-
公开(公告)号：US08582803B2
公开(公告)日：2013-11-12
申请号：US12905272
申请日：2010-10-15
申请人： Lei Ding , Quanfu Fan , Prasad Gabbur , Arun Hampapur , Sachiko Miyazawa , Sharathchandra U. Pankanti
发明人： Lei Ding , Quanfu Fan , Prasad Gabbur , Arun Hampapur , Sachiko Miyazawa , Sharathchandra U. Pankanti
IPC分类号： G06K9/00
CPC分类号： G06K9/6215 , G06K9/00335 , G06K9/00771
摘要： Determination of human behavior from an alignment of data streams includes acquiring visual image primitives from a video input comprising visual information relevant to a human activity. The primitives are temporally aligned to an optimally hypothesized sequence of primitives transformed from a sequence of transactions as a function of a distance metric between the observed primitive sequence and the transformed primitive sequence. More particularly, transforming includes comparing the distance metric costs and choosing and performing the lowest cost of temporally matching the observed primitives to one or more transactions, deleting a primitive, or associating a primitive with a pseudo transaction marker. Accordingly, alerts are issued based on analysis of the transformation of primitives.
摘要翻译： 从数据流的对齐确定人类行为包括从包括与人类活动相关的视觉信息的视频输入中获取视觉图像原语。 原语在时间上与从事件序列变换的最优假设序列的原语对齐，作为观察到的原始序列与经变换的原始序列之间的距离度量的函数。 更具体地，变换包括比较距离度量成本并选择和执行将观察到的原语暂时匹配到一个或多个事务，删除原语或将原语与伪交易标记相关联的最低成本。 因此，基于对原语的转换的分析发出警报。
-
公开(公告)号：US20120008836A1
公开(公告)日：2012-01-12
申请号：US12834104
申请日：2010-07-12
申请人： Russell P. Bobbitt , Lei Ding , Quanfu Fan , Sachiko Miyazawa , Sharathchandra U. Pankanti , Yun Zhai
发明人： Russell P. Bobbitt , Lei Ding , Quanfu Fan , Sachiko Miyazawa , Sharathchandra U. Pankanti , Yun Zhai
CPC分类号： G06K9/00335 , G06K9/00771 , G06K9/6224
摘要： Human behavior is determined by sequential event detection by constructing a temporal-event graph with vertices representing adjacent first and second primitive images of a plurality of individual primitive images parsed from a video stream, and also of first and second idle states associated with the respective first and second primitive images. Constructing the graph is a function of an edge set between the adjacent first and second primitive images, and an edge weight set as a function of a discrepancy between computed visual features within regions of interest common to the adjacent first and second primitive images. A human activity event is determined as a function of a shortest distance path of the temporal-event graph vertices.
摘要翻译： 通过构建具有表示从视频流解析的多个单独原始图像的相邻第一和第二原始图像的顶点的时间事件图以及与各自的第一和第二空闲状态相关联的第一和第二空闲状态，通过顺序事件检测来确定人的行为 和第二原始图像。 构造图是在相邻的第一和第二原始图像之间设置的边缘的函数，以及作为相邻第一和第二原始图像共同的感兴趣区域内的计算的视觉特征之间的差异的函数的边缘权重集合。 人类活动事件被确定为时间 - 事件图形顶点的最短距离路径的函数。
-
公开(公告)号：US08548203B2
公开(公告)日：2013-10-01
申请号：US12834104
申请日：2010-07-12
申请人： Russell P. Bobbitt , Lei Ding , Quanfu Fan , Sachiko Miyazawa , Sharathchandra U. Pankanti , Yun Zhai
发明人： Russell P. Bobbitt , Lei Ding , Quanfu Fan , Sachiko Miyazawa , Sharathchandra U. Pankanti , Yun Zhai
CPC分类号： G06K9/00335 , G06K9/00771 , G06K9/6224
摘要： Human behavior is determined by sequential event detection by constructing a temporal-event graph with vertices representing adjacent first and second primitive images of a plurality of individual primitive images parsed from a video stream, and also of first and second idle states associated with the respective first and second primitive images. Constructing the graph is a function of an edge set between the adjacent first and second primitive images, and an edge weight set as a function of a discrepancy between computed visual features within regions of interest common to the adjacent first and second primitive images. A human activity event is determined as a function of a shortest distance path of the temporal-event graph vertices.
