专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明授权

US08401979B2 Multiple category learning for training classifiers 有权
标题翻译：训练分类器的多类学习
公开(公告)号：US08401979B2
公开(公告)日：2013-03-19
申请号：US12618799
申请日：2009-11-16
申请人： Cha Zhang , Zhengyou Zhang
发明人： Cha Zhang , Zhengyou Zhang
IPC分类号： G06F15/18
CPC分类号： G06N99/005
摘要： Described is multiple category learning to jointly train a plurality of classifiers in an iterative manner. Each training iteration associates an adaptive label with each training example, in which during the iterations, the adaptive label of any example is able to be changed by the subsequent reclassification. In this manner, any mislabeled training example is corrected by the classifiers during training. The training may use a probabilistic multiple category boosting algorithm that maintains probability data provided by the classifiers, or a winner-take-all multiple category boosting algorithm selects the adaptive label based upon the highest probability classification. The multiple category boosting training system may be coupled to a multiple instance learning mechanism to obtain the training examples. The trained classifiers may be used as weak classifiers that provide a label used to select a deep classifier for further classification, e.g., to provide a multi-view object detector.
摘要翻译：描述了多类学习，以迭代的方式联合训练多个分类器。每个训练迭代将自适应标签与每个训练示例相关联，其中在迭代期间，任何示例的自适应标签能够由随后的重新分类改变。以这种方式，任何错误标记的训练示例在训练期间由分类器校正。训练可以使用维护由分类器提供的概率数据的概率多类别提升算法，或者获胜者全部多类别增强算法基于最高概率分类来选择自适应标签。多类别增强训练系统可以耦合到多实例学习机制以获得训练示例。经训练的分类器可以用作弱分类器，其提供用于选择用于进一步分类的深分类器的标签，例如提供多视图对象检测器。

12. 发明申请

US20130010079A1 CALIBRATION BETWEEN DEPTH AND COLOR SENSORS FOR DEPTH CAMERAS 有权
标题翻译：深度摄影机的深度和颜色传感器之间的校准
公开(公告)号：US20130010079A1
公开(公告)日：2013-01-10
申请号：US13178494
申请日：2011-07-08
申请人： Cha Zhang , Zhengyou Zhang
发明人： Cha Zhang , Zhengyou Zhang
IPC分类号： H04N13/02
CPC分类号： H04N13/246 , G06T7/85 , H04N13/20 , H04N13/207 , H04N13/25 , H04N13/257 , H04N13/271
摘要： A system described herein includes a receiver component that receives a first digital image from a color camera, wherein the first digital image comprises a planar object, and a second digital image from a depth sensor, wherein the second digital image comprises the planar object. The system also includes a calibrator component that jointly calibrates the color camera and the depth sensor based at least in part upon the first digital image and the second digital image.
摘要翻译：本文描述的系统包括从彩色摄像机接收第一数字图像的接收器组件，其中第一数字图像包括平面物体和来自深度传感器的第二数字图像，其中第二数字图像包括平面物体。该系统还包括校准器组件，其至少部分地基于第一数字图像和第二数字图像来共同校准彩色摄像机和深度传感器。

13. 发明授权

US08339459B2 Multi-camera head pose tracking 有权
标题翻译：多摄像机头姿态跟踪
公开(公告)号：US08339459B2
公开(公告)日：2012-12-25
申请号：US12561154
申请日：2009-09-16
申请人： Zhengyou Zhang , Aswin Sankaranarayanan , Qing Zhang , Zicheng Liu , Qin Cai
发明人： Zhengyou Zhang , Aswin Sankaranarayanan , Qing Zhang , Zicheng Liu , Qin Cai
IPC分类号： H04N5/225
CPC分类号： H04N7/142 , G06K9/00261 , G06T7/75 , G06T7/85 , G06T2207/10012 , G06T2207/30201
摘要： Techniques and technologies for tracking a face with a plurality of cameras wherein a geometry between the cameras is initially unknown. One disclosed method includes detecting a head with two of the cameras and registering a head model with the image of the head (as detected by one of the cameras). The method also includes back projecting the other detected face image to the head model and determining a head pose from the back-projected head image. Furthermore, the determined geometry is used to track the face with at least one of the cameras.
摘要翻译：用于跟踪具有多个相机的面部的技术和技术，其中相机之间的几何形状最初是未知的。一种公开的方法包括使用两个摄像机检测头部，并用头部的图像（由相机之一检测到）登记头部模型。该方法还包括将另一个检测到的脸部图像反投影到头部模型并且从后投影的头部图像确定头部姿势。此外，所确定的几何形状用于利用至少一个相机跟踪面部。

14. 发明授权

US08310521B2 Insertion of virtual video into live video 有权
标题翻译：将虚拟视频插入实况视频
公开(公告)号：US08310521B2
公开(公告)日：2012-11-13
申请号：US11742504
申请日：2007-04-30
申请人： Zhengyou Zhang , Aaron Bobick
发明人： Zhengyou Zhang , Aaron Bobick
IPC分类号： H04N7/14
CPC分类号： G11B27/036
摘要： The present virtual video muting technique seamlessly inserts a virtual video into a live video when the user does not want to reveal his/her actual activity. The virtual video is generated based on real video frames captured earlier, and thus makes the virtual video appear to be real.
摘要翻译：当用户不想透露他/她的实际活动时，目前的虚拟视频静音技术将虚拟视频无缝地插入到实况视频中。虚拟视频基于先前捕获的实际视频帧生成，从而使虚拟视频看起来是真实的。

