利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

76 条记录 (耗时 0.023 秒)

    Video retrieval method and apparatus
    7.
    发明授权
    Video retrieval method and apparatus 失效
    视频检索方法和装置

    公开(公告)号：US6021231A

    公开(公告)日：2000-02-01

    申请号：US908072

    申请日：1997-08-11

    申请人： Takafumi Miyatake ,  Shigeo Sumino ,  Katsumi Taniguchi ,  Akio Nagasaka ,  Mitsuru Ikezawa ,  Hirotada Ueda

    发明人： Takafumi Miyatake ,  Shigeo Sumino ,  Katsumi Taniguchi ,  Akio Nagasaka ,  Mitsuru Ikezawa ,  Hirotada Ueda

    IPC分类号： G06F7/00 ,  G06F17/30 ,  G06K9/46 ,  G06K9/54 ,  G11B27/10 ,  G11B27/28 ,  G11B31/00 ,  H04H1/00 ,  H04H60/37 ,  H04H60/48 ,  H04H60/59 ,  H04N5/14

    CPC分类号： G06F17/30787 ,  G06F17/30802 ,  G06F17/30817 ,  G06F17/30825 ,  G06F17/30858 ,  H04H60/37 ,  H04H60/59 ,  G11B27/105 ,  G11B27/28 ,  G11B31/00 ,  H04H60/48 ,  H04N5/147

    摘要： There is provided a video retrieval method, and apparatus, capable of fast matching a feature of a target video with a feature of an enquiry video without conducting work of providing keywords for video retrieval. As for the target video, both a video which is being broadcasted and a video included in a data base can be dealt with. A retrieval method includes the steps of providing a representative frame image specified by a user with a code or a code string as a name thereof, and registering beforehand code strings of a plurality of representative frame images as enquiry video names; inputting a target video; extracting a representative frame image from the video; calculating one feature or a plurality of features from a whole or a part of the frame image; assigning a corresponding code to the feature or each of the features; providing the frame image with the code or a code string arranged in a predetermined order as a name thereof, and producing a video name for the video in a form of a frame name string corresponding to a string of the frames; and matching the enquiry video names with the video name by using the frame name string and outputting a result.

    摘要翻译： 提供了一种视频检索方法和装置，其能够快速地将目标视频的特征与查询视频的特征进行匹配，而不进行为视频检索提供关键字的工作。 对于目标视频，可以处理正在广播的视频和包括在数据库中的视频。 一种检索方法包括以下步骤：提供由用户指定的具有代码或代码串的代表性帧图像作为其名称，并且预先将多个代表性帧图像的代码串预先登记为查询视频名称; 输入目标视频; 从视频提取代表帧图像; 从所述帧图像的整体或部分中计算一个特征或多个特征; 为特征或每个特征分配相应的代码; 为帧图像提供具有以预定顺序排列的代码或代码串作为其名称，并且以对应于帧的字符串的帧名称字符串的形式产生视频的视频名称; 并通过使用帧名字符串将查询视频名称与视频名称匹配并输出结果。

    Method for detecting a contour of a given subject to be separated from images and apparatus for separating a given subject from images
    8.
    发明授权
    Method for detecting a contour of a given subject to be separated from images and apparatus for separating a given subject from images 失效
    用于检测要从图像分离的给定对象的轮廓的方法和用于将给定对象与图像分离的装置

    公开(公告)号：US5471535A

    公开(公告)日：1995-11-28

    申请号：US840822

    申请日：1992-02-25

    申请人： Mitsuru Ikezawa ,  Takafumi Miyatake ,  Hirotada Ueda ,  Shigeo Sumino ,  Satoshi Yoshizawa

    发明人： Mitsuru Ikezawa ,  Takafumi Miyatake ,  Hirotada Ueda ,  Shigeo Sumino ,  Satoshi Yoshizawa

    IPC分类号： H04N5/272 ,  G06T5/00 ,  G06T7/60 ,  G06T11/60 ,  G06T11/80 ,  G06K9/48

    CPC分类号： G06T7/0083 ,  G06T2207/10016 ,  G06T2207/20101 ,  G06T2207/20144

    摘要： A method for detecting a contour of a given subject to be separated from images utilizing an image separating system. First, a plurality of candidate points which have been input by a user are displayed on a screen. A smooth curve which connects the plurality of candidate points is determined and is displayed on a display apparatus. The intensity of light on a straight line extending in a direction normal to each candidate point is determined. The position of the candidate point is corrected based upon the rate of change in the intensity of light which is determined for each candidate point. A smooth curve which passes the corrected candidate points is determined and is displayed on the display apparatus. The specified image, represented by the smooth curve connecting the corrected candidate points, is then separated from the rest of the image elements.