摘要翻译： 通过构建具有表示从视频流解析的多个单独原始图像的相邻第一和第二原始图像的顶点的时间事件图以及与各自的第一和第二空闲状态相关联的第一和第二空闲状态，通过顺序事件检测来确定人的行为 和第二原始图像。 构造图是在相邻的第一和第二原始图像之间设置的边缘的函数，以及作为相邻第一和第二原始图像共同的感兴趣区域内的计算的视觉特征之间的差异的函数的边缘权重集合。 人类活动事件被确定为时间 - 事件图形顶点的最短距离路径的函数。
-
公开(公告)号：US08610766B2
公开(公告)日：2013-12-17
申请号：US12890007
申请日：2010-09-24
CPC分类号： G06K9/6284 , G06K9/00335 , G06K9/00771 , G08B13/19613
摘要： Human behavior alerts are determined from a video stream through application of video analytics that parse a video stream into a plurality of segments, wherein each of the segments are either temporally related to at least one of a plurality of temporally distinct transactions in an event data log; or they are each associated with a pseudo transaction marker if not temporally related to at least one of the temporally distinct transactions and an image analysis indicates a temporal correlation with at least one of the distinct transactions is expected. Visual image features are extracted from the segments and one-SVM classification is performed on the extracted features to categorize segments into inliers or outliers relative to a threshold boundary. Event of concern alerts are issued with respect to the inlier segments associated with the associated pseudo transaction marker.
摘要翻译： 通过应用将视频流解析成多个段的视频分析从视频流确定人的行为警报，其中每个段在时间上与事件数据日志中的多个时间上不同的事务中的至少一个相关 ; 或者如果与时间上不同的交易中的至少一个时间上不相关，并且图像分析指示与至少一个不同交易的时间相关性，则它们都与伪交易标记相关联。 从段中提取视觉图像特征，并且对所提取的特征执行单SVM分类，以将段分类为相对于阈值边界的内联或异常值。 关于与相关联的伪交易标记相关联的不规则段发出关注警报的事件。
-
公开(公告)号：US20120075450A1
公开(公告)日：2012-03-29
申请号：US12890007
申请日：2010-09-24
CPC分类号： G06K9/6284 , G06K9/00335 , G06K9/00771 , G08B13/19613
摘要： Human behavior alerts are determined from a video stream through application of video analytics that parse a video stream into a plurality of segments, wherein each of the segments are either temporally related to at least one of a plurality of temporally distinct transactions in an event data log; or they are each associated with a pseudo transaction marker if not temporally related to at least one of the temporally distinct transactions and an image analysis indicates a temporal correlation with at least one of the distinct transactions is expected. Visual image features are extracted from the segments and one-SVM classification is performed on the extracted features to categorize segments into inliers or outliers relative to a threshold boundary. Event of concern alerts are issued with respect to the inlier segments associated with the associated pseudo transaction marker.
摘要翻译： 通过应用将视频流解析成多个段的视频分析从视频流确定人的行为警报，其中每个段在时间上与事件数据日志中的多个时间上不同的事务中的至少一个相关 ; 或者如果与时间上不同的交易中的至少一个时间上不相关，并且图像分析指示与至少一个不同交易的时间相关性，则它们都与伪交易标记相关联。 从段中提取视觉图像特征，并且对所提取的特征执行单SVM分类，以将段分类为相对于阈值边界的内联或异常值。 关于与相关联的伪交易标记相关联的不规则段发出关注警报的事件。
-
公开(公告)号：US08478048B2
公开(公告)日：2013-07-02
申请号：US12832379
申请日：2010-07-08
申请人： Lei Ding , Quanfu Fan , Sharathchandra U. Pankanti
发明人： Lei Ding , Quanfu Fan , Sharathchandra U. Pankanti
CPC分类号： G06K9/00335 , G06K9/00771 , G08B13/19613
摘要： In an embodiment, automated analysis of video data for determination of human behavior includes providing a programmable device that segments a video stream into a plurality of discrete individual frame image primitives which are combined into a visual event that may encompass an activity of concern as a function of a hypothesis. The visual event is optimized by setting a binary variable to true or false as a function of one or more constraints. The optimized visual event is processed in view of associated non-video transaction data and the binary variable by associating the optimized visual event with a logged transaction if associable, issuing an alert if the binary variable is true and the optimized visual event is not associable with the logged transaction, and dropping the optimized visual event if the binary variable is false and the optimized visual event is not associable.
