Patents by Inventor Gary R. Bradski

Gary R. Bradski has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 10275902
    Abstract: A user identification system includes an image recognition network to analyze image data and generate shape data based on the image data. The system also includes a generalist network to analyze the shape data and generate general category data based on the shape data. The system further includes a specialist network to compare the general category data with a characteristic to generate narrow category data. Moreover, the system includes a classifier layer including a plurality of nodes to represent a classification decision based on the narrow category data.
    Type: Grant
    Filed: May 9, 2016
    Date of Patent: April 30, 2019
    Assignee: MAGIC LEAP, INC.
    Inventor: Gary R. Bradski
  • Publication number: 20190094981
    Abstract: Configurations are disclosed for presenting virtual reality and augmented reality experiences to users. The system may comprise an image capturing device to capture one or more images, the one or more images corresponding to a field of the view of a user of a head-mounted augmented reality device, and a processor communicatively coupled to the image capturing device to extract a set of map points from the set of images, to identify a set of sparse points and a set of dense points from the extracted set of map points, and to perform a normalization on the set of map points.
    Type: Application
    Filed: November 26, 2018
    Publication date: March 28, 2019
    Applicant: MAGIC LEAP, INC.
    Inventors: Gary R. Bradski, Samuel A. Miller, Rony Abovitz
  • Patent number: 10203762
    Abstract: Configurations are disclosed for presenting virtual reality and augmented reality experiences to users. The system may comprise an image capturing device to capture one or more images, the one or more images corresponding to a field of the view of a user of a head-mounted augmented reality device, and a processor communicatively coupled to the image capturing device to extract a set of map points from the set of images, to identify a set of sparse points and a set of dense points from the extracted set of map points, and to perform a normalization on the set of map points.
    Type: Grant
    Filed: June 13, 2015
    Date of Patent: February 12, 2019
    Assignee: MAGIC LEAP, INC.
    Inventors: Gary R. Bradski, Samuel A. Miller, Rony Abovitz
  • Patent number: 9990777
    Abstract: An augmented reality display device comprises a housing for one or more components for the augmented reality display device, wherein the one or more components comprises a plurality of sensors to capture information pertaining to the user's surroundings, and wherein at least one sensor of the plurality of sensors is an image-based sensor, a processing module communicatively coupled to the housing to process a set of data retrieved from the plurality of sensors, wherein the processing module comprises a gating mechanism that selectively allows data to be uploaded to the cloud, and a detachable camera removably attached to a housing of the augmented reality display device, such that when the detachable camera is attached to the housing of the augmented reality display device, the gating mechanism is opened such that data retrieved from the detachable camera is uploaded to the cloud.
    Type: Grant
    Filed: May 14, 2016
    Date of Patent: June 5, 2018
    Assignee: MAGIC LEAP, INC.
    Inventor: Gary R. Bradski
  • Patent number: 9874749
    Abstract: Configurations are disclosed for presenting virtual reality and augmented reality experiences to users. The system may comprise a vision system having one or more optical elements to project one or more images to a user, a mapping database comprising map data corresponding to one or more real objects of the world, wherein the mapping database receives inputs from at least a component of one or more wearable augmented reality display systems, and a processor communicatively coupled to the mapping database for retrieving the map data and processing the retrieved map data to determine one or more output parameters, wherein the processor further controls the vision system in a manner such that the one or more images are projected to the user based at least in part on the determined output parameters.
    Type: Grant
    Filed: March 7, 2015
    Date of Patent: January 23, 2018
    Assignee: MAGIC LEAP, INC.
    Inventors: Gary R. Bradski, Brian Schowengerdt, Samuel A. Miller
  • Publication number: 20160358181
    Abstract: A method of conducting a transaction through an augmented reality display device comprises capturing biometric data from a user, determining, based at least in part on the captured biometric data, an identity of the user, and authenticating the user for the transaction based on the determined identity.
    Type: Application
    Filed: May 14, 2016
    Publication date: December 8, 2016
    Applicant: Magic Leap, Inc.
    Inventor: Gary R. Bradski
  • Publication number: 20160335512
    Abstract: A user identification system includes an image recognition network to analyze image data and generate shape data based on the image data. The system also includes a generalist network to analyze the shape data and generate general category data based on the shape data. The system further includes a specialist network to compare the general category data with a characteristic to generate narrow category data. Moreover, the system includes a classifier layer including a plurality of nodes to represent a classification decision based on the narrow category data.
