专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20100315905A1 MULTIMODAL OBJECT LOCALIZATION 有权
标题翻译：多目标对象本地化
公开(公告)号：US20100315905A1
公开(公告)日：2010-12-16
申请号：US12482773
申请日：2009-06-11
申请人： Bowon Lee , Kar-Han Tan
发明人： Bowon Lee , Kar-Han Tan
IPC分类号： G01S3/80
CPC分类号： G01S5/28
摘要： Various embodiments of the present invention are directed to systems and methods for multimodal object localization using one or more depth sensors and two or more microphones. In one aspect, a method comprises capturing three-dimensional images of a region of space wherein the object is located. The images comprise three-dimensional depth sensor observations. The method collects ambient audio generated by the object, providing acoustic observation regarding the ambient audio time difference of arrival at the audio sensors. The method determines a coordinate location of the object corresponding to the maximum of a joint probability distribution characterizing the probability of the acoustic observations emanating from each coordinate location in the region of space and the probability of each coordinate location in the region of space given depth sensor observations.
摘要翻译：本发明的各种实施例涉及使用一个或多个深度传感器和两个或更多个麦克风的多模态对象定位的系统和方法。一方面，一种方法包括捕获物体所位于的空间区域的三维图像。图像包括三维深度传感器观察。该方法收集由对象产生的环境音频，提供关于到达音频传感器的环境音频时差的声学观察。该方法确定对应于对应于联合概率分布的最大值的对象的坐标位置，其表征从空间区域中的每个坐标位置发出的声学观察的概率和给定深度传感器的空间区域中的每个坐标位置的概率观察。

2. 发明授权

US08174932B2 Multimodal object localization 有权
标题翻译：多模态对象定位
公开(公告)号：US08174932B2
公开(公告)日：2012-05-08
申请号：US12482773
申请日：2009-06-11
申请人： Bowon Lee , Kar-Han Tan
发明人： Bowon Lee , Kar-Han Tan
IPC分类号： G01S3/80
CPC分类号： G01S5/28
摘要： Various embodiments of the present invention are directed to systems and methods for multimodal object localization using one or more depth sensors and two or more microphones. In one aspect, a method comprises capturing three-dimensional images of a region of space wherein the object is located. The images comprise three-dimensional depth sensor observations. The method collects ambient audio generated by the object, providing acoustic observation regarding the ambient audio time difference of arrival at the audio sensors. The method determines a coordinate location of the object corresponding to the maximum of a joint probability distribution characterizing the probability of the acoustic observations emanating from each coordinate location in the region of space and the probability of each coordinate location in the region of space given depth sensor observations.
摘要翻译：本发明的各种实施例涉及使用一个或多个深度传感器和两个或更多个麦克风的多模态对象定位的系统和方法。一方面，一种方法包括捕获物体所位于的空间区域的三维图像。图像包括三维深度传感器观察。该方法收集由对象产生的环境音频，提供关于到达音频传感器的环境音频时差的声学观察。该方法确定对应于对应于联合概率分布的最大值的对象的坐标位置，其表征从空间区域中的每个坐标位置发出的声学观察的概率和给定深度传感器的空间区域中的每个坐标位置的概率观察。

3. 发明授权

US08558894B2 Support for audience interaction in presentations 有权
标题翻译：支持演讲中的观众互动
公开(公告)号：US08558894B2
公开(公告)日：2013-10-15
申请号：US12947191
申请日：2010-11-16
申请人： Kar-Han Tan , Bowon Lee
发明人： Kar-Han Tan , Bowon Lee
IPC分类号： H04N5/225
CPC分类号： H04N7/16 , G09B5/06 , G09B5/08 , H04N7/142
摘要： A method for presentation interaction. The method includes, receiving by a computer system an indication of a manual selection of a region proximate to an audience member of an audience wherein the indication is received via an interaction with a displayed image of the audience. The method also includes utilizing a microphone array communicatively coupled with a beam-forming component of the computer system to focus audio pickup from the region proximate to the audience member in response to receiving the indication. The method also includes displaying an enhanced image of the region proximate to the audience member using the computer system in response to receiving the indication.
摘要翻译：呈现交互的方法。该方法包括：由计算机系统接收关于接近受众的观众成员的区域的手动选择的指示，其中通过与观众的显示图像的交互来接收该指示。该方法还包括利用与计算机系统的波束形成部件通信耦合的麦克风阵列，以便响应于接收到指示，将来自接近受众成员的区域的音频拾取聚焦。该方法还包括响应于接收到指示而使用计算机系统显示接近受众成员的区域的增强图像。

