee: Mapbox, Inc.
    Inventor: Aleksandr Buslaev
  • Patent number: 11010640
    Abstract: A system for updating training data includes an interface and a processor. The interface is configured to receive a set of vehicle data. The set of vehicle data includes images and assigned labels associated with the images. The processor is configured to determine a set of training data and a set of test data from the set of vehicle data; train a model with the set of training data; determine a set of predicted labels for the set of vehicle data using the model; identify a set of potential mislabeled data using the set of predicted labels and the assigned labels; and determine an updated set of training data by relabeling the set of potential mislabeled data and replacing the set of potential mislabeled data with a relabeled set of data.
    Type: Grant
    Filed: June 24, 2019
    Date of Patent: May 18, 2021
    Assignee: Lytx, Inc.
    Inventor: Jesse Daniels
  • Patent number: 11003953
    Abstract: A method for converting images to a unified image format for artificial intelligence deep training comprises acquiring a plurality of images and annotating the plurality of images. An annotation site of the plurality of images is determined to be quadrilateral or polygonal. The format of the annotated images is converted according to a first conversion rule when the annotation site of the annotated training images or the annotated verification images is found to be quadrilateral and the format of the annotated images is converted according to a second conversion rule when the annotation site of the annotated training images or the annotated verification images is found to be not a quadrilateral. A device employing the method is also disclosed.
    Type: Grant
    Filed: August 7, 2019
    Date of Patent: May 11, 2021
    Assignees: HONG FU JIN PRECISION INDUSTRY (WuHan) CO., LTD., HON HAI PRECISION INDUSTRY CO., LTD.
    Inventor: Po-Chang Hu
  • Patent number: 11004023
    Abstract: A video training system is described for making short training videos available to employees at their work locations which are simple to operate. It employs several inexpensive video cards each which are loaded with several training videos that redistributed to users at their work locations. A training status device keeps track of which training videos are on which video cards. A tracking base tracks the locations of each video card. Each card has biometrics for identifying the user using each video card. Training status device receives the identity of the current user, checks to see which training videos that current user must view, but did not already view and provides this information to a logic device. Logic device receives the current location of the video cards having the training videos and notifies the current user where to find the video cards.
    Type: Grant
    Filed: May 23, 2018
    Date of Patent: May 11, 2021
    Assignee: Walmart Apollo, LLC
    Inventors: Yurgis Mauro Bacallao, Jaclyn Moreda
  • Patent number: 11003963
    Abstract: A monitoring system assesses the position of at least one target within an area. The monitoring system comprises a processing unit adapted to receive, from a camera, at least a frame depicting a scene of the area. The frames generated by the camera have a first resolution. The processing unit comprises: a database module storing, for each at least one target, a corresponding reference image, each reference image having a second resolution lower than the first resolution; a segmentation module configured to segment a received frame into frame segments, each frame segment having a resolution corresponding to the second resolution; a search module configured to implement a visual search procedure between each frame segment and a reference image comprising a depiction of the at least one target; and a position and translation module for calculating the position of the at least one target within the received frame.
    Type: Grant
    Filed: December 27, 2016
    Date of Patent: May 11, 2021
    Assignee: Telecom Italia S.p.A.
    Inventors: Gianluca Francini, Fabrizio Moggio, Nicola Reale, Andrea Varesio, Marco Vecchietti
  • Patent number: 11004191
    Abstract: An image recognition processor for an industrial device, the image recognition processor implementing, on an integrated circuit thereof, the functions of storing an image data processing algorithm, which has been determined based on prior learning; acquiring image data of an image including a predetermined pattern; and performing recognition processing on the image data based on the image data processing algorithm to output identification information for identifying a recognized pattern.
    Type: Grant
    Filed: June 14, 2019
    Date of Patent: May 11, 2021
    Assignee: KABUSHIKI KAISHA YASKAWA DENKI
    Inventor: Masaru Adachi
  • Patent number: 11004235
    Abstract: Embodiments of the present disclosure provide a method and apparatus for determining position and orientation of a bucket of an excavator, an electronic device and a computer readable medium. The method may include: acquiring an image of a bucket of an excavator collected by a camera provided on an excavator body, the image of the bucket including a preset marker provided on the bucket; determining position and orientation information of the camera relative to the bucket on the basis of the image of the bucket and pre-acquired three-dimensional feature information of the preset marker; and converting the position and orientation information of the camera relative to the bucket into position and orientation information of the bucket relative to the excavator body.
    Type: Grant
    Filed: November 6, 2019
    Date of Patent: May 11, 2021
    Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.
