利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

12 条记录 (耗时 0.017 秒)

    Method for detecting human body motion in frames of a video sequence
    1.
    发明授权
    Method for detecting human body motion in frames of a video sequence 失效
    用于在视频序列的帧中检测人体运动的方法

    公开(公告)号：US5930379A

    公开(公告)日：1999-07-27

    申请号：US876603

    申请日：1997-06-16

    申请人： James M. Rehg ,  Henry A. Rowley

    发明人： James M. Rehg ,  Henry A. Rowley

    IPC分类号： G06K9/00 ,  G06T7/20 ,  G06T15/70

    CPC分类号： G06K9/00342 ,  G06T7/2046 ,  G06T2207/10016 ,  G06T2207/30196

    摘要： In a computerized method, a moving object is detected in a sequence of frames of a video of a scene. Each of the frames includes a plurality of pixels representing measured light intensity values at specific locations in the scene. The pixels are organized in a regularized pattern in a memory. The object is modeled as a branched kinematic chain composed of links connected at joints. The frames are iteratively segmented by assigning groups of pixels having like pixel motion to individual links, while estimating motion parameters for the groups of pixels assigned to the individual links until the segmented pixels and their motion parameters converge and can be identified with the moving object as modeled by the kinematic chain.

    摘要翻译： 在计算机化方法中，以场景的视频的帧序列检测移动物体。 每个帧包括表示场景中特定位置处的测量光强度值的多个像素。 像素以存储器中的正则化图案组织。 该对象被建模为由在连接处连接的链接组成的分支运动链。 通过将具有类似像素运动的像素组分配给各个链路，同时估计分配给各个链接的像素组的运动参数，直到分割的像素及其运动参数收敛并且可以用运动对象来识别，帧被迭代地分段 由运动链模拟。

    Method and system for correlating data streams
    2.
    发明授权
    Method and system for correlating data streams 失效
    用于关联数据流的方法和系统

    公开(公告)号：US06993246B1

    公开(公告)日：2006-01-31

    申请号：US09662474

    申请日：2000-09-15

    申请人： Davis Pan ,  James M. Rehg

    发明人： Davis Pan ,  James M. Rehg

    IPC分类号： H04N5/93

    CPC分类号： G11B27/10 ,  H04L67/12

    摘要： Events in a first data stream are correlated with events in a second data stream based on a method of indexing. As information of a first and second data stream are stored to a data file, the data streams are monitored for certain trigger events. An informational data set is generated and stored in an index file for each detected trigger event. Preferably, each informational data set includes the type of detected event, a time-stamp indicating when the event occurred and a data pointer indicating where the data associated with the event is stored in a corresponding data file. When time-stamps of detected trigger events in both data streams are generated based on a common system clock, data in one data stream is correlated with data in another data stream based on the time-stamps.

    摘要翻译： 基于索引的方法，第一数据流中的事件与第二数据流中的事件相关。 随着第一和第二数据流的信息被存储到数据文件中，对于某些触发事件监视数据流。 生成信息数据集并存储在每个检测到的触发事件的索引文件中。 优选地，每个信息数据集包括检测到的事件的类型，指示事件发生的时间戳和指示与事件相关联的数据在哪里存储在相应的数据文件中的数据指针。 当基于公共系统时钟产生两个数据流中检测到的触发事件的时间戳时，一个数据流中的数据与基于时间戳的另一个数据流中的数据相关。

    Systems and methods for retrieving causal sets of events from unstructured signals
    3.
    发明授权
    Systems and methods for retrieving causal sets of events from unstructured signals 有权
    从非结构化信号中检索事件的因果集的系统和方法

    公开(公告)号：US08909025B2

    公开(公告)日：2014-12-09

    申请号：US13427610

    申请日：2012-03-22

    申请人： James M. Rehg ,  Karthir Prabhakar ,  Sangmin Oh ,  Ping Wang ,  Gregory D. Abowd

    发明人： James M. Rehg ,  Karthir Prabhakar ,  Sangmin Oh ,  Ping Wang ,  Gregory D. Abowd

