利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

19 条记录 (耗时 0.022 秒)

    Composition Engine for Analytical Models
    1.
    发明申请
    Composition Engine for Analytical Models 审中-公开

    公开(公告)号：US20200089817A1

    公开(公告)日：2020-03-19

    申请号：US16135943

    申请日：2018-09-19

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Florian Pinel ,  Russell P. Bobbitt ,  Chiao-Fe Shu

    IPC分类号： G06F17/30 ,  G06F15/18 ,  G06F9/455

    摘要： A computer-implemented method for executing a composition of analytical models. In one embodiment, the computer-implemented method creates analytical model composition definitions for a plurality of analytical models. The computer-implemented method receives analytical model definitions and an analytical model composition. The computer-implemented method binds the analytical model composition to the analytical model definitions. The computer-implemented method deploys the analytical model composition using the analytical model composition definitions. The computer-implemented method executes the analytical model composition and returns a result of the analytical model composition.

    SELF-OPTIMIZED OBJECT DETECTION USING ONLINE DETECTOR SELECTION
    3.
    发明申请
    SELF-OPTIMIZED OBJECT DETECTION USING ONLINE DETECTOR SELECTION 有权
    使用在线检测器选择的自优化对象检测

    公开(公告)号：US20170046596A1

    公开(公告)日：2017-02-16

    申请号：US14824341

    申请日：2015-08-12

    申请人： International Business Machines Corporation

    发明人： Russell P. Bobbitt ,  Rogerio S. Feris ,  Chiao-Fe Shu ,  Yun Zhai

    IPC分类号： G06K9/62 ,  G06T7/20 ,  H04N7/18 ,  G06K9/00

    CPC分类号： G06K9/46 ,  G06K9/00771 ,  G06K9/626 ,  G06K2009/4666 ,  G06K2209/27 ,  H04N7/181

    摘要： Embodiments are directed to an object detection system having at least one processor circuit configured to receive a series of image regions and apply to each image region in the series a detector, which is configured to determine a presence of a predetermined object in the image region. The object detection system performs a method of selecting and applying the detector from among a plurality of foreground detectors and a plurality of background detectors in a repeated pattern that includes sequentially selecting a selected one of the plurality of foreground detectors; sequentially applying the selected one of the plurality of foreground detectors to one of the series of image regions until all of the plurality of foreground detectors have been applied; selecting a selected one of the plurality of background detectors; and applying the selected one of the plurality of background detectors to one of the series of image regions.

    摘要翻译： 实施例涉及一种对象检测系统，其具有至少一个处理器电路，该处理器电路被配置为接收一系列图像区域，并且应用于该系列中的每个图像区域，该检测器被配置为确定图像区域中预定对象的存在。 物体检测系统执行以重复图案从多个前景检测器和多个背景检测器之中选择和应用检测器的方法，该重复图案包括顺序选择多个前景检测器中的一个前景检测器; 将所述多个前景检测器中的所选择的一个顺序地应用到所述一系列图像区域中的一个，直到已经应用所述多个前景检测器; 选择所述多个背景检测器中的所选择的一个; 以及将所述多个背景检测器中的所选择的一个应用于所述一系列图像区域中的一个。

    Identifying spatial locations of events within video image data
    5.
    发明授权
    Identifying spatial locations of events within video image data 有权
    识别视频图像数据中事件的空间位置

    公开(公告)号：US08971580B2

    公开(公告)日：2015-03-03

    申请号：US13903237

    申请日：2013-05-28

    申请人： International Business Machines Corporation

    发明人： Michael J. Desimone ,  Arun Hampapur ,  Zuoxuan Lu ,  Carl P. Mercier ,  Christopher S. Milite ,  Stephen R. Russo ,  Chiao-Fe Shu ,  Chek K. Tan

    IPC分类号： G06K9/00

    CPC分类号： H04N7/18 ,  G06F17/30061 ,  G06F17/30277 ,  G06F17/30802 ,  G06F17/30825 ,  G06K9/00335 ,  G06K9/00711 ,  G06K9/00771 ,  G06K9/48 ,  G06K2009/00738 ,  G06T7/97 ,  G06T2207/30232 ,  G06T2207/30241

    摘要： An invention for identifying a spatial location of an event within video image data is provided. Disclosed are embodiments for generating trajectory data of a trajectory of an object for a plurality of pixel regions of an area of interest within video image data, the generating comprising: identifying one or more pixel regions from the plurality of pixel regions containing trajectory data; performing a multi-point neighborhood scan within the one or more pixel regions from the plurality of pixel regions containing trajectory data; and generating a transition chain code based on the multi-point neighborhood scan. Embodiments further generate a set of compressed spatial representations of the trajectory data of the trajectory of the object for an event based on the transition chain code, and generate a lossless contour code of the trajectory data of the trajectory of the object for the event based on the transition chain code.

