公开(公告)号：US12093830B2

公开(公告)日：2024-09-17

申请号：US16976805

申请日：2019-07-23

Applicant: Google LLC

Inventor： Shahram Izadi ,  Cem Keskin

IPC: G06N3/084 ,  G06F18/213 ,  G06N3/048 ,  G06N3/08

CPC classification number: G06N3/084 ,  G06F18/213 ,  G06N3/048 ,  G06N3/08

Abstract: Methods, systems, and apparatus for more efficiently and accurately generating neural network outputs, for instance, for use in classifying image or audio data. In one aspect, a method includes processing a network input using a neural network including multiple neural network layers to generate a network output. One or more of the neural network layers is a conditional neural network layer. Processing a layer input using a conditional neural network layer to generate a layer output includes obtaining values of one or more decision parameters of the conditional neural network layer. The neural network processes the layer input and the decision parameters of the conditional neural network layer to determine values of one or more latent parameters of the conditional neural network layer from a continuous set of possible latent parameter values. The values of the latent parameters specify the values of the conditional layer weights.

公开(公告)号：US12073028B2

公开(公告)日：2024-08-27

申请号：US18174358

申请日：2023-02-24

Applicant: GOOGLE LLC

Inventor： Dongeek Shin ,  Shahram Izadi ,  David Kim ,  Sofien Bouaziz ,  Steven Benjamin Goldberg ,  Ivan Poupyrev ,  Shwetak N. Patel

IPC: G06F3/01 ,  G06F1/16 ,  G06V40/20

CPC classification number: G06F3/017 ,  G06F1/163 ,  G06F3/014 ,  G06V40/28

Abstract: Techniques of identifying gestures include detecting and classifying inner-wrist muscle motions at a user's wrist using micron-resolution radar sensors. For example, a user of an AR system may wear a band around their wrist. When the user makes a gesture to manipulate a virtual object in the AR system as seen in a head-mounted display (HMD), muscles and ligaments in the user's wrist make small movements on the order of 1-3 mm. The band contains a small radar device that has a transmitter and a number of receivers (e.g., three) of electromagnetic (EM) radiation on a chip (e.g., a Soli chip. This radiation reflects off the wrist muscles and ligaments and is received by the receivers on the chip in the band. The received reflected signal, or signal samples, are then sent to processing circuitry for classification to identify the wrist movement as a gesture.

公开(公告)号：US11934586B2

公开(公告)日：2024-03-19

申请号：US17809772

申请日：2022-06-29

Applicant: GOOGLE LLC

Inventor： Dongeek Shin ,  Andrea Colaco ,  Stiven Guillaume Francois Morvan ,  Adam James Banfield ,  Shahram Izadi

IPC: G06V40/10 ,  G06F1/16 ,  G06F3/01 ,  G06V10/82 ,  G06V20/20 ,  G06V40/13 ,  G06V40/20

CPC classification number: G06F3/017 ,  G06F1/163 ,  G06V10/82 ,  G06V20/20 ,  G06V40/1318 ,  G06V40/15 ,  G06V40/28

Abstract: Techniques of operating an AR system include determining hand gestures formed by a user based on a sequence of two-dimensional images through skin of the user's wrist acquired from a near-infrared camera. Specifically, an image capture device disposed on a band worn around a user's wrist includes a source of electromagnetic radiation, e.g., light-emitting diodes in the infrared (IR) wavelength band that emit the radiation into the user's wrist and an IR detector which produces the sequence of two-dimensional images of a region within a dermal layer in the user's wrist. From this sequence, gesture detection circuitry determines values of a biological flow metric, e.g., a change in perfusion index (PI) between frames of the sequence, based on a trained model that generates the metric from the sequence. Finally, the gesture detection circuitry maps the values of the biological flow metric to specific hand/finger movements that determine a gesture.

公开(公告)号：US11810313B2

公开(公告)日：2023-11-07

申请号：US17249095

申请日：2021-02-19

Applicant: GOOGLE LLC

Inventor： Vladimir Tankovich ,  Christian Haene ,  Sean Ryan Francesco Fanello ,  Yinda Zhang ,  Shahram Izadi ,  Sofien Bouaziz ,  Adarsh Prakash Murthy Kowdle ,  Sameh Khamis

IPC: G06T7/593 ,  H04N13/20 ,  G06T3/00 ,  G06T3/40 ,  G06T5/30 ,  H04N13/00

CPC classification number: G06T7/593 ,  G06T3/0093 ,  G06T3/40 ,  G06T5/30 ,  H04N13/20 ,  G06T2207/20016 ,  G06T2207/20084 ,  H04N2013/0081

Abstract: According to an aspect, a real-time active stereo system includes a capture system configured to capture stereo data, where the stereo data includes a first input image and a second input image, and a depth sensing computing system configured to predict a depth map. The depth sensing computing system includes a feature extractor configured to extract features from the first and second images at a plurality of resolutions, an initialization engine configured to generate a plurality of depth estimations, where each of the plurality of depth estimations corresponds to a different resolution, and a propagation engine configured to iteratively refine the plurality of depth estimations based on image warping and spatial propagation.