    IPC分类号： H04N5/91 ,  H04N9/80 ,  G06K9/00

    CPC分类号： G06K9/00718

    摘要： A method for providing improved performance in retrieving and classifying causal sets of events from an unstructured signal can comprise applying a temporal-causal analysis to the unstructured signal. The temporal-causal analysis can comprise representing the occurrence times of visual events from an unstructured signal as a set of point processes. An exemplary embodiment can comprise interpreting a set of visual codewords produced by a space-time-dictionary representation of the unstructured video sequence as the set of point processes. A nonparametric estimate of the cross-spectrum between pairs of point processes can be obtained. In an exemplary embodiment, a spectral version of the pairwise test for Granger causality can be applied to the nonparametric estimate to identify patterns of interactions between visual codewords and group them into semantically meaningful independent causal sets. The method can further comprise leveraging the segmentation achieved during temporal causal analysis to improve performance in categorizing causal sets.

    摘要翻译： 一种用于在从非结构化信号中检索和分类事件的因果集合中提供改进的性能的方法可以包括对非结构化信号应用时间因果分析。 时间因果分析可以包括将来自非结构化信号的视觉事件的发生时间表示为一组点处理。 示例性实施例可以包括解释由非结构化视频序列的空时 - 字典表示产生的一组可视码字作为点处理的集合。 可以获得点过程对之间的交叉谱的非参数估计。 在示例性实施例中，用于格兰杰因果关系的成对检验的频谱版本可以应用于非参数估计，以识别视觉码字之间的交互模式，并将它们分组成语义有意义的独立因果集合。 该方法可以进一步包括利用在时间因果分析期间实现的分段来提高对因果集进行分类的性能。

    Automated macular pathology diagnosis in three-dimensional (3D) spectral domain optical coherence tomography (SD-OCT) images
    4.
    发明授权
    Automated macular pathology diagnosis in three-dimensional (3D) spectral domain optical coherence tomography (SD-OCT) images 失效
    自动黄斑病理诊断三维（3D）光谱相干层析成像（SD-OCT）图像

    公开(公告)号：US08712505B2

    公开(公告)日：2014-04-29

    申请号：US13294601

    申请日：2011-11-11

    申请人： Hiroshi Ishikawa ,  Gadi Wollstein ,  Joel S. Schuman ,  Yu-Ying Liu ,  James M. Rehg ,  Mei Chen

    发明人： Hiroshi Ishikawa ,  Gadi Wollstein ,  Joel S. Schuman ,  Yu-Ying Liu ,  James M. Rehg ,  Mei Chen

    IPC分类号： A61B8/00 ,  A61B6/00 ,  A61B3/14 ,  A61B3/00

    CPC分类号： A61B3/102 ,  G06K9/4642 ,  G06K2009/4666

    摘要： Systems and methods of analyzing an optical coherence tomography image of a retina are discussed. A 2-dimensional slice of the image can be aligned to produce an approximately horizontal image of the retina and an edge map based at least in part on the aligned slice. Also, at least one global representation can be determined based on a (multi-scale) spatial division, such as multi-scale spatial pyramid, on the slice and/or edge map. Creating the local features is based on the specified cell structure of the global representation. The local features can be constructed based on local binary pattern (LBP)-based features. Additionally, a slice can be categorized into one or more categories via one or more classifiers (e.g., support vector machines). Each category can be associated with at least one ocular pathology, and classifying can be based on the constructed global descriptors, which can include the LBP-based local descriptors.

    摘要翻译： 讨论了分析视网膜的光学相干断层图像的系统和方法。 图像的二维切片可以被对准以至少部分地基于对齐的切片来产生视网膜的近似水平的图像和边缘图。 此外，可以基于切片和/或边缘图上的（多尺度）空间划分（例如多尺度空间金字塔）来确定至少一个全局表示。 创建局部特征是基于全局表示的指定单元格结构。 可以基于局部二进制模式（LBP）的特征构建局部特征。 此外，切片可以经由一个或多个分类器（例如，支持向量机）被分类为一个或多个类别。 每个类别可以与至少一个眼部病理学相关联，并且分类可以基于构建的全局描述符，其可以包括基于LBP的局部描述符。

