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

US20130114942A1 Automatic Surveillance Video Matting Using a Shape Prior 有权
标题翻译：使用形状先前的自动监视视频消隐
公开(公告)号：US20130114942A1
公开(公告)日：2013-05-09
申请号：US13290928
申请日：2011-11-07
申请人： Ting Yu , Peter Henry Tu , Xiaoming Liu , Ser Nam Lim
发明人： Ting Yu , Peter Henry Tu , Xiaoming Liu , Ser Nam Lim
IPC分类号： H04N5/93
CPC分类号： G06K9/6256 , G06K9/52 , G06K9/621 , G06T7/11 , G06T7/194 , G06T7/33 , G06T11/60 , G06T2207/20081 , G06T2207/20221 , G06T2207/30196 , G06T2207/30204 , H04N5/272
摘要： A novel technique for performing video matting, which is built upon a proposed image matting algorithm that is fully automatic is disclosed. The disclosed methods utilize a PCA-based shape model as a prior for guiding the matting process, so that manual interactions required by most existing image matting methods are unnecessary. By applying the image matting algorithm to these foreground windows, on a per frame basis, a fully automated video matting process is attainable. The process of aligning the shape model with the object is simultaneously optimized based on a quadratic cost function.
摘要翻译：公开了一种用于执行视频消隐的新技术，其基于所提出的全自动图像消隐算法。所公开的方法利用基于PCA的形状模型作为先前指导消光处理，使得大多数现有图像消光方法所需的手动交互是不必要的。通过将图像消隐算法应用于这些前景窗口，在每帧的基础上，可以实现完全自动化的视频消隐处理。基于二次成本函数，同时优化了形状模型与对象的对齐过程。

2. 发明授权

US09305357B2 Automatic surveillance video matting using a shape prior 有权
标题翻译：自动监控视频消光使用形状先前
公开(公告)号：US09305357B2
公开(公告)日：2016-04-05
申请号：US13290928
申请日：2011-11-07
申请人： Ting Yu , Peter Henry Tu , Xiaoming Liu , Ser Nam Lim
发明人： Ting Yu , Peter Henry Tu , Xiaoming Liu , Ser Nam Lim
IPC分类号： H04N7/18 , G06T7/00 , H04N5/272 , G06K9/62
CPC分类号： G06K9/6256 , G06K9/52 , G06K9/621 , G06T7/11 , G06T7/194 , G06T7/33 , G06T11/60 , G06T2207/20081 , G06T2207/20221 , G06T2207/30196 , G06T2207/30204 , H04N5/272
摘要： A novel technique for performing video matting, which is built upon a proposed image matting algorithm that is fully automatic is disclosed. The disclosed methods utilize a PCA-based shape model as a prior for guiding the matting process, so that manual interactions required by most existing image matting methods are unnecessary. By applying the image matting algorithm to these foreground windows, on a per frame basis, a fully automated video matting process is attainable. The process of aligning the shape model with the object is simultaneously optimized based on a quadratic cost function.
摘要翻译：公开了一种用于执行视频消隐的新技术，其基于所提出的全自动图像消隐算法。所公开的方法利用基于PCA的形状模型作为先前指导消光处理，使得大多数现有图像消光方法所需的手动交互是不必要的。通过将图像消隐算法应用于这些前景窗口，在每帧的基础上，可以实现完全自动化的视频消隐处理。基于二次成本函数，同时优化了形状模型与对象的对齐过程。

3. 发明申请

US20130138499A1 USAGE MEASURENT TECHNIQUES AND SYSTEMS FOR INTERACTIVE ADVERTISING 审中-公开
标题翻译：用于互动广告的测量技术和系统
公开(公告)号：US20130138499A1
公开(公告)日：2013-05-30
申请号：US13308386
申请日：2011-11-30
申请人： Peter Henry Tu , Mark Lewis Grabb , Xiaoming Liu , Ting Yu , Yi Yao , Dashan Gao , Ming-Ching Chang
发明人： Peter Henry Tu , Mark Lewis Grabb , Xiaoming Liu , Ting Yu , Yi Yao , Dashan Gao , Ming-Ching Chang
IPC分类号： G06Q30/02
摘要： An advertising system is disclosed. In one embodiment, the system includes an advertising display configured to provide an advertisement to potential customers and a camera configured to capture images of the potential customers when the potential customers pass the advertising display. The system may also include an image processing system having a processor and a memory. The memory may include application instructions for execution by the processor, and the image processing system may be configured to execute the application instructions to derive usage characteristics of the potential customers with respect to the advertising display through analysis of the captured images. Additional methods, systems, and articles of manufacture are also disclosed.
摘要翻译：公开了广告系统。在一个实施例中，系统包括被配置为向潜在客户提供广告的广告显示器和被配置为当潜在客户通过广告显示时捕获潜在客户的图像的照相机。该系统还可以包括具有处理器和存储器的图像处理系统。存储器可以包括用于由处理器执行的应用指令，并且图像处理系统可以被配置为执行应用指令以通过分析所捕获的图像来导出相对于广告显示的潜在客户的使用特性。还公开了附加的方法，系统和制品。