    摘要翻译： 一种用于使用图像分离系统检测要与图像分离的给定对象的轮廓的方法。 首先，在屏幕上显示已经由用户输入的多个候选点。 连接多个候选点的平滑曲线被确定并显示在显示装置上。 确定在垂直于每个候选点的方向上延伸的直线上的光强度。 基于针对每个候选点确定的光强度的变化率来校正候选点的位置。 确定通过校正的候选点的平滑曲线并将其显示在显示装置上。 然后将连接校正的候选点的平滑曲线表示的指定图像与其余图像元素分离。

    Apparatus for integrally controlling audio and video signals in real time and multi-site communication control method
    9.
    发明授权
    Apparatus for integrally controlling audio and video signals in real time and multi-site communication control method 失效
    用于实时整体控制音视频信号的装置和多站点通信控制方法

    公开(公告)号：US5548346A

    公开(公告)日：1996-08-20

    申请号：US336646

    申请日：1994-11-04

    申请人： Itaru Mimura ,  Hirotada Ueda ,  Shigeo Sumino ,  Mitsuru Ikezawa ,  Toshiaki Suzuki ,  Taizo Kinoshita ,  Katsumi Tada

    发明人： Itaru Mimura ,  Hirotada Ueda ,  Shigeo Sumino ,  Mitsuru Ikezawa ,  Toshiaki Suzuki ,  Taizo Kinoshita ,  Katsumi Tada

    IPC分类号： H04N5/14 ,  H04N5/45 ,  H04N5/60 ,  H04N7/15 ,  H04N21/43

    CPC分类号： H04N21/4305 ,  H04N5/147 ,  H04N5/607 ,  H04N7/15 ,  H04N5/45

    摘要： A real time visual communication system capable of improving a correspondence between a received video signal and a received audio signal in real time and improving reality. An AV signal is separated into a video signal and an audio signal, and the output state of the video or audio signal is controlled by the characteristics of the audio or video signal. For example, the sound field, reverberation, and the like are controlled in accordance with the characteristics of the video signal. A suitable image pickup unit is selected in accordance with the characteristics of the audio signal to make the sights of conversation participants coincide with each other. It is possible to reproduce sounds of audio signals well matching video signals and to provide visual communication having good reality because of the combination of matched audio and video signals.

    摘要翻译： 一种实时视觉通信系统，其能够实时地改善接收到的视频信号和接收到的音频信号之间的对应关系并改善现实。 AV信号被分成视频信号和音频信号，并且视频或音频信号的输出状态由音频或视频信号的特性来控制。 例如，根据视频信号的特性来控制声场，混响等。 根据音频信号的特性来选择合适的图像拾取单元，以使会话参与者的视线彼此一致。 可以再现与视频信号相匹配的音频信号的声音，并且由于匹配的音频和视频信号的组合而提供具有良好现实的视觉通信。

    Method of synthesizing real image and computer graphic in image processing system
    10.
    发明授权
    Method of synthesizing real image and computer graphic in image processing system 失效
    图像处理系统中真实图像和计算机图形的合成方法

    公开(公告)号：US5325470A

    公开(公告)日：1994-06-28

    申请号：US837890

    申请日：1992-02-20

    申请人： Shigeo Sumino ,  Hirotada Ueda ,  Takafumi Miyatake ,  Satoshi Yoshizawa

    发明人： Shigeo Sumino ,  Hirotada Ueda ,  Takafumi Miyatake ,  Satoshi Yoshizawa

    IPC分类号： G06T3/00 ,  G06T11/80 ,  G06T19/20 ,  G06F15/72

    CPC分类号： G06T15/20

    摘要： A method of synthesizing a real image and a computer graphic (CG) having a complex shape in which the normal vector of each of two adjacent planes of a rectangular parallelepiped CG circumscribed about the CG having a complex shape is determined from the coordinates of six vertices representing the two planes on the basis of a real image of a rectangular parallelepiped, and parameters for three-dimensional rotational transformation of the rectangular parallelepiped CG required for synthesis are determined on the basis of the normal vectors. A CG having a complex shape for synthesis is produced by rotational transformation thereof on the basis of the parameters, and the CG having a complex shape thus produced is synthesized on the real image.

    摘要翻译： 一种合成真实图像的方法和具有复杂形状的计算机图形（CG）的方法，其中，从六个顶点的坐标确定围绕具有复杂形状的CG包围的长方体CG的两个相邻平面的每个的两个相邻平面的法线矢量 基于长方体的真实图像表示两个平面，并且基于法线向量确定合成所需的长方体CG的三维旋转变换的参数。 通过基于参数的旋转变换来生成具有复合合成形状的CG，并且在实际图像上合成具有如此生成的复杂形状的CG。