System and method for audio-visual content synthesis
    11.
    发明授权
    System and method for audio-visual content synthesis 失效
    视听内容合成的系统和方法

    公开(公告)号:US07636662B2

    公开(公告)日:2009-12-22

    申请号:US10573736

    申请日:2004-09-28

    IPC分类号: G10L13/00

    摘要: A system and method is provided for synthesizing audio-visual content in a video image processor. A content synthesis application processor extracts audio features and video features from audio-visual input signals that represent a speaker who is speaking. The processor uses the extracted visual features to create a computer generated animated version of the face of the speaker. The processor synchronizes facial movements of the animated version of the face of the speaker with a plurality of audio logical units such as phonemes that represent the speaker's speech. In this manner the processor synthesizes an audio-visual representation of the speaker's face that is properly synchronized with the speaker's speech.

    摘要翻译: 提供了一种用于在视频图像处理器中合成视听内容的系统和方法。 内容合成应用处理器从表示正在说话的扬声器的视听输入信号中提取音频特征和视频特征。 处理器使用提取的视觉特征来创建计算机生成的演讲者脸部动画版本。 处理器将扬声器的动画版本的面部运动与表示说话者的语音的多个音频逻辑单元(例如,音素)同步。 以这种方式,处理器合成了与扬声器的语音正确同步的扬声器的面部的视听表示。

    Method and Apparatus to Facilitate Provision and Use of a Media Source Bundle
    12.
    发明申请
    Method and Apparatus to Facilitate Provision and Use of a Media Source Bundle 审中-公开
    促进媒体源码包的提供和使用的方法和装置

    公开(公告)号:US20090172106A1

    公开(公告)日:2009-07-02

    申请号:US11965084

    申请日:2007-12-27

    IPC分类号: G06F15/16

    摘要: One provides (101) a media source bundle (200) as pertains to a given subject matter of interest to at least one end user. This media source bundle can comprise, for example and at least in part, content source locations for each of a plurality of independent content sources that each offer content regarding the given subject matter and wherein at least some of these independent content sources are associated with mutually non-compatible electronic content-delivery modalities. (In such an application, the media source bundle will be understood to not comprise the content itself.) These teachings will then provide for transmitting (102) a message that comprises, at least in part, this media source bundle to one or more corresponding end user recipient platforms (303).

    摘要翻译: 一个提供(101)与至少一个最终用户感兴趣的给定主题相关的媒体源束(200)。 该媒体源束可以例如并且至少部分地包括用于多个独立内容源中的每一个的内容源位置,其各自提供关于给定主题的内容,并且其中这些独立内容源中的至少一些与相互关联 不兼容的电子内容传送方式。 (在这样的应用中,媒体源束将被理解为不包括内容本身)。然后,这些教导将提供将至少部分地将该媒体源束包括至一个或多个对应的消息(102) 最终用户收件人平台(303)。

    Method and apparatus for performing object detection
    13.
    发明申请
    Method and apparatus for performing object detection 有权
    用于执行物体检测的方法和装置

    公开(公告)号:US20070140550A1

    公开(公告)日:2007-06-21

    申请号:US11312219

    申请日:2005-12-20

    IPC分类号: G06K9/62 G06K9/46

    CPC分类号: G06K9/00248

    摘要: An object detection algorithm that generates a two-layer Gaussian Mixture Model (GMM) during a training session, and subsequent to the training session, uses the two-layer GMM to perform face detection. No labeling of local features is needed. The only input that is provided by a user is the setting of a few global parameters for the image being captured during the training session, such as, for example, the person's facial pose.

    摘要翻译: 在训练阶段和训练阶段之后生成双层高斯混合模型(GMM)的对象检测算法使用双层GMM进行人脸检测。 不需要标记局部特征。 由用户提供的唯一输入是在训练会话期间为例如人的面部姿势捕获的图像的几个全局参数的设置。

    METHOD AND DEVICE FOR MATCHING SIGNATURES ON THE BASIS OF MOTION SIGNATURE INFORMATION
    14.
    发明申请
    METHOD AND DEVICE FOR MATCHING SIGNATURES ON THE BASIS OF MOTION SIGNATURE INFORMATION 审中-公开
    基于运动签名信息匹配签名的方法和装置

    公开(公告)号:US20160098591A1

    公开(公告)日:2016-04-07

    申请号:US14889320

    申请日:2014-05-05

    申请人: Dongge LI

    发明人: Dongge LI Chengyu LI

    IPC分类号: G06K9/00 G06T7/20

    摘要: A method for matching signatures based on motion signature information including acquiring a first signature and at least one second signature that are to be matched, wherein the first signature and the second signature are generated based on a motion object's motion signature information; and matching the first signature and the second signature based on the motion signature information to obtain a corresponding match result.