公开(公告)号：US11638233B2

公开(公告)日：2023-04-25

申请号：US17196093

申请日：2021-03-09

Applicant: Google LLC

Inventor： Dongeek Shin ,  Steven Benjamin Goldberg ,  Shahram Izadi

IPC: H04W64/00 ,  G01S5/02 ,  G01S13/02

Abstract: This document describes systems and techniques to generate refined location estimates using ultra-wideband (UWB) communication links. Mobile devices, such as smartphones, include location sensors to estimate their location. The accuracy of location sensors is generally about 3 meters (or about 10 feet). More accurate location data would allow mobile devices to provide new and improved functionality. The described systems and techniques determine the distance between nearby mobile devices using UWB communication links. A mobile device can then use the distance between the mobile devices to determine their relative locations. By comparing the relative locations of the mobile devices with their location estimates, the mobile device can generate a refined location estimate.

公开(公告)号：US11037026B2

公开(公告)日：2021-06-15

申请号：US16749626

申请日：2020-01-22

Applicant: Google LLC

Inventor： Sean Ryan Fanello ,  Julien Pascal Christophe Valentin ,  Adarsh Prakash Murthy Kowdle ,  Christoph Rhemann ,  Vladimir Tankovich ,  Philip L. Davidson ,  Shahram Izadi

IPC: G06K9/62

Abstract: Values of pixels in an image are mapped to a binary space using a first function that preserves characteristics of values of the pixels. Labels are iteratively assigned to the pixels in the image in parallel based on a second function. The label assigned to each pixel is determined based on values of a set of nearest-neighbor pixels. The first function is trained to map values of pixels in a set of training images to the binary space and the second function is trained to assign labels to the pixels in the set of training images. Considering only the nearest neighbors in the inference scheme results in a computational complexity that is independent of the size of the solution space and produces sufficient approximations of the true distribution when the solution for each pixel is most likely found in a small subset of the set of potential solutions.

公开(公告)号：US10579905B2

公开(公告)日：2020-03-03

申请号：US15925141

申请日：2018-03-19

Applicant: Google LLC

Inventor： Sean Ryan Fanello ,  Julien Pascal Christophe Valentin ,  Adarsh Prakash Murthy Kowdle ,  Christoph Rhemann ,  Vladimir Tankovich ,  Philip L. Davidson ,  Shahram Izadi

IPC: G06K9/62

Abstract: Values of pixels in an image are mapped to a binary space using a first function that preserves characteristics of values of the pixels. Labels are iteratively assigned to the pixels in the image in parallel based on a second function. The label assigned to each pixel is determined based on values of a set of nearest-neighbor pixels. The first function is trained to map values of pixels in a set of training images to the binary space and the second function is trained to assign labels to the pixels in the set of training images. Considering only the nearest neighbors in the inference scheme results in a computational complexity that is independent of the size of the solution space and produces sufficient approximations of the true distribution when the solution for each pixel is most likely found in a small subset of the set of potential solutions.

公开(公告)号：US20230350049A1

公开(公告)日：2023-11-02

申请号：US17661401

申请日：2022-04-29

Applicant: Google LLC

Inventor： Anandghan Waghmare ,  Dongeek Shin ,  Ivan Poupyrev ,  Shwetak N. Patel ,  Shahram Izadi ,  Adarsh Prakash Murthy Kowdle

IPC: G01S13/72 ,  G01S7/35 ,  G06F3/0338 ,  G06F3/01

CPC classification number: G01S13/723 ,  G01S7/35 ,  G06F3/0338 ,  G06F3/014 ,  G06F2203/0331

Abstract: A method including transmitting, by a peripheral device communicatively coupled to a wearable device, a frequency-modulated continuous wave (FMCW), receiving, by the peripheral device, a reflected signal based on the FMCW, tracking, by the peripheral device, a movement associated with the peripheral device based on the reflected signal, and communicating, from the peripheral device to the wearable device, an information corresponding to the movement associated with the peripheral device.

公开(公告)号：US11589031B2

公开(公告)日：2023-02-21

申请号：US16580802

申请日：2019-09-24

Applicant: Google LLC

Inventor： Sameh Khamis ,  Yinda Zhang ,  Christoph Rhemann ,  Julien Valentin ,  Adarsh Kowdle ,  Vladimir Tankovich ,  Michael Schoenberg ,  Shahram Izadi ,  Thomas Funkhouser ,  Sean Fanello

IPC: H04N13/271 ,  G06T7/90 ,  G06T7/521 ,  H04N5/33 ,  H04N13/239

Abstract: An electronic device estimates a depth map of an environment based on matching reduced-resolution stereo depth images captured by depth cameras to generate a coarse disparity (depth) map. The electronic device downsamples depth images captured by the depth cameras and matches sections of the reduced-resolution images to each other to generate a coarse depth map. The electronic device upsamples the coarse depth map to a higher resolution and refines the upsampled depth map to generate a high-resolution depth map to support location-based functionality.

公开(公告)号：US20220350419A1

公开(公告)日：2022-11-03

申请号：US17302258

申请日：2021-04-28

Applicant: GOOGLE LLC

Inventor： Dongeek Shin ,  Shahram Izadi ,  Shwetak N. Patel

IPC: G06F3/02 ,  A61B5/282 ,  A61B5/332

Abstract: A computing device, such as a wearable device, may include at least two electrodes mounted on a body. The computing device may determine an electrical signal associated with a circuit that includes the at least two electrodes and the user. A pressure applied to at least one electrode of the at least two electrodes may be determined from the electrical signal, and at least one function of the computing device may be implemented, based on the pressure.