MERGING OF A VIDEO AND STILL PICTURES OF THE SAME EVENT, BASED ON GLOBAL MOTION VECTORS OF THIS VIDEO
    1.
    发明申请
    MERGING OF A VIDEO AND STILL PICTURES OF THE SAME EVENT, BASED ON GLOBAL MOTION VECTORS OF THIS VIDEO 审中-公开
    根据本视频的全球运动矢量,合并视频和静止图像

    公开(公告)号:WO2010058334A1

    公开(公告)日:2010-05-27

    申请号:PCT/IB2009/055051

    申请日:2009-11-13

    CPC classification number: G11B27/034 G11B27/036

    Abstract: It is quite common for users to have both video and photo material that refer to the same event. Adding photos to home videos enriches the content. However, just adding still photos to a video sequence has a disturbing effect. The invention relates to a method to seamlessly integrate photos into the video by creating a virtual camera motion in the photo that is aligned with the estimated camera motion in the video. A synthesized video sequence is created by estimating a video camera motion in the video sequence at an insertion position in the video sequence at which the still photo is to be included, creating a virtual video sequence of sub frames of the still photo where the virtual video sequence has a virtual camera motion correlated to the video camera motion at the insertion position.

    Abstract translation: 使用者同时参与同一个活动的影片和照片资料很常见。 将照片添加到家庭影片丰富了内容。 但是,只要将静态照片添加到视频序列就会产生令人不安的效果。 本发明涉及通过在照片中创建与视频中估计的相机运动对准的虚拟相机运动来将照片无缝地集成到视频中的方法。 通过在静止图像被包括的视频序列中的插入位置估计视频序列中的摄像机运动来创建合成视频序列,创建静态照片的子帧的虚拟视频序列,其中虚拟视频 序列具有与插入位置处的摄像机运动相关的虚拟相机运动。

Patent Agency Ranking