公开(公告)号：US08760519B2

公开(公告)日：2014-06-24

申请号：US11675849

申请日：2007-02-16

申请人： Hasan Timucin Ozdemir ,  Kuo Chu Lee

发明人： Hasan Timucin Ozdemir ,  Kuo Chu Lee

IPC分类号： H04N7/18 ,  G08B13/196 ,  H04N5/228

CPC分类号： G08B13/19608 ,  G08B13/19645 ,  G08B25/009 ,  H04N7/188

摘要： A method is provided for detecting a threat in a distributed multi-camera surveillance system. The method includes: monitoring movement of an object in a field of view of a first camera using software installed at the first camera; detecting a suspicious object at the first camera when movement of the object does not conform with a motion flow model residing at the first camera; sending a tracking request from the first camera to a second camera upon detecting the suspicious object at the first camera; monitoring movement of the object in a field of view of the second camera using software installed at the second camera; assigning threat scores at the second camera when the movement of the object does not conform with a motion flow model residing at the second camera; and generating an alarm based in part on the threat scores detected at the first camera and the second camera.

摘要翻译： 提供了一种用于检测分布式多摄像机监视系统中的威胁的方法。 该方法包括：使用安装在第一相机的软件监视第一相机的视场中的对象的移动; 当物体的移动不符合驻留在第一相机的运动流模型时，在第一相机处检测可疑物体; 在第一相机检测到可疑对象时，将第一相机的跟踪请求发送到第二相机; 使用安装在第二相机上的软件监视第二相机的视场中的对象的移动; 当对象的移动不符合驻留在第二相机的运动流模型时，在第二相机处分配威胁分数; 并且部分地基于在第一相机和第二相机处检测到的威胁分数来产生报警。

公开(公告)号：US07667596B2

公开(公告)日：2010-02-23

申请号：US11676127

申请日：2007-02-16

申请人： Hasan Timucin Ozdemir ,  Sameer Kibey ,  Lipin Liu ,  Kuo Chu Lee ,  Supraja Mosali ,  Namsoo Joo ,  Hongbing Li ,  Juan Yu

发明人： Hasan Timucin Ozdemir ,  Sameer Kibey ,  Lipin Liu ,  Kuo Chu Lee ,  Supraja Mosali ,  Namsoo Joo ,  Hongbing Li ,  Juan Yu

IPC分类号： G08B13/00

CPC分类号： G08B31/00 ,  G08B13/196 ,  G08B21/0423

摘要： A surveillance system generally includes a data capture module that collects sensor data. A scoring engine module receives the sensor data and computes at least one of an abnormality score and a normalcy score based on the sensor data, at least one dynamically loaded learned data model, and a learned scoring method. A decision making module receives the at least one of the abnormality score and the normalcy score and generates an alert message based on the at least one of the abnormality score and the normalcy score and a learned decision making method to produce progressive behavior and threat detection.

摘要翻译： 监视系统通常包括收集传感器数据的数据捕获模块。 评分引擎模块接收传感器数据，并且基于传感器数据，至少一个动态加载的学习数据模型和学习评分方法来计算异常分数和正常分数中的至少一个。 决策模块接收异常分数和正常分数中的至少一个，并且基于异常得分和正常分数中的至少一个产生警报消息，以及学习决策方法来产生渐进行为和威胁检测。

公开(公告)号：US20090276705A1

公开(公告)日：2009-11-05

申请号：US12034181

申请日：2008-05-05

申请人： Hasan Timucin Ozdemir ,  Hongbing Li ,  Lipin Liu ,  Kuo Chu Lee ,  Namsoo Joo

发明人： Hasan Timucin Ozdemir ,  Hongbing Li ,  Lipin Liu ,  Kuo Chu Lee ,  Namsoo Joo

IPC分类号： G06F3/00

CPC分类号： G06K9/00771 ,  G06K9/00335

摘要： A multi-perspective context sensitive behavior assessment system includes an adaptive behavior model builder establishing a real-time reference model that captures intention of motion behavior. It operates by modeling outputs of multiple user defined scoring functions with respect to multiple references of application specific target areas of interest. The target areas have criticality values representing a user's preference regarding the target areas with respect to one another. The outputs of the scoring functions are multiplied by the critically values to form high level sequences of representation that are communicated to the user.

