Patents by Inventor Grace Vesom
Grace Vesom 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: 11775788Abstract: Systems and methods for registering arbitrary visual features for use as fiducial elements are disclosed. An example method includes aligning a geometric reference object and a visual feature and capturing an image of the reference object and feature. The method also includes identifying, in the image of the object and the visual feature, a set of at least four non-colinear feature points in the visual feature. The method also includes deriving, from the image, a coordinate system using the geometric object. The method also comprises providing a set of measures to each of the points in the set of at least four non-colinear feature points using the coordinate system. The measures can then be saved in a memory to represent the registered visual feature and serve as the basis for using the registered visual feature as a fiducial element.Type: GrantFiled: April 30, 2021Date of Patent: October 3, 2023Assignee: Matterport, Inc.Inventors: Gary Bradski, Gholamreza Amayeh, Mona Fathollahi, Ethan Rublee, Grace Vesom, William Nguyen
-
Patent number: 11503275Abstract: An improved method, system, and apparatus is provided to perform camera calibration, where cameras are mounted onto a moving conveyance apparatus to capture images of a multi-planar calibration target. The calibration process is optimized by reducing the number of images captured while simultaneously preserving overall information density.Type: GrantFiled: December 19, 2019Date of Patent: November 15, 2022Assignee: Magic Leap, Inc.Inventors: Jeffrey Steven Kranski, Frederick Dennis Zyda, Grace Vesom, Grace Shin-Yee Tsai, Jeremy A. Grata, Zhiheng Jia, Li Jiang
-
Publication number: 20220058414Abstract: Systems and methods for registering arbitrary visual features for use as fiducial elements are disclosed. An example method includes aligning a geometric reference object and a visual feature and capturing an image of the reference object and feature. The method also includes identifying, in the image of the object and the visual feature, a set of at least four non-colinear feature points in the visual feature. The method also includes deriving, from the image, a coordinate system using the geometric object. The method also comprises providing a set of measures to each of the points in the set of at least four non-colinear feature points using the coordinate system. The measures can then be saved in a memory to represent the registered visual feature and serve as the basis for using the registered visual feature as a fiducial element.Type: ApplicationFiled: April 30, 2021Publication date: February 24, 2022Applicant: Matterport, Inc.Inventors: Gary Bradski, Gholamreza Amayeh, Mona Fathollahi, Ethan Rublee, Grace Vesom, William Nguyen
-
Patent number: 11080884Abstract: A trained network for point tracking includes an input layer configured to receive an encoding of an image. The image is of a locale or object on which the network has been trained. The network also includes a set of internal weights which encode information associated with the locale or object, and a tracked point therein or thereon. The network also includes an output layer configured to provide an output based on the image as received at the input layer and the set of internal weights. The output layer includes a point tracking node that tracks the tracked point in the image. The point tracking node can track the point by generating coordinates for the tracked point in an input image of the locale or object. Methods of specifying and training the network using a three-dimensional model of the locale or object are also disclosed.Type: GrantFiled: May 15, 2019Date of Patent: August 3, 2021Assignee: Matterport, Inc.Inventors: Gary Bradski, Gholamreza Amayeh, Mona Fathollahi, Ethan Rublee, Grace Vesom, William Nguyen
-
Publication number: 20210215536Abstract: A method for characterizing a digital color camera includes, for each of three primary colors used in a field sequential color virtual image, determining a conversion model for each color using RGB values and the color-measurement values. For each primary color, the method includes illuminating a display device using an input light beam of a primary color having spectral properties representative of a light beam in a virtual image in a wearable device. The method includes capturing, with the digital color camera, an image of the display device, and determining, from the image, RGB values for each primary color. The method includes capturing, with a color-measurement device, a color-measurement value associated with each corresponding primary color at the display device, thereby acquiring a color-measurement value in an absolute color space. A conversion model for each color is determined using RGB values and the color-measurement values.Type: ApplicationFiled: January 21, 2021Publication date: July 15, 2021Applicant: Magic Leap, Inc.Inventors: Miller Harry Schuck, III, Lei Zhang, Etienne Gregoire Grossmann, Nukul Sanjay Shah, Ohad Zohar, Robert Zito, Nicholas Ihle Morley, Jason Schaefer, Zhiheng Jia, Eric C. Browy, Marshall Charles Capps, Kazunori Tanaka, Grace Vesom, John Monos
-
Patent number: 10997448Abstract: Systems and methods for registering arbitrary visual features for use as fiducial elements are disclosed. An example method includes aligning a geometric reference object and a visual feature and capturing an image of the reference object and feature. The method also includes identifying, in the image of the object and the visual feature, a set of at least four non-colinear feature points in the visual feature. The method also includes deriving, from the image, a coordinate system using the geometric object. The method also comprises providing a set of measures to each of the points in the set of at least four non-colinear feature points using the coordinate system. The measures can then be saved in a memory to represent the registered visual feature and serve as the basis for using the registered visual feature as a fiducial element.Type: GrantFiled: May 15, 2019Date of Patent: May 4, 2021Assignee: Matterport, Inc.Inventors: Gary Bradski, Gholamreza Amayeh, Mona Fathollahi, Ethan Rublee, Grace Vesom, William Nguyen
