公开(公告)号：US08934670B2

公开(公告)日：2015-01-13

申请号：US13597902

申请日：2012-08-29

申请人： Rogerio Schmidt Feris ,  Arun Hampapur ,  Zuoxuan Lu ,  Ying-li Tian

发明人： Rogerio Schmidt Feris ,  Arun Hampapur ,  Zuoxuan Lu ,  Ying-li Tian

IPC分类号： G06K9/00 ,  G06T7/20

CPC分类号： G06T7/2053 ,  G06K9/00711 ,  G06K9/00718 ,  G06K9/00771 ,  G06K9/44 ,  G06T7/187 ,  G06T7/194 ,  G06T7/254 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20036 ,  G06T2207/30232

摘要： A method and system for real time processing of a sequence of video frames. A current frame in the sequence and at least one frame in the sequence occurring prior to the current frame is analyzed. Each frame includes a two-dimensional array of pixels. The sequence of video frames is received in synchronization with a recording of the video frames in real time. The analyzing includes performing a background subtraction on the at least one frame, which determines a background image and a static region mask associated with a static region consisting of a contiguous distribution of pixels in the current frame. The static region mask identifies each pixel in the static region upon the static region mask being superimposed on the current frame. The background image includes the array of pixels and a background model of the at least one frame and does not include any moving object.

摘要翻译： 一种用于实时处理视频帧序列的方法和系统。 分析序列中的当前帧和在当前帧之前发生的序列中的至少一个帧。 每帧包括二维像素阵列。 视频帧的序列与视频帧的实时记录同步地被接收。 所述分析包括在所述至少一个帧上执行背景减除，其确定与由当前帧中的连续的像素分布组成的静态区域相关联的背景图像和静态区域掩模。 当静态区域掩模叠加在当前帧上时，静态区域掩模识别静态区域中的每个像素。 背景图像包括像素阵列和至少一个帧的背景模型，并且不包括任何移动物体。

公开(公告)号：US20080235246A1

公开(公告)日：2008-09-25

申请号：US11688287

申请日：2007-03-20

申请人： Arun Hampapur ,  Zuoxuan Lu ,  Ying-Li Tian

发明人： Arun Hampapur ,  Zuoxuan Lu ,  Ying-Li Tian

IPC分类号： G06F17/00

CPC分类号： G06Q10/06

摘要： In general, the present invention allows any number of sequential filter graphs to be created based on a pub-sub architecture/model. Specifically, under the present invention, the filters (components) will publish their ideal priorities of accessing data source, an ideal input data type, and a unique alternative input data type. A mechanism such as a queue manager will receive the publication(s) and determine an appropriate order/sequence of the filters based on their ideal priorities. The queue manager will also assign an output data type to each filter (an optionally an alternative output data type) based on the ideal input types specified in the publish messages. The queue manager will then transmit messages (e.g., a subscribe message) to the filters with the determined order and assigned data types.

摘要翻译： 通常，本发明允许基于公共子体系结构/模型创建任意数量的顺序过滤器图形。 具体来说，在本发明中，滤波器（组件）将公布其访问数据源，理想输入数据类型和唯一替代输入数据类型的理想优先级。 诸如队列管理器的机制将接收出版物，并根据其理想的优先级确定过滤器的适当顺序/顺序。 队列管理器还将根据发布消息中指定的理想输入类型为每个过滤器（可选地，替代的输出数据类型）分配输出数据类型。 然后，队列管理器将以确定的顺序和分配的数据类型将消息（例如，订阅消息）发送到过滤器。

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。

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。

公开(公告)号：US07889068B2

公开(公告)日：2011-02-15

申请号：US12052046

申请日：2008-03-20

申请人： Jonathan H. Connell, II ,  Myron D. Flickner ,  Norman Haas ,  Arun Hampapur ,  Sharathchandra U. Pankanti

发明人： Jonathan H. Connell, II ,  Myron D. Flickner ,  Norman Haas ,  Arun Hampapur ,  Sharathchandra U. Pankanti

IPC分类号： G08B19/00 ,  G08B29/00 ,  G01N31/00 ,  G06K15/00

CPC分类号： G08B13/00 ,  G06Q20/203 ,  G06Q20/209 ,  G08B13/246

摘要： Under the present invention, a single, overall alarm for an entire set of shopping items will be used for any and all discrepancies. The metric used for creating an alarm for the overall set of shopping items can be based on any one of the following candidate policies: if at least one item generated an alarm; if some fixed number of items generated an alarm; if some threshold discrepancy metric got exceed; if basket size is larger than certain threshold cash value and the alarm exceeded certain threshold alarm rate; a randomly generated alarm (e.g., random audit); the customer's identity and track record (e.g., loyalty card); and/or any combination of the above. Regardless, if an overall alarm is generated one or more of the following actions can be taken: no action send the customer to customer service; appropriately record customer track record (e.g., loyalty card) when customer identity is available; audit the customer at the “shop exit; and/or any combination of thereof.

