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. 发明授权

US08582803B2 Event determination by alignment of visual and transaction data 有权
标题翻译：事件确定通过对齐视觉和交易数据
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。

2. 发明申请

US20120093370A1 EVENT DETERMINATION BY ALIGNMENT OF VISUAL AND TRANSACTION DATA 有权
标题翻译：通过视觉和交易数据的对齐确定事件
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。

3. 发明授权

US08682032B2 Event detection through pattern discovery 有权
标题翻译：通过模式发现进行事件检测
公开(公告)号：US08682032B2
公开(公告)日：2014-03-25
申请号：US13213262
申请日：2011-08-19
申请人： Quanfu Fan , Prasad Gabbur , Sachiko Miyazawa , Jiyan Pan , Sharathchandra U. Pankanti , Hoang Trinh
发明人： Quanfu Fan , Prasad Gabbur , Sachiko Miyazawa , Jiyan Pan , Sharathchandra U. Pankanti , Hoang Trinh
IPC分类号： G06K9/62
CPC分类号： G06K9/6292 , G06K9/6885
摘要： Events are classified through string pattern recognition. Text labels are assigned to image primitives in a time-ordered set of training images and to related time-ordered transactions in an associated training transaction log in a combined time-ordered training string of text labels as a function of image types. Transactions are labeled in a training transaction log with a transaction label, a training primitive image of a start of a transaction with a start image text label, a training primitive of an entry of a transaction into the log with an entry image text label, and a training primitive of a conclusion of a transaction with an ending image text label. Positive subset string patterns are discovered representing true events from the combined time-ordered training string of text labels, and negative subset string patterns defined by removing single transaction primitive labels from the positive subset string patterns.
摘要翻译：事件通过字符串模式识别分类。将文本标签分配给训练图像的时间有序集合中的图像原语以及相关联的训练事务日志中的相关时间顺序事务，其中文本标签的组合时间有序训练串作为图像类型的函数。事务在具有事务标签的训练事务日志中被标记，具有开始图像文本标签的事务开始的训练原始图像，具有条目图像文本标签的事务入口的训练原语以及与结束图像文本标签交易结论的训练原语。从组合的时间有序的文本标签的训练串中发现表示真实事件的正的子集字符串模式，以及通过从正的子集字符串模式中去除单个事务原始标签而定义的负子集串模式。

4. 发明申请

US20130044942A1 EVENT DETECTION THROUGH PATTERN DISCOVERY 有权
标题翻译：通过图案发现的事件检测
公开(公告)号：US20130044942A1
公开(公告)日：2013-02-21
申请号：US13213262
申请日：2011-08-19
申请人： Quanfu Fan , Prasad Gabbur , Sachiko Miyazawa , Jiyan Pan , Sharathchandra U. Pankanti , Hoang Trinh
发明人： Quanfu Fan , Prasad Gabbur , Sachiko Miyazawa , Jiyan Pan , Sharathchandra U. Pankanti , Hoang Trinh
IPC分类号： G06K9/62
CPC分类号： G06K9/6292 , G06K9/6885
摘要： Events are classified through string pattern recognition. Text labels are assigned to image primitives in a time-ordered set of training images and to related time-ordered transactions in an associated training transaction log in a combined time-ordered training string of text labels as a function of image types. Transactions are labeled in a training transaction log with a transaction label, a training primitive image of a start of a transaction with a start image text label, a training primitive of an entry of a transaction into the log with an entry image text label, and a training primitive of a conclusion of a transaction with an ending image text label. Positive subset string patterns are discovered representing true events from the combined time-ordered training string of text labels, and negative subset string patterns defined by removing single transaction primitive labels from the positive subset string patterns.
摘要翻译：事件通过字符串模式识别分类。将文本标签分配给训练图像的时间有序集合中的图像原语以及相关联的训练事务日志中的相关时间顺序事务，其中文本标签的组合时间有序训练串作为图像类型的函数。事务在具有事务标签的训练事务日志中被标记，具有开始图像文本标签的事务开始的训练原始图像，具有条目图像文本标签的事务入口的训练原语以及与结束图像文本标签交易结论的训练原语。从组合的时间有序的文本标签的训练串中发现表示真实事件的正的子集字符串模式，以及通过从正的子集字符串模式中去除单个事务原始标签而定义的负子集串模式。

