公开(公告)号：US08406483B2

公开(公告)日：2013-03-26

申请号：US12492417

申请日：2009-06-26

申请人： Cha Zhang ,  Xiaogang Wang ,  Zhengyou Zhang

发明人： Cha Zhang ,  Xiaogang Wang ,  Zhengyou Zhang

IPC分类号： G06K9/62

CPC分类号： G06K9/6256 ,  G06K9/00248 ,  G06K9/4671 ,  G06K2009/4666

摘要： Techniques for face verification are described. Local binary pattern (LBP) features and boosting classifiers are used to verify faces in images. A boosted multi-task learning algorithm is used for face verification in images. Finally, boosted face verification is used to verify faces in videos.

摘要翻译： 描述面部验证技术。 本地二进制模式（LBP）功能和增强分类器用于验证图像中的人脸。 增强的多任务学习算法用于图像中的面部验证。 最后，提升的面部验证用于验证视频中的人脸。

公开(公告)号：US20120287223A1

公开(公告)日：2012-11-15

申请号：US13104984

申请日：2011-05-11

申请人： Cha Zhang ,  Timothy A. Large ,  Zhengyou Zhang ,  Ruigang Yang

发明人： Cha Zhang ,  Timothy A. Large ,  Zhengyou Zhang ,  Ruigang Yang

IPC分类号： H04N7/15

CPC分类号： H04N7/144 ,  H04N7/155

摘要： The described implementations relate to enhancement images, such as in videoconferencing scenarios. One system includes a poriferous display screen having generally opposing front and back surfaces. This system also includes a camera positioned proximate to the back surface to capture an image through the poriferous display screen.

摘要翻译： 所描述的实现涉及增强图像，例如在视频会议场景中。 一个系统包括具有大致相对的前表面和后表面的多孔显示屏。 该系统还包括靠近后表面定位的照相机，以通过穿孔显示屏捕获图像。

公开(公告)号：US20120242810A1

公开(公告)日：2012-09-27

申请号：US13490341

申请日：2012-06-06

申请人： Dinei Afonso Ferreira Florencio ,  Cha Zhang

发明人： Dinei Afonso Ferreira Florencio ,  Cha Zhang

IPC分类号： H04N13/04

CPC分类号： H04N13/398 ,  H04N13/117 ,  H04N13/366 ,  H04N2213/006

摘要： Techniques and technologies are described herein for motion parallax three-dimensional (3D) imaging. Such techniques and technologies do not require special glasses, virtual reality helmets, or other user-attachable devices. More particularly, some of the described motion parallax 3D imaging techniques and technologies generate sequential images, including motion parallax depictions of various scenes derived from clues in views obtained of or created for the displayed scene.

摘要翻译： 这里描述了用于运动视差三维（3D）成像的技术和技术。 这样的技术和技术不需要特殊的眼镜，虚拟现实头盔或者其他可以连接的用户的装置。 更具体地，所描述的运动视差3D成像技术和技术中的一些产生顺序图像，包括从对所显示的场景获得或创建的视图中的线索导出的各种场景的运动视差描绘。

公开(公告)号：US08233353B2

公开(公告)日：2012-07-31

申请号：US11627799

申请日：2007-01-26

申请人： Cha Zhang ,  Dinei Florencio ,  Zhengyou Zhang

发明人： Cha Zhang ,  Dinei Florencio ,  Zhengyou Zhang

IPC分类号： H04S7/00 ,  H04R1/20

CPC分类号： H04R1/406 ,  H04R3/005 ,  H04S2400/11

摘要： A multi-sensor sound source localization (SSL) technique is presented which provides a true maximum likelihood (ML) treatment for microphone arrays having more than one pair of audio sensors. Generally, this is accomplished by selecting a sound source location that results in a time of propagation from the sound source to the audio sensors of the array, which maximizes a likelihood of simultaneously producing audio sensor output signals inputted from all the sensors in the array. The likelihood includes a unique term that estimates an unknown audio sensor response to the source signal for each of the sensors in the array.

摘要翻译： 提出了一种多传感器声源定位（SSL）技术，为具有多于一对音频传感器的麦克风阵列提供真正的最大似然（ML）处理。 通常，这是通过选择导致从声源传播到阵列的音频传感器的时间的声源位置来实现的，这最大化同时产生从阵列中的所有传感器输入的音频传感器输出信号的可能性。 可能性包括一个唯一的术语，它估计阵列中每个传感器对源信号的未知音频传感器响应。

公开(公告)号：US08098842B2

公开(公告)日：2012-01-17

申请号：US11692920

申请日：2007-03-29

申请人： Dinei Florencio ,  Cha Zhang ,  Demba Ba

发明人： Dinei Florencio ,  Cha Zhang ,  Demba Ba

IPC分类号： H04R3/00

CPC分类号： H04R3/005

摘要： A novel enhanced beamforming technique that improves beamforming operations by incorporating a model for the directional gains of the sensors, such as microphones, and provides means of estimating these gains. The technique forms estimates of the relative magnitude responses of the sensors (e.g., microphones) based on the data received at the array and includes those in the beamforming computations.