4. 发明授权

US09143724B2 Telepresence portal system 有权
标题翻译：网真门户系统
公开(公告)号：US09143724B2
公开(公告)日：2015-09-22
申请号：US14123350
申请日：2011-07-06
申请人： Kar-Han Tan
发明人： Kar-Han Tan
IPC分类号： H04N7/14 , H04N7/15 , H04N9/31
CPC分类号： H04N7/144 , H04N7/147 , H04N7/15 , H04N9/3147
摘要： Embodiments of the present invention disclose a telepresence portal system. According to one embodiment, the telepresence portal system includes a host portal having a plurality of host transparent displays arranged to face different sides of a host user. Furthermore, each host transparent display is associated with an image capturing device for capturing different viewpoint images of the host user. A remote portal is in communication with the host portal and includes a plurality of remote transparent displays arranged to correspond with the positions of the host transparent displays. In addition, each remote transparent display renders a viewpoint image of the host user on the corresponding remote transparent display for view by at least one remote user.
摘要翻译：本发明的实施例公开了一种远程呈现门户系统。根据一个实施例，远程呈现门户系统包括具有多个主机透明显示器的主机门户，该多个主机透明显示器布置成面对主机用户的不同侧面。此外，每个主机透明显示器与用于捕获主机用户的不同视点图像的图像捕获设备相关联。远程门户与主机门户通信，并且包括布置成与主机透明显示器的位置对应的多个远程透明显示器。此外，每个远程透明显示器将主用户的视点图像呈现在相应的远程透明显示器上，供至少一个远程用户观看。

5. 发明授权

US08908008B2 Methods and systems for establishing eye contact and accurate gaze in remote collaboration 有权
标题翻译：在远程协作中建立眼神接触和准确凝视的方法和系统
公开(公告)号：US08908008B2
公开(公告)日：2014-12-09
申请号：US13806531
申请日：2010-07-16
申请人： Kar-Han Tan , Ian N. Robinson
发明人： Kar-Han Tan , Ian N. Robinson
IPC分类号： H04N7/14 , H04N7/15 , H04N9/31
CPC分类号： H04N7/144 , H04N7/15 , H04N9/3179
摘要： In one aspect, a method includes capturing images of a first participant through a display using a camera. The display is located between the first participant and the camera. A video stream of images of a second participant is also received. The images of the second participant are shifted in accordance with a shift vector. The shift vector places the images of the second participant's face in approximate alignment with the eyes of the first participant and the lens of the camera. The shifted images are projected on the display using a projector.
摘要翻译：一方面，一种方法包括通过使用相机的显示来捕获第一参与者的图像。显示器位于第一参与者和相机之间。还接收第二参与者的图像的视频流。根据移位矢量移动第二参与者的图像。移动矢量将第二参与者的脸部的图像与第一参与者的眼睛和相机的镜头大致对准。移动的图像使用投影仪投影在显示器上。