摘要翻译： 在本发明中，对于整个购物项目的单个整体报警将用于任何和所有差异。 用于为整个购物项目创建警报的度量可以基于以下任一候选策略：如果至少一个项目产生了警报; 如果有固定数量的物品产生报警; 如果一些阈值差异度量超过了; 如果篮子尺寸大于某个门槛现金值，并且报警超过一定阈值报警率; 随机生成的警报（例如，随机审计）; 客户的身份和记录（例如会员卡）; 和/或上述的任何组合。 无论如何，如果发生整体报警，可采取以下一项或多项措施：无需向客户提供任何行动; 当客户身份可用时，适当地记录客户记录（例如会员卡）; 在“店铺出口处审核客户; 和/或其任何组合。

公开(公告)号：US20100282841A1

公开(公告)日：2010-11-11

申请号：US12436831

申请日：2009-05-07

申请人： Jonathan H. Connell II ,  Mayron D. Flickner ,  Norman Haas ,  Arun Hampapur ,  Sharathchandra U. Pankanti ,  Yashodhara M. Patnaik

发明人： Jonathan H. Connell II ,  Mayron D. Flickner ,  Norman Haas ,  Arun Hampapur ,  Sharathchandra U. Pankanti ,  Yashodhara M. Patnaik

IPC分类号： G06F17/00

CPC分类号： G07G1/12 ,  G07G1/0018 ,  G07G3/00

摘要： Under the present invention, item verification is automated and expedited. Specifically, items to be purchased can be scanned by the shopper using a barcode reader (e.g., a scanner), attached to or positioned near the checkout station. As items are scanned, they are identified based on their barcode, and added to an item list. Item verification can then be performed at checkout using imaging technology. Specifically, as items are scanned, an item verification unit will capture an appearance thereof (via a camera). Item verification software within the item verification unit will access a database that associates items with their images/appearances. The appearance will be compared for consistency to the identity as determined based on the scan. In general, the item verification unit is a separate unit from the cash register, but adapted to work in conjunction therewith (e.g., as a pluggable system, via wireless communication, etc.).

摘要翻译： 在本发明中，项目验证是自动化和加速的。 特别地，购物者可以使用连接到或位于结帐台附近的条形码读取器（例如扫描器）来扫描购物者。 当项目被扫描时，它们根据其条形码被识别，并被添加到项目列表中。 然后可以使用成像技术在结帐时执行项目验证。 具体地，当项目被扫描时，项目验证单元将捕获其外观（通过照相机）。 项目验证单元中的物品验证软件将访问将项目与其图像/外观相关联的数据库。 将根据扫描确定的一致性与身份进行比较。 通常，项目验证单元是与收银机分开的单元，但适于与其一起工作（例如，作为可插拔系统，经由无线通信等）。

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。

公开(公告)号：US08061603B2

公开(公告)日：2011-11-22

申请号：US12052051

申请日：2008-03-20

申请人： Jonathan H. Connell, II ,  Myron D. Flickner ,  Norman Haas ,  Arun Hampapur ,  Charles A. Otto ,  Sharathchandra U. Pankanti

发明人： Jonathan H. Connell, II ,  Myron D. Flickner ,  Norman Haas ,  Arun Hampapur ,  Charles A. Otto ,  Sharathchandra U. Pankanti

IPC分类号： G06K15/00

CPC分类号： G07G1/0054

摘要： The present invention provides a solution for controlling checkout throughput. Specifically, under the present invention a set of attributes of an item will be obtained. An analysis of the set of attributes will then be performed to determine whether an inconsistency exists based on a tolerance threshold. Such analysis can include, for example, comparing the weight of the item to its expected weight. This can help determine if a mistake has been made or fraud has been committed. Whether an inconsistency is observed is based on a tolerance threshold. For example, a certain deviation (i.e., the tolerance threshold) from an expected value could be allowed to could be allowed to reduce errors during the checkout process and thereby increase checkout throughput. As such, the present invention allows the tolerance threshold to be tuned based on a desired checkout throughput.