    Type: Application
    Filed: May 9, 2016
    Publication date: November 17, 2016
    Inventor: Gary R. Bradski
  • Publication number: 20160335802
    Abstract: An augmented reality display device comprises a housing for one or more components for the augmented reality display device, wherein the one or more components comprises a plurality of sensors to capture information pertaining to the user's surroundings, and wherein at least one sensor of the plurality of sensors is an image-based sensor, a processing module communicatively coupled to the housing to process a set of data retrieved from the plurality of sensors, wherein the processing module comprises a gating mechanism that selectively allows data to be uploaded to the cloud, and a detachable camera removably attached to a housing of the augmented reality display device, such that when the detachable camera is attached to the housing of the augmented reality display device, the gating mechanism is opened such that data retrieved from the detachable camera is uploaded to the cloud.
    Type: Application
    Filed: May 14, 2016
    Publication date: November 17, 2016
    Applicant: Magic Leap, Inc.
    Inventor: Gary R. Bradski
  • Publication number: 20160026253
    Abstract: Configurations are disclosed for presenting virtual reality and augmented reality experiences to users. The system may comprise an image capturing device to capture one or more images, the one or more images corresponding to a field of the view of a user of a head-mounted augmented reality device, and a processor communicatively coupled to the image capturing device to extract a set of map points from the set of images, to identify a set of sparse points and a set of dense points from the extracted set of map points, and to perform a normalization on the set of map points.
    Type: Application
    Filed: June 13, 2015
    Publication date: January 28, 2016
    Applicant: MAGIC LEAP, INC.
    Inventors: Gary R. Bradski, Samuel A. Miller, Rony Abovitz
  • Publication number: 20150178939
    Abstract: Configurations are disclosed for presenting virtual reality and augmented reality experiences to users. The system may comprise a vision system having one or more optical elements to project one or more images to a user, a mapping database comprising map data corresponding to one or more real objects of the world, wherein the mapping database receives inputs from at least a component of one or more wearable augmented reality display systems, and a processor communicatively coupled to the mapping database for retrieving the map data and processing the retrieved map data to determine one or more output parameters, wherein the processor further controls the vision system in a manner such that the one or more images are projected to the user based at least in part on the determined output parameters.
    Type: Application
    Filed: March 7, 2015
    Publication date: June 25, 2015
    Applicant: Magic Leap, Inc.
    Inventors: Gary R. Bradski, Brian Schowengerdt, Samuel A. Miller
  • Patent number: 8615478
    Abstract: A non-binary affinity measure between any two data points for a supervised classifier may be determined. For example, affinity measures may be determined for tree, kernel-based, nearest neighbor-based and neural network supervised classifiers. By providing non-binary affinity measures using supervised classifiers, more information may be provided for clustering, analyzing and, particularly, for visualizing the results of data mining.
    Type: Grant
    Filed: January 3, 2012
    Date of Patent: December 24, 2013
    Assignee: Intel Corporation
    Inventor: Gary R. Bradski
  • Publication number: 20120109865
    Abstract: A non-binary affinity measure between any two data points for a supervised classifier may be determined. For example, affinity measures may be determined for tree, kernel-based, nearest neighbor-based and neural network supervised classifiers. By providing non-binary affinity measures using supervised classifiers, more information may be provided for clustering, analyzing and, particularly, for visualizing the results of data mining.
    Type: Application
    Filed: January 3, 2012
    Publication date: May 3, 2012
    Inventor: Gary R. Bradski
  • Patent number: 8117143
    Abstract: A non-binary affinity measure between any two data points for a supervised classifier may be determined. For example, affinity measures may be determined for tree, kernel-based, nearest neighbor-based and neural network supervised classifiers. By providing non-binary affinity measures using supervised classifiers, more information may be provided for clustering, analyzing and, particularly, for visualizing the results of data mining.