4. 发明授权

US08154600B2 Method and system for distributed multiple target tracking 有权
标题翻译：分布式多目标跟踪的方法和系统
公开(公告)号：US08154600B2
公开(公告)日：2012-04-10
申请号：US12099301
申请日：2008-04-08
申请人： Ting Yu , Peter Henry Tu , Ambalangoda Gurunnanselage Amitha Perera , Jens Rittscher , Nils Oliver Krahnstoever , Xiaoming Liu
发明人： Ting Yu , Peter Henry Tu , Ambalangoda Gurunnanselage Amitha Perera , Jens Rittscher , Nils Oliver Krahnstoever , Xiaoming Liu
IPC分类号： H04N5/225
CPC分类号： G06K9/6278 , G06K9/32 , G06K9/6226 , G06T7/277
摘要： A method and system for distributed tracking of multiple targets is disclosed. Multiple targets to be tracked by a plurality of trackers are detected in a frame. The motion state variable of each of the plurality of trackers is calculated in the E-step of a variational Expectation-Maximization algorithm. Further, the data association variable of each of the plurality of trackers is calculated in the M-step of the algorithm. Depending on the motion state variable and the data association variable, the multiple targets are tracked.
摘要翻译：公开了一种用于多个目标的分布式跟踪的方法和系统。在多个跟踪器中跟踪的多个目标被检测到。在变化期望最大化算法的E步骤中计算多个跟踪器中的每一个的运动状态变量。此外，在算法的M步中计算多个跟踪器中的每一个的数据关联变量。根据运动状态变量和数据关联变量，跟踪多个目标。

5. 发明申请

US20080259163A1 METHOD AND SYSTEM FOR DISTRIBUTED MULTIPLE TARGET TRACKING 有权
标题翻译：用于分布式多目标跟踪的方法和系统
公开(公告)号：US20080259163A1
公开(公告)日：2008-10-23
申请号：US12099301
申请日：2008-04-08
申请人： Ting Yu , Peter Henry Tu , Ambalangoda Gurunnanselage Amitha Perera , Jens Rittscher , Nils Oliver Krahnstoever , Xiaoming Liu
发明人： Ting Yu , Peter Henry Tu , Ambalangoda Gurunnanselage Amitha Perera , Jens Rittscher , Nils Oliver Krahnstoever , Xiaoming Liu
IPC分类号： H04N5/00
CPC分类号： G06K9/6278 , G06K9/32 , G06K9/6226 , G06T7/277
摘要： A method and system for distributed tracking of multiple targets is disclosed. Multiple targets to be tracked by a plurality of trackers are detected in a frame. The motion state variable of each of the plurality of trackers is calculated in the E-step of a variational Expectation-Maximization algorithm. Further, the data association variable of each of the plurality of trackers is calculated in the M-step of the algorithm. Depending on the motion state variable and the data association variable, the multiple targets are tracked.
摘要翻译：公开了一种用于多个目标的分布式跟踪的方法和系统。在多个跟踪器中跟踪的多个目标被检测到。在变化期望最大化算法的E步骤中计算多个跟踪器中的每一个的运动状态变量。此外，在算法的M步中计算多个跟踪器中的每一个的数据关联变量。根据运动状态变量和数据关联变量，跟踪多个目标。