    AUTOMATED MACULAR PATHOLOGY DIAGNOSIS IN THREEDIMENSIONAL (3D) SPECTRAL DOMAIN OPTICAL COHERENCE TOMOGRAPHY (SD-OCT) IMAGES
    6.
    发明申请
    AUTOMATED MACULAR PATHOLOGY DIAGNOSIS IN THREEDIMENSIONAL (3D) SPECTRAL DOMAIN OPTICAL COHERENCE TOMOGRAPHY (SD-OCT) IMAGES 失效
    自动化宏观病理学诊断（3D）光谱域光学相干图像（SD-OCT）图像

    公开(公告)号：US20120184845A1

    公开(公告)日：2012-07-19

    申请号：US13294601

    申请日：2011-11-11

    申请人： Hiroshi Ishikawa ,  Gadi Wollstein ,  Joel S. Schuman ,  Yu-Ying Liu ,  James M. Rehg ,  Mei Chen

    发明人： Hiroshi Ishikawa ,  Gadi Wollstein ,  Joel S. Schuman ,  Yu-Ying Liu ,  James M. Rehg ,  Mei Chen

    IPC分类号： A61B3/14 ,  G06K9/00

    CPC分类号： A61B3/102 ,  G06K9/4642 ,  G06K2009/4666

    摘要： Systems and methods of analyzing an optical coherence tomography image of a retina are discussed. A 2-dimensional slice of the image can be aligned to produce an approximately horizontal image of the retina and an edge map based at least in part on the aligned slice. Also, at least one global representation can be determined based on a (multi-scale) spatial division, such as multi-scale spatial pyramid, on the slice and/or edge map. Creating the local features is based on the specified cell structure of the global representation. The local features can be constructed based on local binary pattern (LBP)-based features. Additionally, a slice can be categorized into one or more categories via one or more classifiers (e.g., support vector machines). Each category can be associated with at least one ocular pathology, and classifying can be based on the constructed global descriptors, which can include the LBP-based local descriptors.

    摘要翻译： 讨论了分析视网膜的光学相干断层图像的系统和方法。 图像的二维切片可以被对准以至少部分地基于对齐的切片来产生视网膜的近似水平的图像和边缘图。 此外，可以基于切片和/或边缘图上的（多尺度）空间划分（例如多尺度空间金字塔）来确定至少一个全局表示。 创建局部特征是基于全局表示的指定单元格结构。 可以基于局部二进制模式（LBP）的特征构建局部特征。 此外，切片可以经由一个或多个分类器（例如，支持向量机）被分类为一个或多个类别。 每个类别可以与至少一个眼部病理学相关联，并且分类可以基于构建的全局描述符，其可以包括基于LBP的局部描述符。

    Multi-layer image-based rendering for video synthesis
    7.
    发明授权
    Multi-layer image-based rendering for video synthesis 失效
    用于视频合成的多层基于图像的渲染

    公开(公告)号：US06266068B1

    公开(公告)日：2001-07-24

    申请号：US09039022

    申请日：1998-03-13

    申请人： Sing Bing Kang ,  James M. Rehg

    发明人： Sing Bing Kang ,  James M. Rehg

    IPC分类号： G06T1160

    CPC分类号： G06T11/60

    摘要： A computerized method and related computer system synthesize video from a plurality of sources of image data. The sources include a variety of image data types such a collection of image stills, a sequence of video frames, and 3-D models of objects. Each source provides image data associated with an object. One source provides image data associated with a first object, and a second source provides image data associated with a second object. The image data of the first and second objects are combined to generate composite images of the first and second objects. From the composite images, an output image of the first and second objects as viewed from an arbitrary viewpoint is generated. Gaps of pixels with unspecified pixel values may appear in the output image. Accordingly, a pixel value for each of these “missing pixels” is obtained by using an epipolar search process to determine which one of the sources of image data should provide the pixel value for that missing pixel.

