知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

82 条记录 (耗时 0.021 秒)

    APPARATUS AND METHOD OF SHOT CLASSIFICATION
    22.
    发明申请
    APPARATUS AND METHOD OF SHOT CLASSIFICATION 审中-公开
    装置和分类方法

    公开(公告)号：US20070098268A1

    公开(公告)日：2007-05-03

    申请号：US11551483

    申请日：2006-10-20

    申请人： Ratna Beresford

    发明人： Ratna Beresford

    IPC分类号： G06K9/62 ,  H04N5/44

    CPC分类号： G11B27/28 ,  G06F16/786

    摘要： A method of classifying a video shot comprises predicting an image from a preceding image using a parameter based image transform, and comparing points in the predicted image with corresponding points in a current image to generate an point error value for each point. These point error values are used to identify those points whose point error value exceeds a point error threshold. Then, for corresponding points on images used as input to subsequent calculations that update the image transform parameters, the points so identified are excluded from contributing to said calculations.

    摘要翻译： 对视频拍摄进行分类的方法包括使用基于参数的图像变换来预测来自前一图像的图像，以及将预测图像中的点与当前图像中的对应点进行比较，以生成每个点的点误差值。 这些点误差值用于识别点误差值超过点误差阈值的点。 然后，对于用作更新图像变换参数的后续计算的输入的图像上的对应点，所识别的点被排除在对所述计算的贡献之外。

    EXTRACTION METHOD AND DEVICE
    25.
    发明申请
    EXTRACTION METHOD AND DEVICE 审中-公开
    提取方法和装置

    公开(公告)号：US20150262619A1

    公开(公告)日：2015-09-17

    申请号：US14633604

    申请日：2015-02-27

    申请人： FUJITSU LIMITED

    发明人： Atsushi Oguchi ,  Susumu Endo ,  Takayuki BABA ,  Sokichi Fujita ,  Tatsuma Muramatsu

    IPC分类号： G11B27/30 ,  G11B27/10 ,  G11B27/06 ,  G11B27/031

    CPC分类号： G11B27/3081 ,  G06F16/786 ,  G11B27/031 ,  G11B27/034 ,  G11B27/06 ,  G11B27/102 ,  G11B27/28

    摘要： An extraction device includes a processor that executes a procedure. The procedure includes detecting a transition between a close-up captured image and a long distance captured image from captured images obtained by capturing a sports game, and, based on the detected transition, extracting a timing corresponding to a break in play in the sports game, or extracting a captured image corresponding to a break in play in the sports game.

    摘要翻译： 提取装置包括执行过程的处理器。 该过程包括：通过捕捉运动游戏获得的拍摄图像检测特写拍摄图像和长距离拍摄图像之间的转换，并且基于检测到的转换，提取与运动游戏中的休息时间相对应的时刻 ，或者提取与运动游戏中的休息中断相对应的拍摄图像。

    SYSTEM AND METHOD FOR EXTRACTING TEXT CAPTIONS FROM VIDEO AND GENERATING VIDEO SUMMARIES
    26.
    发明申请
    SYSTEM AND METHOD FOR EXTRACTING TEXT CAPTIONS FROM VIDEO AND GENERATING VIDEO SUMMARIES 审中-公开
    从视频提取文本和生成视频摘要的系统和方法

    公开(公告)号：US20130293776A1

    公开(公告)日：2013-11-07

    申请号：US13935183

    申请日：2013-07-03

    申请人： The Trustees of Columbia University

    发明人： Chang Shih-Fu ,  Dongqing Zhang

    IPC分类号： H04N7/088

    CPC分类号： H04N7/0882 ,  G06F16/739 ,  G06F16/7844 ,  G06F16/7857 ,  G06F16/786 ,  G06K9/3266 ,  G06K2209/01 ,  G06T7/75 ,  G11B27/031 ,  G11B27/034 ,  G11B27/28 ,  H04N5/93 ,  H04N7/025 ,  H04N21/434 ,  H04N21/4884

    摘要： Caption boxes which are embedded in video content can be located and the text within the caption boxes decoded. Real time processing is enhanced by locating caption box regions in the compressed video domain and performing pixel based processing operations within the region of the video frame in which a caption box is located. The captions boxes are further refined by identifying word regions within the caption boxes and then applying character and word recognition processing to the identified word regions. Domain based models are used to improve text recognition results. The extracted caption box text can be used to detect events of interest in the video content and a semantic model applied to extract a segment of video of the event of interest.