6. 发明申请

US20130138505A1 ANALYTICS-TO-CONTENT INTERFACE FOR INTERACTIVE ADVERTISING 审中-公开
标题翻译：用于互动广告的分析 - 内容接口
公开(公告)号：US20130138505A1
公开(公告)日：2013-05-30
申请号：US13308376
申请日：2011-11-30
申请人： Peter Henry Tu , Mark Lewis Grabb , Xiaoming Liu , Ting Yu , Yi Yao , Dashan Gao , Ming-Ching Chang
发明人： Peter Henry Tu , Mark Lewis Grabb , Xiaoming Liu , Ting Yu , Yi Yao , Dashan Gao , Ming-Ching Chang
IPC分类号： G06Q30/02
CPC分类号： G06Q30/02
摘要： An advertising system is disclosed. In one embodiment, the system includes a processor and a memory including application instructions for execution by the processor. The application instructions may include a visual analytics engine to analyze visual information including human activity and a content engine separate from the visual analytics engine to provide advertising content to one or more potential customers. Further, the instructions may include an interface module to enable information generated from analysis of the human activity by the visual analytics engine to be transferred to the content engine in accordance with a specification in which the information generated is characterized with a hierarchical, object-oriented data structure. Additional methods, systems, and articles of manufacture are also disclosed.
摘要翻译：公开了广告系统。在一个实施例中，该系统包括处理器和包括由处理器执行的应用指令的存储器。应用指令可以包括视觉分析引擎，用于分析包括人类活动的视觉信息和与视觉分析引擎分离的内容引擎，以向一个或多个潜在客户提供广告内容。此外，指令可以包括接口模块，用于根据其中所生成的信息以层次化，面向对象的特征来指示由视觉分析引擎分析人类活动而产生的信息被传送到内容引擎数据结构。还公开了附加的方法，系统和制品。

7. 发明申请

US20130138493A1 EPISODIC APPROACHES FOR INTERACTIVE ADVERTISING 审中-公开
标题翻译：互动广告的感知方法
公开(公告)号：US20130138493A1
公开(公告)日：2013-05-30
申请号：US13308394
申请日：2011-11-30
申请人： Peter Henry Tu , Mark Lewis Grabb , Xiaoming Liu , Ting Yu
发明人： Peter Henry Tu , Mark Lewis Grabb , Xiaoming Liu , Ting Yu
IPC分类号： G06Q30/02
CPC分类号： G06Q30/02
摘要： An advertising system is disclosed. In one embodiment, the system includes an advertising station configured to output advertising content to a potential customer and a data processing system including a processor and a memory having application instructions for execution by the processor. The application instructions may include an identification engine to identify the potential customer, a tracking engine to track encounters between the potential customer and the advertising station, and a content engine to select the advertising content to be output to the potential customer based on the tracked encounters between the potential customer and the advertising station. Additional methods, systems, and articles of manufacture are also disclosed.
摘要翻译：公开了广告系统。在一个实施例中，系统包括被配置为向潜在客户输出广告内容的广告站和包括处理器的数据处理系统和具有由处理器执行的应用指令的存储器。应用程序指令可以包括识别潜在客户的识别引擎，用于跟踪潜在客户和广告站之间的相遇的跟踪引擎，以及内容引擎，以基于被跟踪的遭遇来选择要向潜在客户输出的广告内容潜在客户和广告站之间。还公开了附加的方法，系统和制品。

8. 发明申请

US20100245567A1 SYSTEM, METHOD AND PROGRAM PRODUCT FOR CAMERA-BASED DISCOVERY OF SOCIAL NETWORKS 有权
标题翻译：用于基于摄像机的社交网络发现的系统，方法和程序产品
公开(公告)号：US20100245567A1
公开(公告)日：2010-09-30
申请号：US12412486
申请日：2009-03-27
申请人： Nils Oliver Krahnstoever , Ser Nam Lim , Ting Yu , Kedar Anil Patwardhan
发明人： Nils Oliver Krahnstoever , Ser Nam Lim , Ting Yu , Kedar Anil Patwardhan
IPC分类号： H04N7/18 , G06K9/00
CPC分类号： G06K9/00771 , G06K9/00295 , G06K9/00677
摘要： A system, method and program product for camera-based discovery of social networks. The computer implemented method for identifying individuals and associating tracks with individuals in camera-generated images from a face capture camera(s) and a tracking camera(s), wherein the computer implemented method includes: receiving images of an individual from the face capture camera(s) on a computer; receiving images of a track(s) of an individual from the tracking camera(s) on a computer; automatically determining with the computer the track(s) from the images from the tracking camera(s); and associating with the computer the track(s) with the individual(s) and a unique identifier. The present invention has been described in terms of specific embodiment(s), and it is recognized that equivalents, alternatives, and modifications, aside from those expressly stated, are possible and within the scope of the appending claims.
摘要翻译：一种用于基于摄像机发现社交网络的系统，方法和程序产品。一种计算机实现的方法，用于识别个人并将来自面部捕获相机和跟踪相机的相机生成的图像中的个体与个人相关联，其中所述计算机实现的方法包括：从面部捕获相机接收个体的图像在计算机上; 从计算机上的跟踪相机接收个人的轨道的图像; 使用计算机自动确定来自跟踪相机的图像的轨迹; 并且与计算机将轨道与个人和唯一标识符相关联。已经根据具体实施例描述了本发明，并且认识到除了明确说明的那些之外的等同物，替代方案和修改是可能的并且在所附权利要求的范围内。

