利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

166 条记录 (耗时 0.031 秒)

    System and method for image-based surface detail transfer
    43.
    发明授权
    System and method for image-based surface detail transfer 失效

    公开(公告)号：US07020347B2

    公开(公告)日：2006-03-28

    申请号：US10126118

    申请日：2002-04-18

    申请人： Zhengyou Zhang ,  Zicheng Liu ,  Ying Shan

    发明人： Zhengyou Zhang ,  Zicheng Liu ,  Ying Shan

    IPC分类号： G06K9/36 ,  G09G5/00

    CPC分类号： G06T15/04 ,  G06T11/001

    摘要： A system and method, called Image-Based Surface Detail Transfer, to transfer geometric details from one surface of an object in an image to another with simple 2D image operations. The basic observation is that, without knowing its 3D geometry, geometric details (local deformations) can be extracted from a single image of an object in a way independent of its surface reflectance, and furthermore, these geometric details can be transferred to modify the appearance of other objects directly in images. Examples are shown including surface detail transfer between real objects, as well as between real and synthesized objects.

    Method and apparatus for multi-sensory speech enhancement
    46.
    发明申请
    Method and apparatus for multi-sensory speech enhancement 有权
    多感官语音增强的方法和装置

    公开(公告)号：US20050114124A1

    公开(公告)日：2005-05-26

    申请号：US10724008

    申请日：2003-11-26

    申请人： Zicheng Liu ,  Michael Sinclair ,  Alejandro Acero ,  Xuedong Huang ,  James Droppo ,  Li Deng ,  Zhengyou Zhang ,  Yanli Zheng

    发明人： Zicheng Liu ,  Michael Sinclair ,  Alejandro Acero ,  Xuedong Huang ,  James Droppo ,  Li Deng ,  Zhengyou Zhang ,  Yanli Zheng

    IPC分类号： G10L21/02

    CPC分类号： G10L21/0208 ,  G10L2021/02165

    摘要： A method and system use an alternative sensor signal received from a sensor other than an air conduction microphone to estimate a clean speech value. The estimation uses either the alternative sensor signal alone, or in conjunction with the air conduction microphone signal. The clean speech value is estimated without using a model trained from noisy training data collected from an air conduction microphone. Under one embodiment, correction vectors are added to a vector formed from the alternative sensor signal in order to form a filter, which is applied to the air conductive microphone signal to produce the clean speech estimate. In other embodiments, the pitch of a speech signal is determined from the alternative sensor signal and is used to decompose an air conduction microphone signal. The decomposed signal is then used to determine a clean signal estimate.

    摘要翻译： 一种方法和系统使用从除空气传导麦克风以外的传感器接收的替代传感器信号来估计干净的语音值。 该估计单独使用替代传感器信号，或者与导气麦克风信号一起使用。 无需使用从空气传导麦克风收集的噪声训练数据训练的模型来估计干净的语音值。 在一个实施例中，校正矢量被添加到由替代传感器信号形成的矢量中，以形成滤波器，该滤波器被施加到空气传导麦克风信号以产生干净的语音估计。 在其他实施例中，语音信号的音调由替代传感器信号确定，并用于分解空气传导麦克风信号。 然后使用分解的信号来确定干净的信号估计。

    Hierarchical filtered motion field for action recognition
    47.
    发明授权
    Hierarchical filtered motion field for action recognition 有权
    用于动作识别的层次滤波运动场

    公开(公告)号：US08639042B2

    公开(公告)日：2014-01-28

    申请号：US12820143

    申请日：2010-06-22

    申请人： Zicheng Liu ,  Yingli Tian ,  Liangliang Cao ,  Zhengyou Zhang

    发明人： Zicheng Liu ,  Yingli Tian ,  Liangliang Cao ,  Zhengyou Zhang

    IPC分类号： G06K9/62

    CPC分类号： G06K9/4642 ,  G06K9/6277 ,  G06T7/246 ,  G06T2207/30196

    摘要： Described is a hierarchical filtered motion field technology such as for use in recognizing actions in videos with crowded backgrounds. Interest points are detected, e.g., as 2D Harris corners with recent motion, e.g. locations with high intensities in a motion history image (MHI). A global spatial motion smoothing filter is applied to the gradients of MHI to eliminate low intensity corners that are likely isolated, unreliable or noisy motions. At each remaining interest point, a local motion field filter is applied to the smoothed gradients by computing a structure proximity between sets of pixels in the local region and the interest point. The motion at a pixel/pixel set is enhanced or weakened based on its structure proximity with the interest point (nearer pixels are enhanced).