摘要翻译： 在一个实施例中，用于确定人类行为的视频数据的自动分析包括提供将视频流分段成多个离散的单独帧图像原语的可编程设备，其被组合成视觉事件，视觉事件可以包含作为功能的关注活动 一个假设。 通过将二进制变量设置为true或false作为一个或多个约束的函数来优化视觉事件。 考虑到相关联的非视频交易数据和二进制变量，通过将优化的可视事件与记录的事务相关联来处理优化的视觉事件，如果可关联，则如果二进制变量为真，并且优化的视觉事件不能与 记录的事务，并且如果二进制变量为false并且优化的可视事件不可关联，则丢弃优化的可视事件。
-
公开(公告)号：US20120093370A1
公开(公告)日：2012-04-19
申请号：US12905272
申请日：2010-10-15
申请人： Lei Ding , Quanfu Fan , Prasad Gabbur , Arun Hampapur , Sachiko Miyazawa , Sharathchandra U. Pankanti
发明人： Lei Ding , Quanfu Fan , Prasad Gabbur , Arun Hampapur , Sachiko Miyazawa , Sharathchandra U. Pankanti
IPC分类号： G06K9/00
CPC分类号： G06K9/6215 , G06K9/00335 , G06K9/00771
摘要： Determination of human behavior from an alignment of data streams includes acquiring visual image primitives from a video input comprising visual information relevant to a human activity. The primitives are temporally aligned to an optimally hypothesized sequence of primitives transformed from a sequence of transactions as a function of a distance metric between the observed primitive sequence and the transformed primitive sequence. More particularly, transforming includes comparing the distance metric costs and choosing and performing the lowest cost of temporally matching the observed primitives to one or more transactions, deleting a primitive, or associating a primitive with a pseudo transaction marker. Accordingly, alerts are issued based on analysis of the transformation of primitives.
摘要翻译： 从数据流的对齐确定人类行为包括从包括与人类活动相关的视觉信息的视频输入中获取视觉图像原语。 原语在时间上与从事件序列变换的最优假设序列的原语对齐，作为观察到的原始序列与经变换的原始序列之间的距离度量的函数。 更具体地，变换包括比较距离度量成本并选择和执行将观察到的原语暂时匹配到一个或多个事务，删除原语或将原语与伪交易标记相关联的最低成本。 因此，基于对原语的转换的分析发出警报。
-
公开(公告)号：US20120008819A1
公开(公告)日：2012-01-12
申请号：US12832379
申请日：2010-07-08
申请人： Lei Ding , Quanfu Fan , Sharathchandra U. Pankanti
发明人： Lei Ding , Quanfu Fan , Sharathchandra U. Pankanti
IPC分类号： G06K9/00
CPC分类号： G06K9/00335 , G06K9/00771 , G08B13/19613
摘要： In an embodiment, automated analysis of video data for determination of human behavior includes providing a programmable device that segments a video stream into a plurality of discrete individual frame image primitives which are combined into a visual event that may encompass an activity of concern as a function of a hypothesis. The visual event is optimized by setting a binary variable to true or false as a function of one or more constraints. The optimized visual event is processed in view of associated non-video transaction data and the binary variable by associating the optimized visual event with a logged transaction if associable, issuing an alert if the binary variable is true and the optimized visual event is not associable with the logged transaction, and dropping the optimized visual event if the binary variable is false and the optimized visual event is not associable.
