Virtual view specification and synthesis in free viewpoint
    42.
    发明授权
    Virtual view specification and synthesis in free viewpoint 有权
    虚拟视图规范和自由观点的综合

    公开(公告)号:US07471292B2

    公开(公告)日:2008-12-30

    申请号:US11462327

    申请日:2006-08-03

    申请人: Baoxin Li

    发明人: Baoxin Li

    IPC分类号: G06T15/20 G06T15/00 G06T15/50

    摘要: A system that receives a first video stream of a scene having a first viewpoint and a second video stream having a second viewpoint wherein camera calibration between the first viewpoint and the second viewpoint is unknown. A viewer selects a viewer viewpoint generally between the first viewpoint and the second viewpoint, and the system synthesizes the viewer viewpoint based upon the first video stream and the second video stream.

    摘要翻译: 接收具有第一视点的场景的第一视频流和具有第二视点的第二视频流的系统,其中第一视点和第二视点之间的相机校准是未知的。 观众通常在第一视点和第二视点之间选择观众观点,并且系统基于第一视频流和第二视频流合成观众视点。

    Summarization of sumo video content
    47.
    发明授权
    Summarization of sumo video content 有权
    相扑视频内容的总结

    公开(公告)号:US07120873B2

    公开(公告)日:2006-10-10

    申请号:US10058684

    申请日:2002-01-28

    申请人: Baoxin Li

    发明人: Baoxin Li

    摘要: Summarization of video content, including sumo, may be achieved by identifying a plurality of segments of a video based upon an event that is characterized by a start time of sumo and an end time. One appropriate start time of an event may be sumo wrestlers'initial charge towards one another. One appropriate end time may be when one wrestler wins the match. The summarization of the video includes the plurality of segments, where the summarization includes fewer frames than the video.

    摘要翻译: 可以通过基于由sumo和结束时间的开始时间表征的事件来识别视频的多个片段来实现包括相机的视频内容的总结。 事件的一个适当的开始时间可能是相扑者的初始收费。 一个适当的结束时间可能是当一个摔跤手赢得比赛时。 视频的总结包括多个段,其中摘要包括比视频少的帧。

    Image background replacement method

    公开(公告)号:US06909806B2

    公开(公告)日:2005-06-21

    申请号:US10970096

    申请日:2004-10-20

    申请人: Baoxin Li

    发明人: Baoxin Li

    CPC分类号: G06T11/00 H04N1/3871

    摘要: An image's pixels are initially segmented into pixels of the image foreground and background by comparing the pixels of the image to updated models of background reference pixels. Pixel structures are identified in the image. The probability that a pixel is in the background or foreground is refined by considering the initial segmentation of the pixel's neighbors and the pixel's membership in a pixel structure. If a pixel is identified as a background pixel it is replaced by a pixel of a new background.