6. 发明申请

US20130093838A1 METHODS AND SYSTEMS FOR ESTABLISHING EYE CONTACT AND ACCURATE GAZE IN REMOTE COLLABORATION 有权
标题翻译：用于在远程协作中建立眼睛接触和精确大小的方法和系统
公开(公告)号：US20130093838A1
公开(公告)日：2013-04-18
申请号：US13806531
申请日：2010-07-16
申请人： Kar-Han Tan , Ian N. Robinson
发明人： Kar-Han Tan , Ian N. Robinson
IPC分类号： H04N7/14
CPC分类号： H04N7/144 , H04N7/15 , H04N9/3179
摘要： Embodiments of the present invention are directed to video-conferencing systems that create eye contact and accurate gaze awareness between video-conferencing participants. In one aspect, a method includes capturing images of a first participant through a display using a camera (801). The display is located between the first participant and the camera. A video stream encoding images of a second participant (802,905) is also received. The images of the second participant are shifted in accordance with a shift vector. The shift vector places the images of the second participant's face in approximate alignment with the eyes of the first participant and the lens of the camera (803). The shifted images are projected on the display using a projector (804).
摘要翻译：本发明的实施例涉及视频会议系统，其在视频会议参与者之间产生眼睛接触和准确的凝视感知。一方面，一种方法包括使用相机（801）通过显示器捕获第一参与者的图像。显示器位于第一参与者和相机之间。还接收编码第二参与者（802,905）的图像的视频流。根据移位矢量移动第二参与者的图像。移位矢量将第二参与者的脸部的图像与第一参与者的眼睛和相机的镜头大致对准（803）。使用投影仪将移动后的图像投影在显示器上（804）。

7. 发明申请

US20120274732A1 SYSTEMS AND METHODS FOR REDUCING VIDEO CROSSTALK 有权
标题翻译：用于减少视频CROSSTALK的系统和方法
公开(公告)号：US20120274732A1
公开(公告)日：2012-11-01
申请号：US13098277
申请日：2011-04-29
申请人： Kar-Han Tan , Ramin Samadani
发明人： Kar-Han Tan , Ramin Samadani
IPC分类号： H04N5/21 , H04N7/14
CPC分类号： H04N7/15
摘要： Methods and systems that reduce video crosstalk in video streams sent between participants in a video conference are disclosed. In one aspect, a method for reducing video crosstalk in a video stream sent from a local site to a remote site includes projecting a video stream of the remote site onto a screen at the local site. Each image in the video stream is dimmed according to a dimming factor of a dimming sequence. Crosstalk images of the local site are captured through the screen. Each crosstalk image is a blending of the image of the local site captured through the screen with a dimmed image of the remote site projected onto the screen. Images of the local site with reduced crosstalk are computed based on the dimming sequence. A video stream composed of the images of the local site with reduced crosstalk are sent to the remote site.
摘要翻译：公开了减少在视频会议中的参与者之间发送的视频流中的视频串扰的方法和系统。一方面，一种用于减少从本地站点发送到远程站点的视频流中的视频串扰的方法包括将远程站点的视频流投影到本地站点的屏幕上。视频流中的每个图像根据调光序列的调光因子而变暗。通过屏幕捕获本地站点的串扰图像。每个串扰图像是通过屏幕捕获的本地站点的图像与投影到屏幕上的远程站点的暗淡图像的混合。基于调光顺序计算串扰减小的本地站点图像。将由串扰减小的本地站点的图像组成的视频流发送到远程站点。