9. 发明授权

US08320617B2 System, method and program product for camera-based discovery of social networks 有权
标题翻译：用于基于摄像机发现社交网络的系统，方法和程序产品
公开(公告)号：US08320617B2
公开(公告)日：2012-11-27
申请号：US12412486
申请日：2009-03-27
申请人： Nils Oliver Krahnstoever , Ser Nam Lim , Ting Yu , Kedar Anil Patwardhan
发明人： Nils Oliver Krahnstoever , Ser Nam Lim , Ting Yu , Kedar Anil Patwardhan
IPC分类号： G06K9/00
CPC分类号： G06K9/00771 , G06K9/00295 , G06K9/00677
摘要： A system, method and program product for camera-based discovery of social networks. The computer implemented method for identifying individuals and associating tracks with individuals in camera-generated images from a face capture camera(s) and a tracking camera(s), wherein the computer implemented method includes: receiving images of an individual from the face capture camera(s) on a computer; receiving images of a track(s) of an individual from the tracking camera(s) on a computer; automatically determining with the computer the track(s) from the images from the tracking camera(s); and associating with the computer the track(s) with the individual(s) and a unique identifier. The present invention has been described in terms of specific embodiment(s), and it is recognized that equivalents, alternatives, and modifications, aside from those expressly stated, are possible and within the scope of the appending claims.
摘要翻译：一种用于基于摄像机发现社交网络的系统，方法和程序产品。一种计算机实现的方法，用于识别个人并将来自面部捕获相机和跟踪相机的相机生成的图像中的个体与个人相关联，其中所述计算机实现的方法包括：从面部捕获相机接收个体的图像在计算机上; 从计算机上的跟踪相机接收个人的轨道的图像; 使用计算机自动确定来自跟踪相机的图像的轨迹; 并且与计算机将轨道与个人和唯一标识符相关联。已经根据具体实施例描述了本发明，并且认识到除了明确说明的那些之外的等同物，替代方案和修改是可能的并且在所附权利要求的范围内。

10. 发明授权

US09384448B2 Action-based models to identify learned tasks 有权
标题翻译：基于行动的模型识别学习任务
公开(公告)号：US09384448B2
公开(公告)日：2016-07-05
申请号：US13339297
申请日：2011-12-28
申请人： Peter Henry Tu , Ting Yu , Dashan Gao , Thomas Baby Sebastian , Yi Yao
发明人： Peter Henry Tu , Ting Yu , Dashan Gao , Thomas Baby Sebastian , Yi Yao
IPC分类号： G06N99/00 , G06K9/62
CPC分类号： G06N99/005 , G06K9/6256
摘要： Systems provided herein include a learning environment and an agent. The learning environment includes an avatar and an object. A state signal corresponding to a state of the learning environment includes a location and orientation of the avatar and the object. The agent is adapted to receive the state signal, to issue an action capable of generating at least one change in the state of the learning environment, to produce a set of observations relevant to a task, to hypothesize a set of action models configured to explain the observations, and to vet the set of action models to identify a learned model for the task.
摘要翻译：本文提供的系统包括学习环境和代理。学习环境包括头像和对象。对应于学习环境的状态的状态信号包括化身和对象的位置和方向。该代理适于接收状态信号，以发出能够产生学习环境状态的至少一个变化的动作，以产生与任务相关的一组观察结果，以假设一组动作模型，其被配置为解释观察，并且审视一套动作模型，以确定一个学习的任务模型。

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