    摘要翻译： 描述了一种分层过滤的运动场技术，例如用于识别具有拥挤背景的视频中的动作。 检测到兴趣点，例如，作为具有最近运动的2D哈里斯角，例如， 在运动历史图像（MHI）中具有高强度的位置。 将全局空间运动平滑滤波器应用于MHI的梯度以消除可能是孤立的，不可靠的或噪声运动的低强度拐角。 在每个剩余的兴趣点处，通过计算局部区域中的像素集合和兴趣点之间的结构接近度，将局部运动场滤波器应用于平滑的梯度。 基于其与兴趣点的结构接近（更近的像素被增强），像素/像素集合处的运动被增强或削弱。

    Recognizing actions of animate objects in video
    48.
    发明授权
    Recognizing actions of animate objects in video 有权
    识别视频中动画对象的动作

    公开(公告)号：US08396247B2

    公开(公告)日：2013-03-12

    申请号：US12183078

    申请日：2008-07-31

    申请人： Zhengyou Zhang ,  Wanqing Li ,  Zicheng Liu

    发明人： Zhengyou Zhang ,  Wanqing Li ,  Zicheng Liu

    IPC分类号： G06K9/00

    CPC分类号： G06K9/6892 ,  G06K9/00362 ,  G06K9/00711

    摘要： A system that facilitates automatically determining an action of an animate object is described herein. The system includes a receiver component that receives video data that includes images of an animate object. The system additionally includes a determiner component that accesses a data store that includes an action graph and automatically determines an action undertaken by the animate object in the received video data based at least in part upon the action graph. The action graph comprises a plurality of nodes that are representative of multiple possible postures of the animate object. At least one node in the action graph is shared amongst multiple actions represented in the action graph.

    摘要翻译： 这里描述了便于自动确定动画对象的动作的系统。 该系统包括接收包括动画对象的图像的视频数据的接收器组件。 该系统还包括确定器组件，其访问包括动作图的数据存储，并至少部分地基于动作图，自动地确定由所接收的视频数据中的动画对象所执行的动作。 动作图包括代表动画对象的多个可能姿势的多个节点。 动作图中至少有一个节点在动作图中表示的多个动作中共享。

    Ambulatory presence features
    49.
    发明授权
    Ambulatory presence features 有权
    动态存在功能

    公开(公告)号：US08253774B2

    公开(公告)日：2012-08-28

    申请号：US12413782

    申请日：2009-03-30

    申请人： Christian Huitema ,  William A. S. Buxton ,  John E. Paff ,  Zicheng Liu ,  Rajesh Kutpadi Hegde ,  Zhengyou Zhang ,  Kori Marie Quinn ,  Jin Li ,  Michel Pahud

    发明人： Christian Huitema ,  William A. S. Buxton ,  John E. Paff ,  Zicheng Liu ,  Rajesh Kutpadi Hegde ,  Zhengyou Zhang ,  Kori Marie Quinn ,  Jin Li ,  Michel Pahud

    IPC分类号： H04N7/14

    CPC分类号： H04N7/147 ,  H04L12/1827 ,  H04N7/142 ,  H04N7/15 ,  H04N21/42203 ,  H04N21/4223 ,  H04N21/44213 ,  H04N21/4788 ,  H04N2007/145

    摘要： The claimed subject matter provides a system and/or a method that facilitates managing one or more devices utilized for communicating data within a telepresence session. A telepresence session can be initiated within a communication framework that includes two or more virtually represented users that communicate therein. A device can be utilized by at least one virtually represented user that enables communication within the telepresence session, the device includes at least one of an input to transmit a portion of a communication to the telepresence session or an output to receive a portion of a communication from the telepresence session. A detection component can adjust at least one of the input related to the device or the output related to the device based upon the identification of a cue, the cue is at least one of a movement detected, an event detected, or an ambient variation.

    摘要翻译： 所要求保护的主题提供了一种有助于管理用于在远程呈现会话内传送数据的一个或多个设备的系统和/或方法。 可以在通信框架内启动远程呈现会话，该通信框架包括在其中通信的两个或更多虚拟表示的用户。 至少一个虚拟表示的用户可以利用设备来实现远程呈现会话内的通信，该设备包括将通信的一部分传送到远程呈现会话的输入或输出以接收通信的一部分中的至少一个 从远程呈现会话。 检测部件可以基于提示的识别来调整与设备相关的输入或输出中的至少一个，所述提示是检测到的运动，检测到的事件或环境变化中的至少一个。

    Video noise reduction
    50.
    发明授权
    Video noise reduction 有权
    视频降噪

    公开(公告)号：US08031967B2

    公开(公告)日：2011-10-04

    申请号：US11765029

    申请日：2007-06-19

    申请人： Cha Zhang ,  Zhengyou Zhang ,  Zicheng Liu

    发明人： Cha Zhang ,  Zhengyou Zhang ,  Zicheng Liu

    IPC分类号： G06K9/40

    CPC分类号： G06T5/002 ,  G06T2207/10016 ,  H04N5/14 ,  H04N5/21

    摘要： A video noise reduction technique is presented. Generally, the technique involves first decomposing each frame of the video into low-pass and high-pass frequency components. Then, for each frame of the video after the first frame, an estimate of a noise variance in the high pass component is obtained. The noise in the high pass component of each pixel of each frame is reduced using the noise variance estimate obtained for the frame under consideration, whenever there has been no substantial motion exhibited by the pixel since the last previous frame. Evidence of motion is determined by analyzing the high and low pass components.

    摘要翻译： 提出了一种视频降噪技术。 通常，该技术首先将视频的每帧分解为低通和高通频率分量。 然后，对于第一帧之后的视频的每帧，获得高通分量中的噪声方差的估计。 每当从最后一帧起就没有像素所呈现的实质运动时，使用针对所考虑的帧获得的噪声方差估计，减少每帧的每个像素的高通分量中的噪声。 通过分析高通和低通分量来确定运动的证据。