Binary mask interpolation
    41.
    发明授权
    Binary mask interpolation 有权
    二进制掩码插值

    公开(公告)号:US07440613B2

    公开(公告)日:2008-10-21

    申请号:US10661315

    申请日:2003-09-12

    申请人: Xun Xu

    发明人: Xun Xu

    IPC分类号: G06K9/34

    摘要: Generating a transitional mask is described. A video segmentation generates a first binary mask and a second binary mask. Binary mask interpolation interpolates the first binary mask and the second binary mask to generate one or more transitional binary masks.

    摘要翻译: 描述生成过渡掩码。 视频分割产生第一二进制掩码和第二二进制掩码。 二进制掩码插值插值第一个二进制掩码和第二个二进制掩码,以生成一个或多个过渡二进制掩码。

    ENTROPY DECODING METHODS AND APPARATUS
    42.
    发明申请
    ENTROPY DECODING METHODS AND APPARATUS 有权
    诠释方法和设备

    公开(公告)号:US20080048893A1

    公开(公告)日:2008-02-28

    申请号:US11844319

    申请日:2007-08-23

    申请人: Xun Xu

    发明人: Xun Xu

    IPC分类号: H03M7/00

    摘要: Methods and apparatus for entropy decoding are disclosed. Compressed input data representing one or more signals is loaded into one or more registers. A first candidate value for a most probable signal case is prepared from the input data. A second candidate value for a least probable signal case is prepared from the input data. A final signal value for the one or more signals is selected from the first and second candidate values and an output bin value is generated based on the final signal value. A processor readable medium having embodied therein processor readable instructions for implementing the method for entropy decoding is also disclosed. In addition, a method of avoiding a branch instruction in an electronic processing algorithm is disclosed.

    摘要翻译: 公开了用于熵解码的方法和装置。 代表一个或多个信号的压缩输入数据被加载到一个或多个寄存器中。 从输入数据准备最可能的信号情况的第一候选值。 从输入数据准备最小可能信号情况的第二候选值。 从第一和第二候选值中选择一个或多个信号的最终信号值,并且基于最终信号值生成输出bin值。 还公开了一种其中包含用于实现用于熵解码的方法的处理器可读指令的处理器可读介质。 此外,公开了一种在电子处理算法中避免分支指令的方法。

    Multiple thresholding for video frame segmentation
    43.
    发明授权
    Multiple thresholding for video frame segmentation 有权
    视频帧分割的多重阈值

    公开(公告)号:US07277580B2

    公开(公告)日:2007-10-02

    申请号:US10319145

    申请日:2002-12-12

    申请人: Xun Xu

    发明人: Xun Xu

    IPC分类号: G06K9/00 G06K9/34

    摘要: Intensity of each pixel in a source video frame is compared with intensities of one or more corresponding pixels in a reference video frame to calculate one or more intensity differences for each pixel in the source video frame. Further, a determination is made for each pixel in the source video frame, based on the intensity differences and multiple threshold sets, as to whether each pixel in the source video frame is a foreground pixel or a background pixel.

    摘要翻译: 将源视频帧中的每个像素的强度与参考视频帧中的一个或多个对应像素的强度进行比较,以计算源视频帧中的每个像素的一个或多个亮度差。 此外,基于强度差和多个阈值集,确定源视频帧中的每个像素是前景像素还是背景像素,确定源视频帧中的每个像素。

    Voting-based video background mosaicking
    44.
    发明授权
    Voting-based video background mosaicking 有权
    基于投票的视频背景镶嵌

    公开(公告)号:US07257252B2

    公开(公告)日:2007-08-14

    申请号:US10318563

    申请日:2002-12-12

    申请人: Xun Xu

    发明人: Xun Xu

    IPC分类号: G06K9/34

    摘要: For each pixel in a video background mosaic, intensity values associated with corresponding pixels in multiple video frames are collected, and an intensity value associated with the majority of the corresponding pixels is selected. The selected intensity value defines intensity of the pixel in the video background mosaic.

    摘要翻译: 对于视频背景马赛克中的每个像素,收集与多个视频帧中的对应像素相关联的强度值,并且选择与大部分相应像素相关联的强度值。 所选择的强度值定义视频背景马赛克中像素的强度。

    Hybrid global motion estimator for video encoding
    45.
    发明申请
    Hybrid global motion estimator for video encoding 审中-公开
    用于视频编码的混合全局运动估计器

    公开(公告)号:US20060062303A1

    公开(公告)日:2006-03-23

    申请号:US10943625

    申请日:2004-09-17

    申请人: Xun Xu

    发明人: Xun Xu

    摘要: A method and system for detecting and estimating global motion among video frames includes down sampling a first and a second video frame to a low resolution version (I1, I2) and performing a block matching on the low resolution images by treating both images (I1, I2) as two single blocks. This method and system therefore utilizes low-frequency picture information, resulting in a motion vector (U,V), and the second low resolution image I2 being segmented into two regions, a region of high matching difference and a region of low matching difference. The method and system then refines the motion vector (U,V) by calculating the horizontal, vertical, zooming and rotation motion components (Tx, Ty, Tz, Tr), based on the pixels in the region of low matching difference, by gradient-based method.

    摘要翻译: 用于检测和估计视频帧中的全局运动的方法和系统包括将第一和第二视频帧下采样到低分辨率版本(I 1,I 2),并通过处理两个图像对低分辨率图像执行块匹配( I 1,I 2)作为两个单独的块。 因此,该方法和系统利用低频图像信息,得到运动矢量(U,V),将第二低分辨率图像I 2分割成两个区域,高匹配差区域和低匹配差区域 。 然后,该方法和系统通过计算水平,垂直,变焦和旋转运动分量(T,T,T,T,SUB) 通过基于梯度的方法,基于低匹配差的区域中的像素,以及/或者,Z )。