公开(公告)号：US20150195454A1

公开(公告)日：2015-07-09

申请号：US14148229

申请日：2014-01-06

Applicant: Google Inc.

Inventor： Frank Petterson ,  Kathryn Cushing ,  Sanjay G. Mavinkurve ,  Marshall Bock ,  Scott Shumaker

IPC: H04N5/232

CPC classification number: H04N5/23245 ,  H04N1/00209 ,  H04N1/00212 ,  H04N5/23216

Abstract: A method and computing system for determining a time differential between an image capture initiation indicator and an image capture completion indicator on a client electronic device. In response to a short time differential, a photograph is captured using the client electronic device. In response to a long time differential, a video is captured using the client electronic device.

Abstract translation: 一种用于确定客户端电子设备上的图像捕获启动指示符和图像捕获完成指示符之间的时间差的方法和计算系统。 响应于短时差，使用客户端电子设备拍摄照片。 响应于长时间差异，使用客户端电子设备捕获视频。

公开(公告)号：US20170308249A1

公开(公告)日：2017-10-26

申请号：US15596116

申请日：2017-05-16

Applicant: Google Inc.

Inventor： Frank Petterson ,  Brian Laird ,  Chikezie Ejiasi ,  Anand Agarawala ,  Leslie Ikemoto ,  Daniel Burka ,  Karl Channell

IPC: G06F3/0482 ,  G06F3/048 ,  G06F3/0485

CPC classification number: G06F3/0482 ,  G06F3/048 ,  G06F3/0485 ,  G06F2203/04803

Abstract: A system and method for generating and providing user interfaces for interacting with a stream of content are disclosed. A system having one or more processors and a memory is configured to perform operations including receiving a stream of content including one or more content items; selecting a content item; determining a tile type for providing the content item based upon an attribute of the content item; populating tile components for the tile type using the content item; organizing content tiles in a dynamic grid using the attribute of the content items; and providing the dynamic grid of content tiles for display.

公开(公告)号：US20160366483A1

公开(公告)日：2016-12-15

申请号：US15179575

申请日：2016-06-10

Applicant: Google Inc.

Inventor： Alan Joyce ,  Marshall Bock ,  Jonathan Terleski ,  Frank Petterson ,  Jason Robert Sao Bento ,  Kristofer Chiao

IPC: H04N21/472 ,  H04N21/61 ,  A63F13/79 ,  H04N21/41 ,  G06F17/30 ,  A63F13/85 ,  H04N21/45 ,  H04N21/462

Abstract: Methods, systems, and media for aggregating and presenting content relevant to a particular video game. In some embodiments, the method comprises: identifying videos related to a video game; selecting videos relevant to each of a plurality of categories; selecting videos based on popularity; receiving a request to present a user interface related to the video game; determining user subscription information for a user associated with the request; selecting videos based on user subscription information; causing the user interface to be presented including representations of: videos relevant to a first category in a first portion, videos selected based on popularity in a second portion, and videos selected based on the user subscription information in a third portion; receiving a request to present a video selected via the user interface; and causing the user device to present the requested video.

Abstract translation: 用于聚合和呈现与特定视频游戏相关的内容的方法，系统和媒体。 在一些实施例中，该方法包括：识别与视频游戏相关的视频; 选择与多个类别中的每一个相关的视频; 基于人气选择视频; 接收呈现与视频游戏相关的用户界面的请求; 确定与所述请求相关联的用户的用户订阅信息; 基于用户订阅信息选择视频; 使得呈现用户界面，包括：与第一部分中的第一类别相关的视频，基于第二部分中的受欢迎程度选择的视频，以及在第三部分中基于用户订阅信息选择的视频; 接收通过所述用户界面选择的视频的请求; 并使用户设备呈现所请求的视频。

公开(公告)号：US20150003727A1

公开(公告)日：2015-01-01

申请号：US14485186

申请日：2014-09-12

Applicant: Google Inc.

Inventor： Thor Carpenter ,  Frank Petterson ,  Janahan Vivekanandan

IPC: G06K9/00 ,  G06T7/00

CPC classification number: G06K9/00335 ,  G06T7/11 ,  G06T7/143 ,  G06T7/194 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20016

Abstract: Methods and systems are provided allowing for background identification and gesture recognition in video images. A computer-implemented image processing method includes: receiving, using at least one processing circuit, a plurality of image frames of a video; constructing, using at feast one processing circuit, a plurality of statistical models of the plurality of image frames at a plurality of pixel granularity levels; constructing, using at least one processing circuit, a plurality of probabilistic models of an input image frame at a plurality of channel granularity levels based on the plurality of statistical models; merging at least some of the plurality of probabilistic models based on a weighted average to form a single probability image; determining background pixels, based on a probability threshold value, from the single probability image; and determining whether the plurality of image frames, when examined in a particular sequence, conveys a gesture by the object.

Abstract translation: 提供了允许在视频图像中进行背景识别和手势识别的方法和系统。 计算机实现的图像处理方法包括：使用至少一个处理电路接收视频的多个图像帧; 在多个像素粒度级别构建，使用一个处理电路中的多个图像帧的多个统计模型; 基于所述多个统计模型，构建使用至少一个处理电路多个信道粒度级的输入图像帧的概率模型; 基于加权平均来合并多个概率模型中的至少一些以形成单个概率图像; 基于概率阈值从单个概率图像确定背景像素; 以及当以特定顺序检查时，确定所述多个图像帧是否由所述对象传送手势。