摘要翻译： 在一个实施例中，用于确定人类行为的视频数据的自动分析包括提供将视频流分段成多个离散的单独帧图像原语的可编程设备，其被组合成视觉事件，视觉事件可以包含作为功能的关注活动 一个假设。 通过将二进制变量设置为true或false作为一个或多个约束的函数来优化视觉事件。 考虑到相关联的非视频交易数据和二进制变量，通过将优化的可视事件与记录的事务相关联来处理优化的视觉事件，如果可关联，则如果二进制变量为真，并且优化的视觉事件不能与 记录的事务，并且如果二进制变量为false并且优化的可视事件不可关联，则丢弃优化的可视事件。
-
公开(公告)号：US11507854B2
公开(公告)日：2022-11-22
申请号：US16739311
申请日：2020-01-10
申请人： Liang Liang , Lei Ding , Bin Dong , Shanshan Jiang , Yixuan Tong
发明人： Liang Liang , Lei Ding , Bin Dong , Shanshan Jiang , Yixuan Tong
IPC分类号： G06N5/02 , G06K9/62 , G06F16/9032 , G06N20/10
摘要： A method and an apparatus for recognizing an intention, and a non-transitory computer-readable recording medium are provided. The method includes learning vectors of knowledge base elements in corpus samples, and converting the corpus samples into row vectors composed of the vectors of the knowledge base elements in a knowledge base; extracting feature vectors from respective pooling windows in the corpus samples by hierarchical pooling, determining weights positively correlated with similarities between texts within the respective pooling windows and the respective corpus samples, performing weighting on the extracted feature vectors to obtain feature vectors of the respective pooling windows, and obtaining feature vectors of the respective corpus samples composed of the feature vectors of the pooling windows; training a vector-based intention recognition classifier, based on the feature vectors of the corpus samples; and recognizing an intention in querying a corpus, using the trained intention recognition classifier.
-
公开(公告)号：US08469729B2
公开(公告)日：2013-06-25
申请号：US13257861
申请日：2009-12-14
申请人： Lei Ding
发明人： Lei Ding
IPC分类号： H01R13/44
摘要： The present disclosure provides a rotary wireless network card with double rotating shafts, which comprises a wireless network card body, an ultra-thin USB interface and a first rotating shaft, wherein at the top of the wireless network card body a opening is provided to accommodate the ultra-thin USB interface as withdrawn; the ultra-thin USB interface extends out of or returns back to the opening by rotating around the first rotating shaft; inside the wireless network card body a rotating shaft support is provided; a second rotating shaft in the opening is rotatably connected to the rotating shaft support; the second rotating shaft is accommodated outside the ultra-thin USB interface and connected to the ultra-thin USB interface; and when the second rotating shaft rotates in the opening, the ultra-thin USB interface and the first rotating shaft rotate in the opening along with the second rotating shaft. By designing a rotary head, the present disclosure frees a USB from the external connection with a cap or other objects that are easily lost or broken, and as the rotary shaft of the ultra-thin USB interface is smaller than common rotary shafts, the whole wireless network card is much shorter and narrower, causing no interference on the use of a neighboring interface.
摘要翻译： 本公开提供一种具有双旋转轴的旋转无线网卡，其包括无线网卡主体，超薄USB接口和第一旋转轴，其中在无线网卡主体的顶部提供开口以容纳 超薄USB接口退出; 超薄USB接口通过围绕第一旋转轴旋转而延伸出或返回到开口; 在无线网卡内部提供旋转轴支撑; 开口中的第二旋转轴可旋转地连接到旋转轴支撑件; 第二旋转轴容纳在超薄USB接口外部，并连接到超薄USB接口; 并且当第二旋转轴在开口中旋转时，超薄USB接口和第一旋转轴与第二旋转轴一起在开口中旋转。 通过设计旋转磁头，本公开通过一个容易丢失或断开的盖或其它物体从外部连接中释放USB，并且当超薄USB接口的旋转轴小于普通旋转轴时，整个 无线网卡的时间要短得多，不会对相邻接口的使用造成干扰。
-
-
-
-
-
-
-
-
-
搜索结果
63 条记录 (耗时 0.025 秒)