    摘要翻译： 嵌入在视频内容中的字幕框可以被定位，并且标题框内的文本被解码。 通过将标题框区域定位在压缩视频域中并且在字幕框所在的视频帧的区域内执行基于像素的处理操作来增强实时处理。 通过识别字幕框内的字区域，然后对识别的字区域应用字符和字识别处理，进一步细化字幕框。 基于域的模型用于改进文本识别结果。 提取的字幕框文本可用于检测视频内容中感兴趣的事件和应用于提取感兴趣事件的视频片段的语义模型。

    METHOD OF MEASURING A SIMILARITY DEGREE OF DIGITAL VIDEO CONTENTS, METHOD OF MANAGING VIDEO CONTENTS USING THE SAME AND MANAGEMENT SYSTEM FOR VIDEO CONTENTS USING THE METHOD OF MANAGING VIDEO CONTENTS
    27.
    发明申请
    METHOD OF MEASURING A SIMILARITY DEGREE OF DIGITAL VIDEO CONTENTS, METHOD OF MANAGING VIDEO CONTENTS USING THE SAME AND MANAGEMENT SYSTEM FOR VIDEO CONTENTS USING THE METHOD OF MANAGING VIDEO CONTENTS 审中-公开
    测量数字视频内容的相似度的方法，使用该视频内容管理视频内容的方法和使用管理视频内容的视频内容的管理系统

    公开(公告)号：US20100071016A1

    公开(公告)日：2010-03-18

    申请号：US12559869

    申请日：2009-09-15

    申请人： Won-Suhk UHM ,  Sang-Gyoo SIM

    发明人： Won-Suhk UHM ,  Sang-Gyoo SIM

    IPC分类号： H04N7/173 ,  H04N17/00

    CPC分类号： G06K9/00758 ,  G06F16/786 ,  H04N7/16 ,  H04N19/137 ,  H04N19/142 ,  H04N19/61 ,  H04N21/2541 ,  H04N21/2585 ,  H04N21/44008 ,  H04N21/440263 ,  H04N21/835 ,  H04N21/8352 ,  H04N21/8355

    摘要： A method of measuring a similarity degree of digital video contents is provided as follows. Firstly, scene conversion of a video content is detected to divide the video content into a plurality of scenes. Then, a first scene feature is extracted from a first scene of the divided scenes. Thereafter, a similarity degree is measured by comparing the extracted first scene feature of the first scene with a second scene feature of a second scene. Thus, a similarity degree of digital video contents may be effectively measured, the digital video contents may be prevented from illegal sharing, and additional contents information related to the digital video contents may be provided when playing the digital video contents. Therefore, the method may be effectively used in contents management and contents circulation.

    摘要翻译： 如下提供测量数字视频内容的相似度的方法。 首先，检测视频内容的场景转换以将视频内容划分为多个场景。 然后，从划分的场景的第一场景中提取第一场景特征。 此后，通过将所提取的第一场景的第一场景特征与第二场景的第二场景特征进行比较来测量相似度。 因此，可以有效地测量数字视频内容的相似度，可以防止数字视频内容的非法共享，并且当播放数字视频内容时可以提供与数字视频内容相关的附加内容信息。 因此，该方法可以有效地用于内容管理和内容流通。

    METHOD, APPARATUS AND PROGRAM PRODUCTS FOR RETRIEVING MOVING IMAGE
    30.
    发明申请
    METHOD, APPARATUS AND PROGRAM PRODUCTS FOR RETRIEVING MOVING IMAGE 审中-公开
    用于检测移动图像的方法，装置和程序产品

    公开(公告)号：US20090049103A1

    公开(公告)日：2009-02-19

    申请号：US12249682

    申请日：2008-10-10

    申请人： Katsunao TAKAHASHI ,  Nobuyoshi Terashima ,  Hideyoshi Tominaga

    发明人： Katsunao TAKAHASHI ,  Nobuyoshi Terashima ,  Hideyoshi Tominaga

    IPC分类号： G06F17/30

    CPC分类号： G06F16/785 ,  G06F16/786 ,  G06F16/7864

    摘要： An apparatus for retrieving moving image according to the present invention has an extracting unit for extracting the information of the feature quantity of the moving image from the fixed moving image data, an extracting unit for extracting the information of the unique identification of the moving image to identify the moving image according to the information of the feature quantity of the moving image, and a retrieving unit for retrieving and identifying the fixed moving image from the object moving image for retrieving by comparing the information of the unique identification of the moving image with the information of the unique identification of the moving image beforehand extracted from the object moving image. Therefore, the information of the unique identification of the moving image for retrieving the moving image depends on the content of the moving image can be extracted, consequently, the identical moving image can be retrieved and identified from the moving image by using the information of the unique identification of the moving image at high speed.

    摘要翻译： 根据本发明的用于检索运动图像的装置具有提取单元，用于从固定运动图像数据中提取运动图像的特征量的信息;提取单元，用于将运动图像的唯一识别信息提取到 根据运动图像的特征量的信息识别运动图像;以及检索单元，用于通过将运动图像的唯一标识的信息与 从对象运动图像预先提取的运动图像的唯一标识的信息。 因此，用于检索运动图像的运动图像的唯一标识的信息取决于可以提取的运动图像的内容，因此，可以通过使用运动图像的信息从运动图像中检索和识别相同的运动图像 高速运动图像的独特识别。