    摘要翻译: 一种用于基于运动签名信息匹配签名的方法,包括获取第一签名和至少一个第二签名,其中基于运动对象的运动签名信息生成第一签名和第二签名; 并且基于运动签名信息匹配第一签名和第二签名以获得相应的匹配结果。

    Method and apparatus for performing object detection
    15.
    发明授权
    Method and apparatus for performing object detection 有权
    用于执行物体检测的方法和装置

    公开(公告)号:US07697752B2

    公开(公告)日:2010-04-13

    申请号:US11312219

    申请日:2005-12-20

    IPC分类号: G06K9/62

    CPC分类号: G06K9/00248

    摘要: An object detection algorithm that generates a two-layer Gaussian Mixture Model (GMM) during a training session, and subsequent to the training session, uses the two-layer GMM to perform face detection. No labeling of local features is needed. The only input that is provided by a user is the setting of a few global parameters for the image being captured during the training session, such as, for example, the person's facial pose.

    摘要翻译: 在训练阶段和训练阶段之后生成双层高斯混合模型(GMM)的对象检测算法使用双层GMM进行人脸检测。 不需要标记局部特征。 由用户提供的唯一输入是在训练会话期间为例如人的面部姿势捕获的图像的几个全局参数的设置。

    Personal identification method and apparatus
    16.
    发明授权
    Personal identification method and apparatus 有权
    个人识别方法和装置

    公开(公告)号:US07272246B2

    公开(公告)日:2007-09-18

    申请号:US10443637

    申请日:2003-05-22

    IPC分类号: G06K9/00

    CPC分类号: G06K9/00288 G06K9/72

    摘要: A processor (10) utilizes information regarding one or more physical dimensions of an individual (14) to better inform a personal identification process. In one embodiment, the measured physical dimensions are utilized to influence the conduct of a face recognition process. In one embodiment, a Bayesian Belief Network can be utilized to facilitate such processes.

    摘要翻译: 处理器(10)利用关于个人(14)的一个或多个物理维度的信息来更好地通知个人识别过程。 在一个实施例中,所测量的物理尺寸用于影响面部识别过程的进行。 在一个实施例中,贝叶斯信仰网络可以用于促进这种过程。

    Method and apparatus for identifying related media across playback platforms
    17.
    发明申请
    Method and apparatus for identifying related media across playback platforms 审中-公开
    用于在播放平台上识别相关媒体的方法和装置

    公开(公告)号:US20070156667A1

    公开(公告)日:2007-07-05

    申请号:US11324854

    申请日:2006-01-04

    IPC分类号: G06F17/30

    CPC分类号: G06F16/9535

    摘要: A network element of choice receives (101) information and uses (102) that information to develop a content search query. That network element then instigates (103) a content search using the content search query and receives (104), in turn, content search results comprising a plurality of content items. Profile information for a plurality of playback platforms is then accessed (105) and used (106) to identify which of the content items are best played back on particular ones of the playback platforms.

    摘要翻译: 选择的网络元件接收(101)信息并使用(102)该信息来开发内容搜索查询。 该网络元件然后使用内容搜索查询来发起(103)内容搜索,并且接收(104)依次包括多个内容项的内容搜索结果。 然后访问(105)并使用(106)识别多个回放平台的简档信息,以识别哪些内容项目在特定的回放平台上被最好地回放。

    Method and apparatus for meta-data storage and retrieval
    18.
    发明申请
    Method and apparatus for meta-data storage and retrieval 审中-公开
    元数据存储和检索的方法和装置

    公开(公告)号:US20060062059A1

    公开(公告)日:2006-03-23

    申请号:US10945414

    申请日:2004-09-20

    IPC分类号: G11C7/00

    摘要: Meta-data retrieved externally is determined to be relevant to the creation of an electronic programming guide (EPG) or relevant to a user's preferred programs. The meta-data is stored locally if it is determined that it is relevant to the creation of the EPG or if it is relevant to the user's preferred programs. All other meta-data is discarded. When a user requests meta-data, an attempt is made to retrieve the data from a local database, and if the attempt fails, then the meta-data is obtained from an external source.

    摘要翻译: 外部检索的元数据被确定为与创建电子节目指南(EPG)或与用户的首选节目有关的元数据相关。 如果确定其与EPG的创建相关或者如果它与用户的优选程序相关,则元数据被存储在本地。 所有其他元数据都被丢弃。 当用户请求元数据时,尝试从本地数据库检索数据,如果尝试失败,则从外部源获得元数据。