-
公开(公告)号:US10012766B2
公开(公告)日:2018-07-03
申请号:US14683769
申请日:2015-04-10
Applicant: Google Inc.
Inventor: Yash Modi , Kenneth Louis Herman , Laura Rabb , Michael Lammers , Bryan James , Kevin Charles Peterson , Mark Rajan Malhotra
Abstract: A system and method is provided for the control of a network of devices wherein each device of the networked devices provides for the operation of a sensor such as an accelerometer, processor and communication element within each device, and network and/or cloud based processing and storage, to process collected data to permit detection and predictive analysis of traffic patterns, weather patterns and other forces of nature. The system and method can analyze duration and magnitude of vibration signals, and considering maps and known locations of devices, tracks and highways and historical data regarding each, use machine learning techniques to accurately classify the motion and provide real-time and predictive analysis.
-
公开(公告)号:US20180184142A1
公开(公告)日:2018-06-28
申请号:US15710062
申请日:2017-09-20
Applicant: Google Inc.
Inventor: Brian Schmidt
IPC: H04N21/2343 , H04N21/2368 , H04N21/2187 , H04N21/6373 , H04N19/184 , H04N19/146 , H04N19/132
CPC classification number: H04N21/234381 , H04N19/132 , H04N19/146 , H04N19/184 , H04N21/2187 , H04N21/23406 , H04N21/2368 , H04N21/24 , H04N21/6373
Abstract: Implementations disclose zero-copy adaptive bitrate video streaming. A method includes capturing, by a user device, a first video frame of a plurality of video frames of a video item to be transmitted as a livestream; delivering the first video frame to an encoder of the user device; capturing a second video frame of the plurality of video frames, the second video frame being captured after the first video frame; delivering the second video frame to the encoder of the user device; in response to determining that the first video frame did not enter the encoder prior to the second video frame arriving at the encoder, discarding the first video frame; determining, by the user device, a frequency of discarded video frames comprising the first video frame; and adjusting, by a processing device of the user device, quality of the video item transmitted as the livestream based on the frequency.
-
公开(公告)号:US20180181366A1
公开(公告)日:2018-06-28
申请号:US15392732
申请日:2016-12-28
Applicant: Google Inc.
Inventor: Zaccariah Bowling
IPC: G06F3/16 , H04R29/00 , H04R3/04 , G10L19/018
CPC classification number: G06F3/165 , G10L21/00 , G10L25/51 , H04R27/00 , H04R2227/003 , H04R2420/07 , H04R2499/13
Abstract: A system comprising at least one processor; and at least one storage device. The storage device(s) store instructions that, when executed, cause the at least one processor to: prior to enabling output of an audio signal based on an audio data stream, detect, within the audio data stream, an indication of a target sound that corresponds to one of a plurality of sounds that are expected to cause distraction, replace, within the audio data stream, the indication of the target sound with an indication of a replacement sound, wherein the replacement sound is a less distracting version of the target sound, and after replacing the indication of the target sound with the indication of the replacement sound, output the audio data stream.
-
公开(公告)号:US20180177464A1
公开(公告)日:2018-06-28
申请号:US14715793
申请日:2015-05-19
Applicant: Google, Inc.
Inventor: Brian Derek DeBusschere , James Moad Reid , Jeffrey L. Rogers
IPC: A61B5/00 , A61B5/021 , A61B5/107 , A61B5/0205
CPC classification number: A61B5/7278 , A61B5/0013 , A61B5/0059 , A61B5/0075 , A61B5/0077 , A61B5/02028 , A61B5/0205 , A61B5/021 , A61B5/02125 , A61B5/02416 , A61B5/0816 , A61B5/1072 , A61B5/1079 , A61B5/489 , A61B5/6898 , A61B5/7246 , A61B5/725 , A61B5/7275 , A61B5/7285 , A61B5/742 , A61B5/7475 , A61B2560/0475 , A61B2562/0233 , A61B2576/00
Abstract: This document describes optical central venous pressure measurement. To determine the central venous pressure (CVP) of a person optically, video of a right side of the person's neck is captured. By way of example, a medical professional records a video of the right side of the person's neck using a smartphone. The right side of the person's neck is captured because it is where the person's external and internal jugular veins are located and pulsatile motions that are usable to measure CVP occur in those veins. The video is then processed according to video motion amplification techniques to generate a reconstructed video of the right side of the person's neck. In the reconstructed video, the pulsatile motion of the person's venous system that occurs at the right side of their neck is visually amplified. Using the reconstructed video, measurements are made of a distance between a peak of the visually-amplified pulsatile motion and an anatomical feature of the person. The measured distance between the peak of the visually-amplified pulsatile motion and the anatomical feature is used to determine CVP of the person. These techniques enable CVP to be determined without relying on estimates made by medical professionals.
-
公开(公告)号:US10009622B1
公开(公告)日:2018-06-26
申请号:US14969675
申请日:2015-12-15
Applicant: Google Inc.
Inventor: Debargha Mukherjee , Shunyao Li , Peyman Milanfar
IPC: H04N7/12 , H04N19/52 , H04N19/124 , H04N19/82 , H04N19/44 , H04N19/59 , H04N19/61 , H04N19/91 , H04N19/86 , H04N19/107 , H04N19/176 , H04N19/182
CPC classification number: H04N19/52 , H04N19/107 , H04N19/117 , H04N19/124 , H04N19/132 , H04N19/146 , H04N19/176 , H04N19/182 , H04N19/44 , H04N19/59 , H04N19/61 , H04N19/82 , H04N19/86 , H04N19/91
Abstract: A method for encoding a video signal using a computing device, the video signal having a plurality of frames, each frame having a plurality of blocks, and each block having a plurality of pixels. The method includes generating a residual block from an original block of a current frame and a prediction block, degrading the residual block to decrease a bit-cost for encoding the residual block, and encoding the residual block into an encoded residual block.