    Type: Grant
    Filed: May 28, 2004
    Date of Patent: February 14, 2012
    Assignee: Intel Corporation
    Inventor: Gary R. Bradski
  • Patent number: 7644049
    Abstract: For a first feature of a dataset having a plurality of features, training a classifier to predict the first feature in terms of other features in the data set to obtain a trained classifier; scrambling the values of a second feature in the data set to obtain a scrambled data set, executing the trained classifier on the scrambled data set, determining predictive importance of the seconds feature in predicting the first feature based at least in part on the accuracy of the trained classifier in predicting the first feature when executed with the scrambled data set and creating a graph of the data set in which each of the first and the second features is a node of the graph and a label on an edge between the first node and the second node is based at least in part on the predictive importance of the first feature in terms of the second feature.
    Type: Grant
    Filed: November 19, 2004
    Date of Patent: January 5, 2010
    Assignee: Intel Corporation
    Inventor: Gary R. Bradski
  • Patent number: 7590291
    Abstract: In one embodiment, the present invention includes a method of forming windows corresponding to a data point of a data set, successively expanding the windows, determining a local hill for the windows, re-centering the windows on the local hill, and merging any of the windows within a selected distance of each other. The windows formed may be substantially the same size as a single data point, in one embodiment. The merged windows may be recorded as possible merge points of a hierarchical cluster formed from the data set. Other embodiments are described and claimed.
    Type: Grant
    Filed: December 6, 2004
    Date of Patent: September 15, 2009
    Assignee: Intel Corporation
    Inventor: Gary R. Bradski
  • Patent number: 7429996
    Abstract: An imaging system configured to take panoramic pictures is disclosed. In one embodiment, the imaging system includes a camera, range finder associated with the camera and configured to provide depth information for objects within a field of view of the camera; and a processor coupled to receive information from the camera and depth information from the range finder, and configured to unwrap pictures taken by the camera according to the depth information.
    Type: Grant
    Filed: July 16, 2002
    Date of Patent: September 30, 2008
    Assignee: Intel Corporation
    Inventor: Gary R. Bradski
  • Patent number: 7379560
    Abstract: Method and apparatus of the present invention include an image-capturing device coupled to a computer system. An image captured by the image-capturing device is analyzed using a face tracking technique to learn behaviors of the user. This may include determining if the user is paying attention. The attention may be toward a display of the computer system. When the user does not pay attention, power consumption of one or more components of the computer system is reduced.
    Type: Grant
    Filed: March 5, 2003
    Date of Patent: May 27, 2008
    Assignee: Intel Corporation
    Inventors: Gary R. Bradski, Aaron M. Tsirkel
  • Patent number: 7271795
    Abstract: The present invention relates to a simple to use intuitive interface for mobile devices and, in particular, to a method and apparatus to permit the motion of a mobile device to serve as an input to the mobile device. In various embodiments, the relative and/or absolute motion, distance and/or acceleration for instance, of the mobile device may be mapped to correspond to particular commands. In one embodiment, this permits the display screen of the mobile device to serve as a virtual window to view a large data set by modifying the view of the displayed data according to the motion of the mobile device. In another embodiment, the present invention allows the user to navigate a virtual space, displayed on the screen of the mobile device, by the motion of the mobile device in real space. Additionally, the user may also control the different displayed views of virtual objects by the relative and/or absolute motion of the mobile device.
    Type: Grant
    Filed: June 30, 2003
    Date of Patent: September 18, 2007
    Assignee: Intel Corporation
    Inventor: Gary R. Bradski
  • Patent number: 7272583
    Abstract: In one embodiment, a method includes converting unsupervised data into supervised data using multiple processes and training multiple supervised classifiers with the supervised data of the processes. In such manner, supervised classifiers may be used to classify unsupervised data. Affinity measures may be determined and data clustered using the resulting trained classifiers. Other embodiments are described and claimed.
    Type: Grant
    Filed: December 6, 2004
    Date of Patent: September 18, 2007
    Assignee: Intel Corporation
    Inventor: Gary R. Bradski
  • Patent number: 7246100
    Abstract: In one embodiment, the present invention includes a method of successively splitting an analog function into high and low ranges and calculating a binary mask for these ranges to obtain a plurality of data regions at a plurality of split levels, and training binary classifiers on the plurality of data regions of at least one of the split levels. In such manner, binary classifiers may be used to classify an analog function. Other embodiments are described and claimed.
    Type: Grant
    Filed: December 6, 2004
    Date of Patent: July 17, 2007
    Assignee: Intel Corporation
    Inventor: Gary R. Bradski