8. 发明申请

US20120274727A1 METHODS AND SYSTEMS FOR SHARING CONTENT VIA A COLLABORATION SCREEN 有权
标题翻译：通过协作屏幕共享内容的方法和系统
公开(公告)号：US20120274727A1
公开(公告)日：2012-11-01
申请号：US13097481
申请日：2011-04-29
申请人： Ian N. Robinson , Kar-Han Tan , Daniel George Gelb
发明人： Ian N. Robinson , Kar-Han Tan , Daniel George Gelb
IPC分类号： H04N7/15
CPC分类号： H04N7/15
摘要： Video conferencing methods and systems that enable shared content to be displayed in a separate window within a screen or in a separate display are described. In one aspect, a method for establishing a video conference with shared content using a computing device includes capturing images of a first participant through a screen using a camera. The screen is located between the first participant and the camera. The method also includes projecting images of a second participant on the screen to be viewed by the first participant using a projector, and displaying shared content separate from the images of the second participant. The shared content is to be presented in different format than the images of the second participant presented on the screen.
摘要翻译：描述使共享内容能够在屏幕或单独显示器中的单独窗口中显示的视频会议方法和系统。一方面，使用计算装置建立具有共享内容的视频会议的方法包括使用相机通过屏幕拍摄第一参与者的图像。屏幕位于第一个参与者和相机之间。该方法还包括投影屏幕上的第二参与者的图像，以使用投影仪由第一参与者观看，并且显示与第二参与者的图像分离的共享内容。共享内容将以与屏幕上呈现的第二参与者的图像不同的格式呈现。

9. 发明授权

US08260076B1 Constant time filtering 有权
标题翻译：恒定时间滤波
公开(公告)号：US08260076B1
公开(公告)日：2012-09-04
申请号：US12415962
申请日：2009-03-31
申请人： Qingxiong Yang , Kar-Han Tan
发明人： Qingxiong Yang , Kar-Han Tan
IPC分类号： G06K9/40 , G06F17/10 , H04B1/10
CPC分类号： G06F17/10 , G06T5/002 , G06T2207/20028 , G06T2207/20192
摘要： A system for filtering an image using a bilateral filter includes a receiver and a bilateral filter. The receiver is for receiving an image having a plurality of pixels. The bilateral filter is run in constant time and comprises a pixel value range determinor and a spatial filter. The pixel value range determinor is configured to determine a range of pixel values of the plurality of pixels. The spatial filter is configured to spatially filter at least one of the plurality of pixels. The spatial filter is further configured to perform over a plurality of pixel values in the range of pixel values.
摘要翻译：使用双边滤波器对图像进行滤波的系统包括接收机和双向滤波器。接收机用于接收具有多个像素的图像。双向滤波器在恒定时间内运行，包括像素值范围确定器和空间滤波器。像素值范围确定器被配置为确定多个像素的像素值的范围。空间滤波器被配置为对多个像素中的至少一个进行空间滤波。空间滤波器还被配置为在像素值的范围内执行多个像素值。

10. 发明授权

US08248410B2 Synthesizing detailed depth maps from images 有权
标题翻译：从图像合成详细的深度图
公开(公告)号：US08248410B2
公开(公告)日：2012-08-21
申请号：US12331084
申请日：2008-12-09
申请人： Kar-Han Tan
发明人： Kar-Han Tan
IPC分类号： G06K9/36
CPC分类号： G06T7/579 , G06T2207/10016
摘要： Disclosed are embodiments of systems and methods for synthesizing a detailed depth map from a video image. In embodiments, the motion vectors decoded from a video stream may be classified into groups by the application of K-Model clustering techniques based on an affine model. In embodiments, a coarse depth map of the image pixels may be generated using the image segmented according to the motion vector clusters. In embodiments, high resolution gradient maps of the image may be generated using the coarse depth map as well as edge information from the image. In embodiments, a surface reconstruction algorithm, such as the Frankot-Chellappa algorithm, may be applied to the high resolution gradient maps to synthesize a detailed depth map of the image. A detailed depth map of an image may be used to render a three-dimensional surface, for example.
摘要翻译：公开了用于从视频图像合成详细深度图的系统和方法的实施例。在实施例中，通过基于仿射模型的K模型聚类技术的应用，可以将从视频流解码的运动矢量分类成组。在实施例中，可以使用根据运动矢量簇分割的图像来生成图像像素的粗略深度图。在实施例中，可以使用粗略深度图以及来自图像的边缘信息来生成图像的高分辨率梯度图。在实施例中，诸如Frankot-Chellappa算法的表面重建算法可以应用于高分辨率梯度图，以合成图像的详细深度图。例如，可以使用图像的详细深度图来渲染三维表面。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式