    Inventors: Xinjing Cheng, Ruigang Yang, Feixiang Lu, Yajue Yang, Hao Xu
  • Patent number: 10999534
    Abstract: Systems and methods provide for optimizing video review using motion recap images. A video review system can identify background image data of a video clip including an amount of motion satisfying a motion threshold. The video review system can generate foreground mask data segmenting foreground image data, representing a moving object in the video clip, from the background image data. The video review system can select a set of instances of the moving object represented in the foreground image data. The video review system can generate a motion recap image by superimposing the set of instances of the moving object represented in the foreground image data onto the background data.
    Type: Grant
    Filed: May 8, 2019
    Date of Patent: May 4, 2021
    Assignee: CISCO TECHNOLOGY, INC.
    Inventor: Nathaniel Webster Storer
  • Patent number: 10997722
    Abstract: A method for identifying a body motion includes receiving a series of images including a visual presentation of a human face from the image capture device. The series of images may form an image sequence. Each of the series of images may have a previous image or a next image in the image sequence. The method also includes, for each of the series of images, determining a plurality of characteristic points on the human face, determining positions of the plurality of characteristic points on the human face, and determining an asymmetry value based on the positions of the plurality of characteristic points. The method further includes identifying a head-shaking movement of the human face based on the asymmetry values of the series of images.
    Type: Grant
    Filed: August 3, 2020
    Date of Patent: May 4, 2021
    Assignee: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventor: Xiubao Zhang
  • Patent number: 10991064
    Abstract: A system for protecting a proprietary medium is provided, the system comprising a processor and a memory having instructions stored thereon that when executed by the processor cause the processor to: identify at least one first feature of interest in an original digital image; generate a watermarked copy of the original image and generate a masked copy of the original image in which the first feature of interest is masked; combine the watermarked copy with the masked copy to provide a modified watermarked copy having a region of lower intensity watermarking corresponding to the location of the first feature of interest in the original digital image; and overlay the modified watermarked copy over the original image to provide a final copy in which the regions of lower intensity watermarking are aligned with the first feature of interest.
    Type: Grant
    Filed: March 7, 2019
    Date of Patent: April 27, 2021
    Assignee: Adventure Soup Inc.
    Inventors: Keith Emery Belovay, Neal Hugh Belovay
  • Patent number: 10990923
    Abstract: Objects in a facility, such as users or totes, may be tracked as the object moves within the facility. An object representation of the object may be detected using image data. Apparent motion of the object representation may also be detected based on changes within the image data over time, which can help determine movement data for the object representation. However, the identity of the object representation may not be known. Using data from motion sensors in a device, movement data for the device can be generated. Thereafter, the movement data determined using the image data and the movement data determined using the data from the motion sensors in the device are compared for a possible match. If a match is found, an identifier of the device may then be associated with the object representation in the image data for tracking purposes.
    Type: Grant
    Filed: December 19, 2019
    Date of Patent: April 27, 2021
    Assignee: AMAZON TECHNOLOGIES, INC.
    Inventors: Somasundaram Niranjayan, Nathan Pius O'Neill
  • Patent number: 10984250
    Abstract: The present disclosure provides a method for managing an article storage. The method includes recognizing user identity information, and associating the user identity information with a user identifier. The method includes obtaining first information on taking an article by a user, which includes an article identifier of the article, the user identifier of the user, an identifier of a location where the article is taken, and information on an action of taking the article by the user. The method includes obtaining second information on placing the article by the user, which includes the article identifier of the article, the user identifier of the user, an identifier of a location where the article is placed, and information on an action of placing the article by the user. The method includes classifying the action of placing the article by the user based on the first information and the second information.
    Type: Grant
    Filed: January 30, 2019
    Date of Patent: April 20, 2021
    Assignee: BOE TECHNOLOGY GROUP CO., LTD.
    Inventors: Naifu Wu, Xitong Ma, Hongtao Guan
  • Patent number: 10981597
    Abstract: The purpose of the present invention is to perform mirror control as driving control when recognizing a mirror in front of the vehicle. By adopting this configuration, it is possible to perform appropriate driving control for automated driving. Another purpose of the present invention is to perform mirror processing as recognition processing when recognizing a mirror in front of a vehicle. By adopting this configuration it is possible to perform appropriate recognition processing in automated driving.
    Type: Grant
    Filed: December 16, 2016
    Date of Patent: April 20, 2021
    Assignee: Honda Motor Co., Ltd.
    Inventors: Yugo Ueda, Maiko Adachi