摘要翻译： 本发明提供了一种用于控制检验吞吐量的解决方案。 具体地说，在本发明中，将获得一组物品的属性。 然后将执行对该组属性的分析，以基于公差阈值确定是否存在不一致。 这种分析可以包括例如将物品的重量与其预期重量进行比较。 这可以帮助确定是否发生了错误或已经犯了欺诈。 观察到不一致是基于公差阈值。 例如，可以允许从期望值的一定偏差（即，容限阈值）被允许在结算过程期间减少错误，从而增加结帐吞吐量。 因此，本发明允许基于期望的结算吞吐量来调整公差阈值。

公开(公告)号：US20090272801A1

公开(公告)日：2009-11-05

申请号：US12112318

申请日：2008-04-30

申请人： Jonathan H. Connell, II ,  Myron D. Flickner ,  Norman Haas ,  Arun Hampapur ,  Sharathchandra U. Pankanti ,  Unsang Park

发明人： Jonathan H. Connell, II ,  Myron D. Flickner ,  Norman Haas ,  Arun Hampapur ,  Sharathchandra U. Pankanti ,  Unsang Park

IPC分类号： G06K7/00

CPC分类号： G06K17/0022 ,  G06K7/10792 ,  G06Q10/087

摘要： Aspects of the present invention provide an approach for deterring checkout fraud comprising a camera (e.g., still, video, etc.) that is located near (overhead) a scanner used to scan a barcode of an item being purchased. Specifically, the barcode of the item is scanned and an image of the item is recorded. It is then determined whether the identity of the item as determined based on the barcode is consistent with its appearance as determined from the image. If not, a discrepancy is registered. It is then determined whether the discrepancy is due to fraud (e.g., theft) or device error. In the case of the latter, the system can be updated to prevent a repeat of the error. In either event, the scan, the image and a shopping event corresponding to the scan and image can be logged for future analysis and/or learning.

摘要翻译： 本发明的方面提供了一种用于阻止结帐欺诈的方法，其包括位于扫描器附近（开销）用于扫描待购买物品的条形码的相机（例如静止图像，视频等）。 具体地，扫描项目的条形码并记录该项目的图像。 然后，确定基于条形码确定的物品的身份是否与从图像确定的外观一致。 如果不是，则注册差异。 然后确定差异是否是由于欺诈（例如盗窃）或设备错误引起的。 在后者的情况下，可以更新系统以防止重复错误。 在任一情况下，可以记录与扫描和图像相对应的扫描，图像和购物事件，以便将来进行分析和/或学习。

公开(公告)号：US20090216632A1

公开(公告)日：2009-08-27

申请号：US12037270

申请日：2008-02-26

申请人： Jonathan H. Connell, II ,  Myron D. Flickner ,  Norman Haas ,  Arun Hampapur ,  Sharathchandra U. Pankanti

发明人： Jonathan H. Connell, II ,  Myron D. Flickner ,  Norman Haas ,  Arun Hampapur ,  Sharathchandra U. Pankanti

IPC分类号： G06Q30/00

CPC分类号： G06Q30/02 ,  G06Q30/0242

摘要： The present invention provides an approach for rewarding customers for use of self-checkout stations and, optionally, for being self-sufficient in such use by not requiring retailer (employee) assistance. Specifically, the under the present invention, a set of service choices made by a customer during purchasing transactions are tracked. Such service choices include whether the customer elected to use self-checkout stations. In addition, a frequency of assistance needed by the customer during the purchasing transactions will be tracked. Such tracking can be accomplished using any known technology including the use of the customer loyalty cards that are assigned to specific customers. In any event, a reward can be offered to the customer if the customer elected to use self-checkout stations to complete at least a subset of the purchasing transactions, and/or if the frequency of assistance needed by the customer during the purchasing transactions fell below a predetermined threshold.

摘要翻译： 本发明提供了一种用于奖励客户使用自助结账站的方法，并且可选地，在不需要零售商（雇员）协助的情况下为了这种使用而自给自足。 具体地说，根据本发明，跟踪顾客在购买交易期间做出的一组服务选择。 这样的服务选择包括客户是否选择使用自助结账站。 此外，客户在采购交易中需要的频率也将被跟踪。 这种跟踪可以使用任何已知技术来实现，包括使用分配给特定客户的客户会员卡。 无论如何，如果客户选择使用自助结账站完成至少一部分采购交易，和/或如果客户在采购交易期间所需的协助频率下降，则可以向客户提供奖励 低于预定阈值。