摘要翻译： 一种新颖的增强波束形成技术，其通过结合用于诸如麦克风的传感器的定向增益的模型来改进波束成形操作，并且提供估计这些增益的手段。 该技术基于在阵列处接收到的数据并且包括波束成形计算中的数据来形成传感器（例如，麦克风）的相对幅度响应的估计。

公开(公告)号：US20100329358A1

公开(公告)日：2010-12-30

申请号：US12491775

申请日：2009-06-25

申请人： Cha Zhang ,  Dinei Florencio

发明人： Cha Zhang ,  Dinei Florencio

IPC分类号： H04N7/26

CPC分类号： H04N19/54 ,  H04N19/115 ,  H04N19/187 ,  H04N19/597

摘要： Multi-view video that is being streamed to a remote device in real time may be encoded. Frames of a real-world scene captured by respective video cameras are received for compression. A virtual viewpoint, positioned relative to the video cameras, is used to determine expected contributions of individual portions of the frames to a synthesized image of the scene from the viewpoint position using the frames. For each frame, compression rates for individual blocks of a frame are computed based on the determined contributions of the individual portions of the frame. The frames are compressed by compressing the blocks of the frames according to their respective determined compression rates. The frames are transmitted in compressed form via a network to a remote device, which is configured to render the scene using the compressed frames.

摘要翻译： 可以对正在流式传输到远程设备的多视图视频进行编码。 接收由各个摄像机拍摄的真实世界场景的帧，用于压缩。 使用相对于摄像机定位的虚拟视点用于使用帧从视点位置确定帧的各个部分对场景的合成图像的预期贡献。 对于每个帧，基于帧的各个部分的确定的贡献来计算帧的各个块的压缩率。 通过根据它们各自确定的压缩率压缩帧的块来压缩帧。 这些帧通过网络以压缩形式传输到远程设备，远程设备被配置为使用压缩帧渲染场景。

公开(公告)号：US20080317371A1

公开(公告)日：2008-12-25

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。

公开(公告)号：US20080240463A1

公开(公告)日：2008-10-02

申请号：US11692920

申请日：2007-03-29

申请人： Dinei A. Florencio ,  Cha Zhang ,  Demba Elimane Ba

发明人： Dinei A. Florencio ,  Cha Zhang ,  Demba Elimane Ba

IPC分类号： H04R3/10

CPC分类号： H04R3/005

摘要： A novel enhanced beamforming technique that improves beamforming operations by incorporating a model for the directional gains of the sensors, such as microphones, and provides means of estimating these gains. The technique forms estimates of the relative magnitude responses of the sensors (e.g., microphones) based on the data received at the array and includes those in the beamforming computations.

摘要翻译： 一种新颖的增强波束形成技术，其通过结合用于诸如麦克风的传感器的定向增益的模型来改进波束成形操作，并且提供估计这些增益的手段。 该技术基于在阵列处接收到的数据并且包括波束成形计算中的数据来形成传感器（例如，麦克风）的相对幅度响应的估计。

公开(公告)号：US07065260B2

公开(公告)日：2006-06-20

申请号：US10963882

申请日：2004-10-13

申请人： Cha Zhang ,  Jin Li ,  Yunnan Wu

发明人： Cha Zhang ,  Jin Li ,  Yunnan Wu

IPC分类号： G06K9/36

CPC分类号： H04N19/597 ,  H04N19/13 ,  H04N19/61 ,  H04N19/615 ,  H04N19/619 ,  H04N19/63

摘要： Rebinning methods and arrangements are provided that significantly improve the 3D wavelet compression performance of the image based rendering data, such as, e.g., concentric mosaic image data. Through what is essentially a selective cutting and pasting process the image data is divided into stripes that are then used to form a set of multi-perspective panoramas. The rebinning process greatly improves the performance of the cross shot filtering, and thus improves the transform and coding efficiency of 3D wavelet codecs. While the region of support after rebinning may cease to be rectangular in some cases, a padding scheme and an arbitrary shape wavelet coder can be implemented to encode the result data volume of the smart rebinning. With an arbitrary shape wavelet codec, the rebinning outperforms MPEG-2 by 3.7 dB, outperforms direct 3D wavelet coder by 4.3 dB, and outperforms a reference block coder (RBC) by 3.2 dB on certain tested concentric mosaic image scenes. Hence, the rebinning process nearly quadruples the compression ratio for selected scenes. Additional methods and arrangements are provided that include selectively dividing the image data into slits and rebinning the slits into a huge 2D array, which is then compressed using conventional still image codecs, such as, JPEG.

公开(公告)号：US06993074B2

公开(公告)日：2006-01-31

申请号：US09812713

申请日：2001-03-19

申请人： Cha Zhang ,  Jin Li

发明人： Cha Zhang ,  Jin Li

IPC分类号： H04N7/18

CPC分类号： H04N19/23

摘要： Methods and arrangements are provided for compressing, transporting and decompressing/rendering concentric mosaic image data. The methods and arrangements compress concentric mosaic image data using reference block coding (RBC) techniques. Such RBC techniques selectively divide each of the frames of the concentric mosaic image data into blocks, and then predictively encodes each of these blocks. Some of the blocks are independently encoded as anchor blocks. Each of the remaining blocks is encoded as a predicted block with motion compensation to the anchor frame. The resulting compressed data file includes indexing information that can be used to selectively, randomly access the compressed data during decompression/rendering. A bitstream can be selectively tailored to provide portions of the compressed data file, as needed, for example, during rendering of a particular user-selected view of the concentric mosaic image scene.

摘要翻译： 提供了用于压缩，传送和解压缩/再现同心马赛克图像数据的方法和装置。 方法和布置使用参考块编码（RBC）技术压缩同心马赛克图像数据。 这种RBC技术有选择地将同心马赛克图像数据的每个帧划分成块，然后预测地对这些块中的每一个进行编码。 一些块被独立地编码为锚块。 每个剩余的块被编码为具有对锚帧的运动补偿的预测块。 所得到的压缩数据文件包括可用于在解压缩/渲染期间选择性地随机访问压缩数据的索引信息。 比特流可以被选择性地定制以根据需要提供压缩数据文件的部分，例如在呈现同心马赛克图像场景的特定用户选择的视图期间。