5. 发明申请

US20130050517A1 VISUAL CONTENT-AWARE AUTOMATIC CAMERA ADJUSTMENT 失效
标题翻译：视觉内容自动相机调整
公开(公告)号：US20130050517A1
公开(公告)日：2013-02-28
申请号：US13218845
申请日：2011-08-26
申请人： Quanfu Fan , Prasad Gabbur , Sachiko Miyazawa , Sharathchandra U. Pankanti , Hoang Trinh
发明人： Quanfu Fan , Prasad Gabbur , Sachiko Miyazawa , Sharathchandra U. Pankanti , Hoang Trinh
IPC分类号： H04N5/228 , G06K9/00
CPC分类号： G06K9/00 , G06K9/00771 , H04N5/232 , H04N5/23222
摘要： Visual content in images captured from a scene by a camera in each of a plurality of different pose settings are analyzed to determine predicted occurrences of a transaction associated with the visual content in each pose, which are compared with actual transaction occurrence data to generate performance values for each pose as a function difference between the predicted and actual transactions. Optimized poses are chosen having the best performance value, wherein a camera controller may place the camera in the optimum pose for use in monitoring the scene and generating the primitives of interest associated with the transactions.
摘要翻译：分析由多个不同姿势设置中的每一个中的摄像机从场景捕获的图像中的视觉内容，以确定与每个姿态中的视觉内容相关联的事务的预测出现，其与实际交易发生数据进行比较以生成性能值对于每个姿势作为预测和实际交易之间的功能差异。选择具有最佳性能值的优化姿态，其中相机控制器可将相机放置在用于监视场景的最佳姿态并产生与交易相关联的感兴趣的原始图案。

6. 发明授权

US08610766B2 Activity determination as function of transaction log 有权
标题翻译：活动确定作为事务日志的功能
公开(公告)号：US08610766B2
公开(公告)日：2013-12-17
申请号：US12890007
申请日：2010-09-24
申请人： Lei Ding , Quanfu Fan , Arun Hampapur , Sharathchandra U. Pankanti
发明人： Lei Ding , Quanfu Fan , Arun Hampapur , Sharathchandra U. Pankanti
IPC分类号： G06K9/00 , H04N7/18
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。

7. 发明申请

US20120075450A1 ACTIVITY DETERMINATION AS FUNCTION OF TRANSACTION LOG 有权
标题翻译：作为交易日志功能的活动决定
公开(公告)号：US20120075450A1
公开(公告)日：2012-03-29
申请号：US12890007
申请日：2010-09-24
申请人： Lei Ding , Quanfu Fan , Arun Hampapur , Sharathchandra U. Pankanti
发明人： Lei Ding , Quanfu Fan , Arun Hampapur , Sharathchandra U. Pankanti
IPC分类号： G06K9/00 , H04N7/18
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。

8. 发明申请

US20120008836A1 SEQUENTIAL EVENT DETECTION FROM VIDEO 有权
标题翻译：视频中的顺序事件检测
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
IPC分类号： G06K9/00 , G06T11/20
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。

9. 发明授权

US08548203B2 Sequential event detection from video 有权
标题翻译：来自视频的连续事件检测
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
IPC分类号： G06K9/00 , G06K9/48
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。

10. 发明申请

US20100111404A1 DYNAMICALLY LEARNING ATTRIBUTES OF A POINT OF SALE OPERATOR 失效
标题翻译：动态点销售操作员的动态学习属性
公开(公告)号：US20100111404A1
公开(公告)日：2010-05-06
申请号：US12261304
申请日：2008-10-30
申请人： Russell P. Bobbitt , Quanfu Fan , Arun Hampapur , Frederik C. M. Kjeldsen , Sharathchandra U. Pankanti , Akira Yanagawa , Yun Zhai
发明人： Russell P. Bobbitt , Quanfu Fan , Arun Hampapur , Frederik C. M. Kjeldsen , Sharathchandra U. Pankanti , Akira Yanagawa , Yun Zhai
IPC分类号： G06K9/66
CPC分类号： G06K9/00771
摘要： An approach that dynamically learns a set of attributes of an operator of a point of sale (POS) is provided. In one embodiment, there is an attribute tool, including an extraction component configured to receive sensor data of a set of moving objects, and extract a set of attributes from each of the set of moving objects captured within the scan area at the POS; an identification component configured to update an appearance model with the set of attributes from each of the set of moving objects; and an analysis component configured to analyze the appearance model to identify at least one of the set of moving objects as an operator of the POS.
摘要翻译：提供了动态学习销售点（POS）的运营商的一组属性的方法。在一个实施例中，存在一种属性工具，包括被配置为接收一组移动对象的传感器数据的提取部件，并且从POS中的扫描区域内捕获的移动对象集合中的每一个提取一组属性; 识别组件，被配置为使用来自所述一组移动对象的所述一组属性来更新外观模型; 以及分析部件，被配置为分析所述外观模型以将所述一组移动对象中的至少一个识别为所述POS的操作者。

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