    摘要翻译： 计算机化方法和相关计算机系统从多个图像数据源合成视频。 这些源包括各种图像数据类型，诸如图像静止图像集合，视频帧序列和对象的3D模型。 每个源提供与对象相关联的图像数据。 一个源提供与第一对象相关联的图像数据，第二源提供与第二对象相关联的图像数据。 组合第一和第二对象的图像数据以生成第一和第二对象的合成图像。 从合成图像生成从任意视点观察第一和第二对象的输出图像。 输出图像中可能会出现具有未指定像素值的像素间隙。 因此，通过使用对极搜索处理来确定图像数据的哪一个源应该为缺失像素提供像素值，从而获得每个这些“丢失像素”的像素值。

    SYSTEMS AND METHODS FOR RETRIEVING CASUAL SETS OF EVENTS FROM UNSTRUCTURED SIGNALS
    9.
    发明申请
    SYSTEMS AND METHODS FOR RETRIEVING CASUAL SETS OF EVENTS FROM UNSTRUCTURED SIGNALS 有权
    用于从非结构化信号中检索休闲活动的系统和方法

    公开(公告)号：US20120301105A1

    公开(公告)日：2012-11-29

    申请号：US13427610

    申请日：2012-03-22

    申请人： James M. Rehg ,  Karthir Prabhakar ,  Sangmin Oh ,  Ping Wang ,  Gregory D. Abowd

    发明人： James M. Rehg ,  Karthir Prabhakar ,  Sangmin Oh ,  Ping Wang ,  Gregory D. Abowd

    IPC分类号： H04N5/91

    CPC分类号： G06K9/00718

    摘要： A method for providing improved performance in retrieving and classifying causal sets of events from an unstructured signal can comprise applying a temporal-causal analysis to the unstructured signal. The temporal-causal analysis can comprise representing the occurrence times of visual events from an unstructured signal as a set of point processes. An exemplary embodiment can comprise interpreting a set of visual codewords produced by a space-time-dictionary representation of the unstructured video sequence as the set of point processes. A nonparametric estimate of the cross-spectrum between pairs of point processes can be obtained. In an exemplary embodiment, a spectral version of the pairwise test for Granger causality can be applied to the nonparametric estimate to identify patterns of interactions between visual codewords and group them into semantically meaningful independent causal sets. The method can further comprise leveraging the segmentation achieved during temporal causal analysis to improve performance in categorizing causal sets.

    摘要翻译： 一种用于在从非结构化信号中检索和分类事件的因果集合中提供改进的性能的方法可以包括对非结构化信号应用时间因果分析。 时间因果分析可以包括将来自非结构化信号的视觉事件的发生时间表示为一组点处理。 示例性实施例可以包括解释由非结构化视频序列的空时 - 字典表示产生的一组可视码字作为点处理的集合。 可以获得点过程对之间的交叉谱的非参数估计。 在示例性实施例中，用于格兰杰因果关系的成对检验的频谱版本可以应用于非参数估计，以识别视觉码字之间的交互模式，并将它们分组成语义有意义的独立因果集合。 该方法可以进一步包括利用在时间因果分析期间实现的分段来提高对因果集进行分类的性能。

    On-line scheduling of constrained dynamic applications for parallel targets
    10.
    发明授权
    On-line scheduling of constrained dynamic applications for parallel targets 失效
    并行目标约束动态应用的在线调度

    公开(公告)号：US07073175B2

    公开(公告)日：2006-07-04

    申请号：US11145325

    申请日：2005-06-03

    申请人： James M. Rehg ,  Kathleen Knobe

    发明人： James M. Rehg ,  Kathleen Knobe

    IPC分类号： G06F9/46 ,  G06F7/38 ,  G06F15/16 ,  G06F15/00 ,  G06F12/00 ,  G06G7/48 ,  G06F9/44 ,  G06F9/45

    CPC分类号： G06F9/4881 ,  G06K9/00993

    摘要： A static schedule is selected from a set of static schedules for an application dependent on the state of the application. A scheduling system stores a set of pre-defined static schedules for each state of the application. A scheduling system learns the costs of predefined schedules for each state of the application on-line as the application executes. Upon the detection of a state change in the application during run-time, the scheduling system selects a new static schedule for the application. The new static schedule is determined based on schedule costs and exploration criteria.

    摘要翻译： 从应用程序的状态的一组静态调度中选择一个静态调度。 调度系统为应用程序的每个状态存储一组预定义的静态时间表。 调度系统在应用程序执行时在线了解应用程序的每个状态的预定义时间表的成本。 在运行时检测到应用程序的状态变化时，调度系统为应用程序选择新的静态调度。 新的静态计划是根据进度成本和勘探标准确定的。