15. 发明申请

US20120268563A1 AUGMENTED AUDITORY PERCEPTION FOR THE VISUALLY IMPAIRED 有权
标题翻译：视觉受损的审计意见
公开(公告)号：US20120268563A1
公开(公告)日：2012-10-25
申请号：US13092276
申请日：2011-04-22
申请人： Philip A. Chou , Zhengyou Zhang , Dinei Florencio
发明人： Philip A. Chou , Zhengyou Zhang , Dinei Florencio
IPC分类号： H04R5/02 , H04N13/02
CPC分类号： H04N13/271 , A61H3/061 , A61H2201/0157 , A61H2201/165 , A61H2201/501 , A61H2201/5048 , A61H2201/5058 , A61H2201/5092 , G01S15/025 , G01S15/89 , G01S15/93 , H04N13/239 , H04R5/033 , H04R2420/07
摘要： A person is provided with the ability to auditorily determine the spatial geometry of his current physical environment. A spatial map of the current physical environment of the person is generated. The spatial map is then used to generate a spatialized audio representation of the environment. The spatialized audio representation is then output to a stereo listening device which is being worn by the person.
摘要翻译：一个人被赋予了能够自觉地确定他当前的物理环境的空间几何的能力。生成人的当前物理环境的空间映射。然后使用空间映射来生成环境的空间化音频表示。然后将空间化音频表示输出到由人佩戴的立体声聆听装置。

16. 发明授权

US08281334B2 Facilitating advertisement placement over video content 有权
标题翻译：促进视频内容的广告放置
公开(公告)号：US08281334B2
公开(公告)日：2012-10-02
申请号：US12059255
申请日：2008-03-31
申请人： Ying Shan , Yue Zhou , Xu Liu , Ying Li , Zhengyou Zhang
发明人： Ying Shan , Yue Zhou , Xu Liu , Ying Li , Zhengyou Zhang
IPC分类号： H04N7/10 , G06F3/048
CPC分类号： G06Q30/02 , G06T7/97 , G06T2207/10016 , G06T2207/20021
摘要： Systems, methods, computer-readable media, and graphical user interfaces for facilitating advertisement placement over video content are provided. Images within a video are partitioned into image regions. Upon partitioning images into image regions, an intrusiveness score is determined for each image region. Based on the intrusiveness scores, optimal placement of an advertisement within the video is determined.
摘要翻译：提供了系统，方法，计算机可读介质和图形用户界面，以便于通过视频内容进行广告放置。视频内的图像被分割成图像区域。在将图像分割成图像区域时，针对每个图像区域确定侵入性分数。基于侵入性分数，确定视频内的广告的最佳放置。

17. 发明申请

US20120155680A1 VIRTUAL AUDIO ENVIRONMENT FOR MULTIDIMENSIONAL CONFERENCING 有权
标题翻译：多媒体会议的虚拟音频环境
公开(公告)号：US20120155680A1
公开(公告)日：2012-06-21
申请号：US12970964
申请日：2010-12-17
申请人： Wei-ge Chen , Zhengyou Zhang , Yoomi Hur
发明人： Wei-ge Chen , Zhengyou Zhang , Yoomi Hur
IPC分类号： H04R5/02
CPC分类号： H04R27/00 , H04R2227/003 , H04R2227/005
摘要： The disclosed architecture employs signal processing techniques to provide audio perception only, or audio perception that matches the visual perception. This also provides spatial audio reproduction for multiparty teleconferencing such that the teleconferencing participants perceive themselves as if they were sitting in the same room. The solution is based on the premise that people perceive sounds as a reconstructed wavefront, and hence, the wavefronts are used to provide the spatial perceptual cues. The differences between the spatial perceptual cues derived from the reconstructed wavefront of sound waves and the ideal wavefront of sound waves form an objective metric for spatial perceptual quality, and provide the means of evaluating the overall system performance. Additionally, compensation filters are employed to improve the spatial perceptual quality of stereophonic systems by optimizing the objective metrics.
摘要翻译：所公开的架构采用信号处理技术来仅提供音频感知，或者与视觉感知匹配的音频感知。这也为多方电话会议提供了空间音频再现，使得电话会议参与者将自己视为坐在同一个房间中。解决方案是基于人们将声音视为重建波前的前提，因此波前用于提供空间感知线索。从声波重构波前衍生的空间感知线索与声波理想波阵面之间的差异形成了空间感知质量的客观指标，并提供了评估整体系统性能的手段。另外，通过优化客观指标，采用补偿滤波器来提高立体声系统的空间感知质量。

