公开(公告)号：WO2017019295A1

公开(公告)日：2017-02-02

申请号：PCT/US2016/041943

申请日：2016-07-12

Applicant: GOOGLE INC.

Inventor： ST. CLAIR, Timothy, Sepkoski ,  LIU, Tinglin ,  BABACAN, Sevket, Derin

IPC: G06T5/00 ,  G06T5/50

CPC classification number: G06T5/002 ,  G06K9/00536 ,  G06K9/00711 ,  G06K9/40 ,  G06K9/6256 ,  G06K9/66 ,  G06T5/20 ,  G06T5/50 ,  G06T2207/10016

Abstract: Implementations generally relate to enhancing a video. In some implementations, a method includes classifying one or more objects in one or more frames of the video. The method further includes determining one or more filter parameters of one or more filters based on the classifying of the one or more objects. The method further includes smoothing one or more of the determined filter parameters based on the classifying of the one or more objects. The method further includes applying one or more of the filters with corresponding smoothed filter parameters to one or more frames of the video.

Abstract translation: 实施通常涉及增强视频。 在一些实现中，一种方法包括对视频的一个或多个帧中的一个或多个对象进行分类。 该方法还包括基于一个或多个对象的分类来确定一个或多个过滤器的一个或多个过滤器参数。 该方法还包括基于一个或多个对象的分类来平滑一个或多个所确定的过滤器参数。 该方法还包括将一个或多个具有对应的平滑滤波器参数的滤波器应用于视频的一个或多个帧。

公开(公告)号：WO2014105816A1

公开(公告)日：2014-07-03

申请号：PCT/US2013/077471

申请日：2013-12-23

Applicant: GOOGLE INC.

Inventor： ST. CLAIR, Timothy, Sepkoski

IPC: H04N21/60

CPC classification number: H04N7/155 ,  H04N21/4394 ,  H04N21/44008 ,  H04N21/8456 ,  H04N21/8549

Abstract: A system and method for identifying one or more notable moments from video data are disclosed. In one embodiment, the system includes a video receiving module, an identification criteria module, a moment identification module and a presentation module. The video receiving module receives video data. The identification criteria module determines one or more criteria for identifying a notable moment. The one or more criteria are based at least in part on one or more of an audio indicator and a facial indicator. The moment identification module automatically identifies at least one notable moment in the video data based at least in part on the one or more criteria. The at least one notable moment is based on a subset of the video data. The presentation module sends the identified at least one notable moment for presentation to at least one user.

Abstract translation: 公开了一种从视频数据中识别一个或多个显着时刻的系统和方法。 在一个实施例中，系统包括视频接收模块，识别标准模块，时刻识别模块和呈现模块。 视频接收模块接收视频数据。 识别标准模块确定用于识别显着时刻的一个或多个标准。 一个或多个标准至少部分地基于一个或多个音频指示器和面部指示器。 该时刻识别模块至少部分地基于一个或多个标准自动识别视频数据中的至少一个显着时刻。 至少一个显着的时刻是基于视频数据的子集。 呈现模块将所识别的至少一个显着的时刻发送给至少一个用户。

公开(公告)号：WO2014100517A2

公开(公告)日：2014-06-26

申请号：PCT/US2013/076754

申请日：2013-12-19

Applicant: GOOGLE INC.

Inventor： COHEN, Dave ,  ST. CLAIR, Timothy, Sepkoski

IPC: H04N5/232

CPC classification number: H04N5/23222 ,  H04N5/23206

Abstract: A computer-implemented method, computer program product, and computing system is provided for interacting with images having similar content. In an embodiment, a method may include identifying one or more event attributes associated with an ongoing event. The method may also include determining one or more statistical characteristics associated with the one or more of the event attributes. The method may further include generating a prompt to an event participant to take a photograph during the ongoing event based on, at least in part, the one or more statistical characteristics.

Abstract translation: 提供了计算机实现的方法，计算机程序产品和计算系统，用于与具有相似内容的图像进行交互。 在一个实施例中，方法可以包括识别与正在进行的事件相关联的一个或多个事件属性。 该方法还可以包括确定与一个或多个事件属性相关联的一个或多个统计特征。 所述方法可以进一步包括至少部分地基于所述一个或多个统计特征，在所述持续事件期间向事件参与者产生提示以拍摄照片。