    摘要翻译： 提供了一种用于识别视频图像数据内的事件的空间位置的发明。 公开了用于生成视频图像数据内感兴趣区域的多个像素区域的对象的轨迹的轨迹数据的实施例，该生成包括：从包含轨迹数据的多个像素区域中识别一个或多个像素区域; 在来自包含轨迹数据的多个像素区域的一个或多个像素区域内执行多点邻域扫描; 以及基于所述多点邻域扫描生成过渡链码。 实施例还基于过渡链码产生一组事件的对象的轨迹数据的压缩空间表示，并且生成基于事件的对象的轨迹数据的无损轮廓代码 过渡链代码。

    IDENTIFYING SPATIAL LOCATIONS OF EVENTS WITHIN VIDEO IMAGE DATA
    6.
    发明申请
    IDENTIFYING SPATIAL LOCATIONS OF EVENTS WITHIN VIDEO IMAGE DATA 有权
    在视频图像数据中识别事件的空间位置

    公开(公告)号：US20130259316A1

    公开(公告)日：2013-10-03

    申请号：US13903237

    申请日：2013-05-28

    申请人： International Business Machines Corporation

    发明人： Michael J. Desimone ,  Arun Hampapur ,  Zuoxuan Lu ,  Carl P. Mercier ,  Christopher S. Milite ,  Stephen R. Russo ,  Chiao-Fe Shu ,  Chek K. Tan

    IPC分类号： G06K9/00

    CPC分类号： H04N7/18 ,  G06F17/30061 ,  G06F17/30277 ,  G06F17/30802 ,  G06F17/30825 ,  G06K9/00335 ,  G06K9/00711 ,  G06K9/00771 ,  G06K9/48 ,  G06K2009/00738 ,  G06T7/97 ,  G06T2207/30232 ,  G06T2207/30241

    摘要： An invention for identifying a spatial location of an event within video image data is provided. Disclosed are embodiments for generating trajectory data of a trajectory of an object for a plurality of pixel regions of an area of interest within video image data, the generating comprising: identifying one or more pixel regions from the plurality of pixel regions containing trajectory data; performing a multi-point neighborhood scan within the one or more pixel regions from the plurality of pixel regions containing trajectory data; and generating a transition chain code based on the multi-point neighborhood scan. Embodiments further generate a set of compressed spatial representations of the trajectory data of the trajectory of the object for an event based on the transition chain code, and generate a lossless contour code of the trajectory data of the trajectory of the object for the event based on the transition chain code.

    摘要翻译： 提供了一种用于识别视频图像数据内的事件的空间位置的发明。 公开了用于生成视频图像数据内感兴趣区域的多个像素区域的对象的轨迹的轨迹数据的实施例，该生成包括：从包含轨迹数据的多个像素区域中识别一个或多个像素区域; 在来自包含轨迹数据的多个像素区域的一个或多个像素区域内执行多点邻域扫描; 以及基于所述多点邻域扫描生成过渡链码。 实施例还基于过渡链码产生一组事件的对象的轨迹数据的压缩空间表示，并且生成基于事件的对象的轨迹数据的无损轮廓代码 过渡链代码。

    Self-optimized object detection using online detector selection
    7.
    发明授权
    Self-optimized object detection using online detector selection 有权

    公开(公告)号：US10089551B2

    公开(公告)日：2018-10-02

    申请号：US14962791

    申请日：2015-12-08

    申请人： International Business Machines Corporation

    发明人： Russell P. Bobbitt ,  Rogerio S. Feris ,  Chiao-Fe Shu ,  Yun Zhai

    IPC分类号： G06K9/46 ,  G06K9/00 ,  G06K9/62 ,  H04N7/18

    摘要： Embodiments are directed to an object detection system having at least one processor circuit configured to receive a series of image regions and apply to each image region in the series a detector, which is configured to determine a presence of a predetermined object in the image region. The object detection system performs a method of selecting and applying the detector from among a plurality of foreground detectors and a plurality of background detectors in a repeated pattern that includes sequentially selecting a selected one of the plurality of foreground detectors; sequentially applying the selected one of the plurality of foreground detectors to one of the series of image regions until all of the plurality of foreground detectors have been applied; selecting a selected one of the plurality of background detectors; and applying the selected one of the plurality of background detectors to one of the series of image regions.

    Self-optimized object detection using online detector selection
    8.
    发明授权
    Self-optimized object detection using online detector selection 有权

    公开(公告)号：US09946951B2

    公开(公告)日：2018-04-17

    申请号：US14824341

    申请日：2015-08-12

    申请人： International Business Machines Corporation

    发明人： Russell P. Bobbitt ,  Rogerio S. Feris ,  Chiao-Fe Shu ,  Yun Zhai

    IPC分类号： G06K9/46 ,  G06K9/00 ,  G06K9/62 ,  H04N7/18

    CPC分类号： G06K9/46 ,  G06K9/00771 ,  G06K9/626 ,  G06K2009/4666 ,  G06K2209/27 ,  H04N7/181

    摘要： Embodiments are directed to an object detection system having at least one processor circuit configured to receive a series of image regions and apply to each image region in the series a detector, which is configured to determine a presence of a predetermined object in the image region. The object detection system performs a method of selecting and applying the detector from among a plurality of foreground detectors and a plurality of background detectors in a repeated pattern that includes sequentially selecting a selected one of the plurality of foreground detectors; sequentially applying the selected one of the plurality of foreground detectors to one of the series of image regions until all of the plurality of foreground detectors have been applied; selecting a selected one of the plurality of background detectors; and applying the selected one of the plurality of background detectors to one of the series of image regions.