-
Publication number: 20200364895Abstract: A trained network for point tracking includes an input layer configured to receive an encoding of an image. The image is of a locale or object on which the network has been trained. The network also includes a set of internal weights which encode information associated with the locale or object, and a tracked point therein or thereon. The network also includes an output layer configured to provide an output based on the image as received at the input layer and the set of internal weights. The output layer includes a point tracking node that tracks the tracked point in the image. The point tracking node can track the point by generating coordinates for the tracked point in an input image of the locale or object. Methods of specifying and training the network using a three-dimensional model of the locale or object are also disclosed.Type: ApplicationFiled: May 15, 2019Publication date: November 19, 2020Applicant: Matterport, Inc.Inventors: Gary Bradski, Gholamreza Amayeh, Mona Fathollahi, Ethan Rublee, Grace Vesom, William Nguyen
-
Publication number: 20200364900Abstract: Systems and methods for point marking using virtual fiducial elements are disclosed. An example method includes placing a set of fiducial elements in a locale or on an object and capturing a set of calibration images using an imager. The set of fiducial elements is fully represented in the set of calibration images. The method also includes generating a three-dimensional geometric model of the set of fiducial elements using the set of calibration images. The method also includes capturing a run time image of the locale or object. The run time image does not include a selected fiducial element, from the set of fiducial elements, which was removed from a location in the locale or on the object prior to capturing the run time image. The method concludes with identifying the location relative to the run time image using the run time image and the three-dimensional geometric model.Type: ApplicationFiled: May 15, 2019Publication date: November 19, 2020Applicant: Matterport, Inc.Inventors: Gary Bradski, Gholamreza Amayeh, Mona Fathollahi, Ethan Rublee, Grace Vesom, William Nguyen
-
Publication number: 20200364482Abstract: Systems and methods for registering arbitrary visual features for use as fiducial elements are disclosed. An example method includes aligning a geometric reference object and a visual feature and capturing an image of the reference object and feature. The method also includes identifying, in the image of the object and the visual feature, a set of at least four non-colinear feature points in the visual feature. The method also includes deriving, from the image, a coordinate system using the geometric object. The method also comprises providing a set of measures to each of the points in the set of at least four non-colinear feature points using the coordinate system. The measures can then be saved in a memory to represent the registered visual feature and serve as the basis for using the registered visual feature as a fiducial element.Type: ApplicationFiled: May 15, 2019Publication date: November 19, 2020Applicant: Matterport, Inc.Inventors: Gary Bradski, Gholamreza Amayeh, Mona Fathollahi, Ethan Rublee, Grace Vesom, William Nguyen
-
Publication number: 20200364521Abstract: Trained networks configured to detect fiducial elements in encodings of images and associated methods are disclosed. One method includes instantiating a trained network with a set of internal weights which encode information regarding a class of fiducial elements, applying an encoding of an image to the trained network where the image includes a fiducial element from the class of fiducial elements, generating an output of the trained network based on the set of internal weights of the network and the encoding of the image, and providing a position for at least one fiducial element in the image based on the output. Methods of training such networks are also disclosed.Type: ApplicationFiled: May 15, 2019Publication date: November 19, 2020Applicant: Matterport, Inc.Inventors: Gary Bradski, Gholamreza Amayeh, Mona Fathollahi, Ethan Rublee, Grace Vesom, William Nguyen
-
Publication number: 20200128235Abstract: An improved method, system, and apparatus is provided to perform camera calibration, where cameras are mounted onto a moving conveyance apparatus to capture images of a multi-planar calibration target. The calibration process is optimized by reducing the number of images captured while simultaneously preserving overall information density.Type: ApplicationFiled: December 19, 2019Publication date: April 23, 2020Applicant: MAGIC LEAP, INC.Inventors: Jeffrey Steven Kranski, Frederick Dennis Zyda, Grace Vesom, Grace Shin-Yee Tsai, Jeremy A. Grata, Zhiheng Jia, Li Jiang
-
Patent number: 10547833Abstract: An improved method, system, and apparatus is provided to perform camera calibration, where cameras are mounted onto a moving conveyance apparatus to capture images of a multi-planar calibration target. The calibration process is optimized by reducing the number of images captured while simultaneously preserving overall information density.Type: GrantFiled: June 27, 2017Date of Patent: January 28, 2020Assignee: Magic Leap, Inc.Inventors: Jeffrey Steven Kranski, Frederick Dennis Zyda, Grace Vesom, Grace Shin-Yee Tsai, Jeremy A. Grata, Zhiheng Jia, Li Jiang
-
Publication number: 20170374360Abstract: An improved method, system, and apparatus is provided to perform camera calibration, where cameras are mounted onto a moving conveyance apparatus to capture images of a multi-planar calibration target. The calibration process is optimized by reducing the number of images captured while simultaneously preserving overall information density.Type: ApplicationFiled: June 27, 2017Publication date: December 28, 2017Applicant: Magic Leap, Inc.Inventors: Jeffrey Steven Kranski, Frederick Dennis Zyda, Grace Vesom, Grace Shin-Yee Tsai, Jeremy A. Grata, Zhiheng Jia, Li Jiang