18. 发明申请

US20120105585A1 IN-HOME DEPTH CAMERA CALIBRATION 有权
标题翻译：家庭深度摄像机校准
公开(公告)号：US20120105585A1
公开(公告)日：2012-05-03
申请号：US12939038
申请日：2010-11-03
申请人： Prafulla J. Masalkar , Szymon P. Stachniak , Tommer Leyvand , Zhengyou Zhang , Leonardo Del Castillo , Zsolt Mathe
发明人： Prafulla J. Masalkar , Szymon P. Stachniak , Tommer Leyvand , Zhengyou Zhang , Leonardo Del Castillo , Zsolt Mathe
IPC分类号： H04N13/02
CPC分类号： H04N13/327 , A63F13/213 , A63F13/22 , G06F3/017 , G06T7/80 , G06T2207/10021 , G06T2207/10028 , G06T2207/30196 , H04N13/128 , H04N13/271
摘要： A system and method are disclosed for calibrating a depth camera in a natural user interface. The system in general obtains an objective measurement of true distance between a capture device and one or more objects in a scene. The system then compares the true depth measurement to the depth measurement provided by the depth camera at one or more points and determines an error function describing an error in the depth camera measurement. The depth camera may then be recalibrated to correct for the error. The objective measurement of distance to one or more objects in a scene may be accomplished by a variety of systems and methods.
摘要翻译：公开了用于在自然界面中校准深度相机的系统和方法。该系统通常获得捕获装置与场景中的一个或多个物体之间的真实距离的客观测量。然后，系统将真实深度测量与深度相机在一个或多个点提供的深度测量进行比较，并确定描述深度相机测量中的误差的误差函数。然后可以重新校准深度相机以校正错误。可以通过各种系统和方法来实现对场景中的一个或多个对象的距离的客观测量。

19. 发明申请

US20110295392A1 DETECTING REACTIONS AND PROVIDING FEEDBACK TO AN INTERACTION 有权
标题翻译：检测反应并提供反馈到交互
公开(公告)号：US20110295392A1
公开(公告)日：2011-12-01
申请号：US12789055
申请日：2010-05-27
申请人： Sharon K. Cunnington , Rajesh K. Hegde , Kori Quinn , Jin Li , Philip A. Chou , Zhengyou Zhang , Desney S. Tan
发明人： Sharon K. Cunnington , Rajesh K. Hegde , Kori Quinn , Jin Li , Philip A. Chou , Zhengyou Zhang , Desney S. Tan
IPC分类号： G06F17/00 , G06F19/00
CPC分类号： G06Q10/10 , H04N7/15
摘要： Reaction information of participants to an interaction may be sensed and analyzed to determine one or more reactions or dispositions of the participants. Feedback may be provided based on the determined reactions. The participants may be given an opportunity to opt in to having their reaction information collected, and may be provided complete control over how their reaction information is shared or used.
摘要翻译：可以感测和分析参与者对于相互作用的反应信息以确定参与者的一个或多个反应或处置。可以基于确定的反应来提供反馈。参与者可能有机会选择收集他们的反应信息，并且可以完全控制他们的反应信息如何共享或使用。

20. 发明申请

US20110267419A1 ACCELERATED INSTANT REPLAY FOR CO-PRESENT AND DISTRIBUTED MEETINGS 有权
标题翻译：加快现场和分销会议的即时更换
公开(公告)号：US20110267419A1
公开(公告)日：2011-11-03
申请号：US12771429
申请日：2010-04-30
申请人： Kori Inkpen Quinn , Rajesh Hegde , Zhengyou Zhang , John Tang , Sasa Junuzovic , Christopher Brooks
发明人： Kori Inkpen Quinn , Rajesh Hegde , Zhengyou Zhang , John Tang , Sasa Junuzovic , Christopher Brooks
IPC分类号： H04N7/14 , G10L15/26
CPC分类号： G06F3/04842 , G06K9/4676 , G10L25/78 , H04N7/15 , H04N7/155 , H04N21/2387 , H04N21/47202
摘要： Techniques for recording and replay of a live conference while still attending the live conference are described. A conferencing system includes a user interface generator, a live conference processing module, and a replay processing module. The user interface generator is configured to generate a user interface that includes a replay control panel and one or more output panels. The live conference processing module is configured to extract information included in received conferencing data that is associated with one or more conferencing modalities, and to display the information in the one or more output panels in a live manner (e.g., as a live conference). The replay processing module is configured to enable information associated with the one or more conferencing modalities corresponding to a time of the conference session prior to live to be presented at a desired rate, possibly different from the real-time rate, if a replay mode is selected in the replay control panel.
摘要翻译：描述了现场直播会议记录和重放现场会议的技巧。会议系统包括用户界面生成器，实时会议处理模块和重放处理模块。用户界面生成器被配置为生成包括重放控制面板和一个或多个输出面板的用户界面。实况会议处理模块被配置为提取包含在与一个或多个会议模式相关联的接收的会议数据中的信息，并以现场方式（例如，作为直播会议）在一个或多个输出面板中显示信息。重放处理模块被配置为如果重放模式是重放模式，则使能与在实时之前的会议会话的时间相对应的一个或多个会议模式的信息以与实时速率可能不同的期望速率被呈现在重播控制面板中选择。

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