利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

147 条记录 (耗时 0.041 秒)

    Multi-image face-based image processing
    65.
    发明授权
    Multi-image face-based image processing 有权
    多图像面部图像处理

    公开(公告)号：US08582834B2

    公开(公告)日：2013-11-12

    申请号：US13221888

    申请日：2011-08-30

    申请人： Xin Tong ,  Adriana Dumitras ,  Andrew Bryant ,  Olivier Fedkiw ,  Daniel Pettigrew ,  Peter Warner

    发明人： Xin Tong ,  Adriana Dumitras ,  Andrew Bryant ,  Olivier Fedkiw ,  Daniel Pettigrew ,  Peter Warner

    IPC分类号： G06K9/00

    CPC分类号： G11B27/034 ,  G11B27/28 ,  G11B27/34 ,  H04N5/262

    摘要： Some embodiments provide a method for detecting and/or identifying a set of faces in a video frame and performing a set of image processing operations based on locations of the set of faces. In particular, the method identifies a set of respective locations of the set of faces in the video frame and applies one or more image processing operations based on the locations of the set of faces found in the video frame. The image processing operations include color correction operations, non-color correction operations, and image processing operations that modify areas inside or outside of the detected and/or identified faces. Additionally, some embodiments provide a graphical user interface for automatically applying image processing operations to an area of a video frame isolated by an ellipse-shaped mask. Furthermore, some embodiments provide a system for automatically applying image processing operations to an area of a video frame isolated by an ellipse-shaped mask.

    摘要翻译： 一些实施例提供了一种用于检测和/或识别视频帧中的一组面部并且基于该组面部的位置执行一组图像处理操作的方法。 具体地，该方法识别视频帧中的一组面部的相应位置的集合，并且基于在视频帧中找到的面部集合的位置来应用一个或多个图像处理操作。 图像处理操作包括修改检测到的和/或识别的面部内部或外部的区域的颜色校正操作，非颜色校正操作和图像处理操作。 另外，一些实施例提供了一种图形用户界面，用于将图像处理操作自动应用于由椭圆形掩模隔离的视频帧的区域。 此外，一些实施例提供了一种用于将图像处理操作自动应用于由椭圆形掩模隔离的视频帧的区域的系统。

    Method and system for video encoding using a variable number of B frames
    70.
    发明授权
    Method and system for video encoding using a variable number of B frames 有权
    使用可变数量的B帧进行视频编码的方法和系统

    公开(公告)号：US08130834B2

    公开(公告)日：2012-03-06

    申请号：US13025802

    申请日：2011-02-11

    申请人： Adriana Dumitras ,  Barin Geoffry Haskell

    发明人： Adriana Dumitras ,  Barin Geoffry Haskell

    IPC分类号： H04N7/32 ,  H04N7/36 ,  H04N7/28

    CPC分类号： H04N19/87 ,  H04N19/109 ,  H04N19/114 ,  H04N19/139 ,  H04N19/142 ,  H04N19/172

    摘要： An effective method for dynamically selecting the number of I, P and B frames during video coding is proposed. Short-term look-ahead analysis of a video sequence yields a variable number of B frames to be coded between any two stored pictures. The first picture of a group of frames (GOF) may be coded as a B picture. Motion speed is calculated for each picture of the GOF with respect to the first picture of the GOF. Subject to exceptions, as long as the subsequent pictures exhibit motion speeds that are similar and motion vector displacements that are co-linear with those of the first picture in the GOF, they may be coded as B pictures. When a picture is encountered having a motion speed that is not the same as that of the first picture in the GOF, the picture may be coded as a P picture. In some embodiments, a sequence of B pictures that terminates in a P picture may be called a “group of frames” (GOF).

    摘要翻译： 提出了一种在视频编码过程中动态选择I，P和B帧数量的有效方法。 视频序列的短期预先分析产生在任何两个存储的图像之间编码的可变数量的B帧。 一组帧（GOF）的第一图像可以被编码为B图像。 针对GOF的第一张照片计算GOF的每张照片的运动速度。 除了例外，只要后续图像显示与GOF中的第一图像的运动速度相似的运动速度和与第一图像的运动矢量位移共线的运动矢量位移，则它们可以被编码为B图像。 当遇到具有与GOF中的第一图像的运动速度不同的运动速度的图像时，图像可以被编码为P图像。 在一些实施例中，终止于P图像的B图像序列可以被称为“帧组”（GOF）。