-
公开(公告)号:US10007717B2
公开(公告)日:2018-06-26
申请号:US14414855
申请日:2014-09-18
Applicant: Google Inc.
Inventor: Xincheng Zhang , Hui Tan , Zhiyu Wang , Jinan Lou
CPC classification number: G06F16/285 , G06F16/35 , H04L43/04
Abstract: Methods and apparatus related to clustering documents based on one or more classification terms and optionally based on similarity of structural paths of the documents. In some implementations, the documents are communications such as structured emails or other structured communications. In some of those implementations, clustering the communications includes identifying a plurality of classification terms indicative of a classification, identifying a corpus of communications that includes communications that are not labeled with an association to the classification, and determining a cluster of the communications based on occurrence of one or more of the classification terms in the communications of the cluster.
-
公开(公告)号:US10007565B1
公开(公告)日:2018-06-26
申请号:US15278954
申请日:2016-09-28
Applicant: Google Inc.
Inventor: Adam William Powell , Neel Rao , Benjamin David Poiesz
IPC: G06F9/54 , G06F3/0482 , G06F3/0488 , G06F3/01 , G06F17/22
CPC classification number: G06F9/543 , G06F3/016 , G06F3/0482 , G06F3/0484 , G06F3/04883 , G06F9/445 , G06F9/451 , G06F17/2235
Abstract: A computing device may receive from a first application executing on at least one processor an indication of an action to be performed. The computing device may determine, based on at least the indication of the action to be performed, a plurality of deep links to a plurality of actions performable by a plurality of applications. The computing device may select a subset of deep links from the plurality of deep links. The computing device may output for display a graphical user interface including an indication of each deep link from the subset of deep links. The computing device may receive an indication of a user input, the user input corresponding to a selection of one of the deep links from the subset of deep links. A second application executing on the at least one processor may perform an action linked to by the selected deep link.
-
公开(公告)号:US10007555B1
公开(公告)日:2018-06-26
申请号:US14562593
申请日:2014-12-05
Applicant: Google Inc.
Inventor: Stefan Kuhne
CPC classification number: G06F9/50 , G06F3/0481 , G06F3/0488 , G06F9/445 , G06F9/451 , G06F9/5011 , G06F2209/5019
Abstract: Techniques for dynamic resource management are provided. An example method includes identifying one or more applications executing on a computing device, wherein one or more user interface elements representing the applications allow switching between interaction with the applications, determining an application of the one or more applications that is presently not receiving interaction from a user, selectively reducing resources allocated to the determined application based at least on a past usage pattern of the application or predicted future interaction with the application while continuing display of a user interface element representing the application, and when the determined application is predicted to receive future interaction by the user, increasing resources allocated to the determined application prior to the predicted future interaction.
-
公开(公告)号:US20180175618A1
公开(公告)日:2018-06-21
申请号:US15385365
申请日:2016-12-20
Applicant: Google Inc.
Inventor: Eduardo Lao , Jyoti Sastry , James Kennedy , Christopher Gregory Malone , Varun Sakalkar
Abstract: This specification describes a power distribution system comprising a first section that receives power from a first source. The power received from the first source is adjusted by a first rectifier unit coupled to a first power bus of the first section. The system also comprises a second section that is separate from the first section and that receives power from a second source. The power received from the second source is adjusted by a second rectifier unit coupled to a second power bus of the second distribution section. The system includes a swing rectifier connected to the first section and connected to the second section. The swing rectifier is configured to provide power to the first power bus and to the second power bus and to dynamically adjust the power capacity of the first section that is available to computing loads, and to dynamically adjust the power capacity of the second section that is available to computing loads.
-
公开(公告)号:US20180174600A1
公开(公告)日:2018-06-21
申请号:US15497497
申请日:2017-04-26
Applicant: Google Inc.
Inventor: Sourish Chaudhuri , Kenneth Hoover
IPC: G10L25/57 , G11B27/10 , G10L17/00 , G06K9/00 , G10L25/21 , G10L15/26 , G10L25/93 , G06K9/66 , G10L15/06 , H04N21/488
CPC classification number: G10L25/57 , G06K9/00288 , G06K9/00744 , G06K9/00765 , G06K9/66 , G10L15/063 , G10L15/265 , G10L17/005 , G10L17/04 , G10L17/10 , G10L21/0272 , G10L25/21 , G10L25/30 , G10L25/78 , G10L25/93 , G11B27/031 , G11B27/10 , G11B27/28 , H04N21/233 , H04N21/23418 , H04N21/4394 , H04N21/44008 , H04N21/4666 , H04N21/4884 , H04N21/8549
Abstract: A computer-implemented method for speech diarization is described. The method comprises determining temporal positions of separate faces in a video using face detection and clustering. Voice features are detected in the speech sections of the video. The method further includes generating a correlation between the determined separate faces and separate voices based at least on the temporal positions of the separate faces and the separate voices in the video. This correlation is stored in a content store with the video.
-
-
-
-
-
-
-
-
-