利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

17 条记录 (耗时 0.017 秒)

    CONTOUR FINDING IN SEGMENTATION OF VIDEO SEQUENCES
    2.
    发明授权
    CONTOUR FINDING IN SEGMENTATION OF VIDEO SEQUENCES 有权

    公开(公告)号：EP1969559B1

    公开(公告)日：2018-09-05

    申请号：EP05821518.7

    申请日：2005-12-30

    申请人： Telecom Italia S.p.A.

    发明人： ROSSATO, Luca ,  VARESIO, Andrea

    IPC分类号： G06T5/00

    CPC分类号： G06T7/155 ,  G06T7/12 ,  G06T7/194 ,  G06T2207/10016

    摘要： A method of image processing includes: receiving at least one video frame of a video sequence, the at least one video frame including at least one foreground subject and a background; and processing the at least one video frame so as to separate the at least one foreground subject from the background. The processing includes: generating a pixel mask containing information indicating, for each pixel of the at least one video frame, whether the pixel belongs to the foreground subject or to the background, and determining contours of the at least one foreground subject on the pixel mask. The determining of the contours includes for each pixel in the at least one video frame; based on the information included in the pixel mask, determining whether at least one pixel border belongs to a contour of the at least one foreground subject, the at least one pixel border separating the pixel from a respective at least one adjacent pixel.

    EDGE COMPARISON IN SEGMENTATION OF VIDEO SEQUENCES
    4.
    发明公开
    EDGE COMPARISON IN SEGMENTATION OF VIDEO SEQUENCES 有权
    边沿控制形态学闭幕视频序列中的分段

    公开(公告)号：EP1969560A1

    公开(公告)日：2008-09-17

    申请号：EP05821689.6

    申请日：2005-12-30

    申请人： Telecom Italia S.p.A.

    发明人： ROSSATO, Luca ,  VARESIO, Andrea

    IPC分类号： G06T5/00

    CPC分类号： G06K9/38 ,  G06T7/12 ,  G06T7/155 ,  G06T7/194 ,  G06T2207/10016 ,  G06T2207/20081

    摘要： A method of image processing, comprising: receiving at least one video frame of a video sequence, the at least one video frame comprising at least one foreground subject and a background; and processing the at least one video frame so as to separate the at least one foreground subject from said background. The processing includes: obtaining a reference image including the background; comparing the at least one video frame to the reference image; and generating a pixel mask as a result of the comparison, the pixel mask indicating whether a pixel of the at least one video frame belongs to the foreground subject or to the background. The method further comprises at least partially determining edges of the at least one foreground subject in the at least one video frame, and modifying the pixel mask based on the determined foreground subject edges.

    CONFERENCE WHERE MIXING IS TIME CONTROLLED BY A RENDERING DEVICE
    6.
    发明公开
    CONFERENCE WHERE MIXING IS TIME CONTROLLED BY A RENDERING DEVICE 有权
    会议在驴友的再现装置是定时

    公开(公告)号：EP2103098A1

    公开(公告)日：2009-09-23

    申请号：EP06841205.5

    申请日：2006-12-29

    申请人： Telecom Italia S.p.A.

    发明人： VARESIO, Andrea

    IPC分类号： H04M3/56

    CPC分类号： H04M3/56 ,  H04M3/562 ,  H04M3/568 ,  H04N7/157 ,  H04N21/4788

    摘要： A telecommunications terminal (110c) hosting a conference mixer (205) adapted to enabling an at least audio conference between a first conference peer (105c) and at least two further conference peers (105a, 105b), the conference mixer comprising: for each of the at least two further conference peers, a respective first data buffer (430-1,430-2) configured to buffering portions of at least an audio data stream received from the respective conference peer; a first audio data stream portions mixer (430) fed by the first data buffers and configured to: a) get audio data stream portions buffered in the first data buffers; b) mix the audio data stream portions got from the first data buffers to produce a first mixed audio data portion; and c) feed the first mixed audio data portion to a rendering device (210c) of the telecommunications terminal, wherein the first audio data stream portions mixer is configured to perform operations a), b) and c) upon receipt of a notification (507) from the rendering device indicating that the rendering device is ready to render a new mixed audio data portion.

    SEGMENTATION OF VIDEO SEQUENCES
    7.
    发明公开
    SEGMENTATION OF VIDEO SEQUENCES 审中-公开
    SEGMENTIERUNG VON VIDEOSEQUENZEN

    公开(公告)号：EP1969561A1

    公开(公告)日：2008-09-17

    申请号：EP05825174.5

    申请日：2005-12-30

    申请人： Telecom Italia S.p.A.

    发明人： ROSSATO, Luca ,  VARESIO, Andrea ,  PORTA, Alessandro

    IPC分类号： G06T5/00

    CPC分类号： G06T7/155 ,  G06T7/12 ,  G06T7/194 ,  G06T2207/10016 ,  G06T2207/20081

    摘要： A method of image processing, comprising: providing a data processing apparatus, comprising a central processing unit and a graphics processing unit; feeding at least one video frame of a video sequence to the data processing apparatus, the at least one video frame comprising at least one foreground subject and a background; processing the at least one video frame in the data processing apparatus so as to separate the at least one foreground subject from the background. The processing is at least partially performed by the processors of the graphics processing unit.

    摘要翻译： 一种图像处理方法，包括：提供包括中央处理单元和图形处理单元的数据处理装置; 将至少一个视频序列的视频帧馈送到所述数据处理设备，所述至少一个视频帧包括至少一个前景主题和背景; 以及处理所述数据处理装置中的所述至少一个视频帧，以将所述至少一个前景对象与所述背景分离。 处理至少部分地由图形处理单元的处理器执行。

    CONTOUR FINDING IN SEGMENTATION OF VIDEO SEQUENCES
    8.
    发明公开
    CONTOUR FINDING IN SEGMENTATION OF VIDEO SEQUENCES 审中-公开
    KONTURFINDUNG BEI DER SEGMENTIERUNG VON VIDEOSEQUENZEN

    公开(公告)号：EP1969559A1

    公开(公告)日：2008-09-17

    申请号：EP05821518.7

    申请日：2005-12-30

    申请人： Telecom Italia S.p.A.

    发明人： ROSSATO, Luca ,  VARESIO, Andrea

    IPC分类号： G06T5/00

    CPC分类号： G06T7/155 ,  G06T7/12 ,  G06T7/194 ,  G06T2207/10016

    摘要： A method of image processing includes: receiving at least one video frame of a video sequence, the at least one video frame including at least one foreground subject and a background; and processing the at least one video frame so as to separate the at least one foreground subject from the background. The processing includes: generating a pixel mask containing information indicating, for each pixel of the at least one video frame, whether the pixel belongs to the foreground subject or to the background, and determining contours of the at least one foreground subject on the pixel mask. The determining of the contours includes for each pixel in the at least one video frame; based on the information included in the pixel mask, determining whether at least one pixel border belongs to a contour of the at least one foreground subject, the at least one pixel border separating the pixel from a respective at least one adjacent pixel.

    摘要翻译： 一种图像处理方法包括：接收视频序列的至少一个视频帧，所述至少一个视频帧包括至少一个前景对象和背景; 以及处理所述至少一个视频帧，以便将所述至少一个前景被摄体与所述背景分离。 该处理包括：生成包含信息的像素掩码，该信息指示至少一个视频帧的每个像素，该像素是否属于前景对象或背景，以及确定像素掩码上的至少一个前景对象的轮廓 。 轮廓的确定包括对于至少一个视频帧中的每个像素; 基于包括在所述像素掩模中的信息，确定至少一个像素边界是否属于所述至少一个前景对象的轮廓，所述至少一个像素边界将所述像素与相应的至少一个相邻像素分开。