摘要翻译： 多视角上下文敏感行为评估系统包括建立实时参考模型的自适应行为模型构建器，其捕获运动行为的意图。 它通过针对感兴趣的应用程序特定目标区域的多个引用对多个用户定义的评分函数的输出进行建模来进行操作。 目标区域具有表示用户相对于彼此的目标区域的偏好的临界值。 评分函数的输出乘以临界值以形成传达给用户的高级表示序列。

公开(公告)号：US07567562B2

公开(公告)日：2009-07-28

申请号：US11070797

申请日：2005-03-02

申请人： K. C. Lee ,  Hasan Timucin Ozdemir

发明人： K. C. Lee ,  Hasan Timucin Ozdemir

IPC分类号： H04L12/28

CPC分类号： H04L45/00

摘要： The originator requests information from a target by launching a receptor agent that propagates across the mobile ad hoc network to the target. Along the way, intermediate nodes retain copies of the receptor. The target adds reply information to the receptor and launches it onto the network. When the reply-bearing receptor rendezvous with a receptor copies that contain matching patterns corresponding to the reply-bearing receptor, the reply information is transferred to those receptor copies. The information transferred may be encrypted at the target, using encryption key supplied by the originator. In this way, intermediate nodes cannot access the information being propagated in the receptors that they host.

摘要翻译： 发起者通过启动通过移动自组织网络传播到目标的受体代理来从目标者请求信息。 一路上，中间节点保留受体的拷贝。 目标将回复信息添加到受体，并将其发送到网络上。 当受体受体复合物与含有与应答受体相对应的匹配模式的受体拷贝时，应答信息被转移到这些受体拷贝。 传输的信息可以使用由发起者提供的加密密钥在目标处加密。 以这种方式，中间节点不能访问在它们所承载的受体中传播的信息。

公开(公告)号：US07426743B2

公开(公告)日：2008-09-16

申请号：US11058557

申请日：2005-02-15

申请人： Kuo Chu Lee ,  Lipin Liu ,  Hasan Timucin Ozdemir

发明人： Kuo Chu Lee ,  Lipin Liu ,  Hasan Timucin Ozdemir

IPC分类号： H04N7/173 ,  H04N5/225 ,  H04N5/232

CPC分类号： H04N5/23206 ,  H04N5/232 ,  H04N7/181

摘要： A peer-to-peer camera sensor network is defined using intelligent cameras that employ iSCSI initiators and iSCSI targets to read and write data and to send control commands directly across the network as iSCSI blocks. Because data transfer rides on top of the internet protocol, cameras can be directly attached to the internet without requiring attachment to a host computer. Image data represented as video frames are mapped onto iSCSI data blocks and are shared among the cameras directly to form an efficient virtual block level video image frame storage that can be directly manipulated by multiple cameras without data replications. Transport of multiple streams, associated with scalable or multilevel MPEG encoding scheme for instance, are automatically sequenced and realigned as the iSCSI data blocks are time-aligned.

摘要翻译： 使用智能摄像机定义对等摄像机传感器网络，该摄像机采用iSCSI启动器和iSCSI目标来读取和写入数据，并通过网络作为iSCSI块直接发送控制命令。 由于数据传输是在互联网协议之上进行的，摄像机可以直接连接到互联网，而无需附加到主机。 表示为视频帧的图像数据被映射到iSCSI数据块，并且直接在相机之间共享，以形成可以由多个摄像机直接操纵而无需数据复制的有效的虚拟块级视频图像帧存储。 例如，与可扩展或多级MPEG编码方案相关联的多个流的传输将自动排序并重新对齐，因为iSCSI数据块是时间对齐的。

公开(公告)号：US07237260B2

公开(公告)日：2007-06-26

申请号：US10614909

申请日：2003-07-08

申请人： Juan Yu ,  Hasan Timucin Ozdemir ,  Kuo Chu Lee ,  Shiwen Chen ,  Eimei Nanma

发明人： Juan Yu ,  Hasan Timucin Ozdemir ,  Kuo Chu Lee ,  Shiwen Chen ,  Eimei Nanma

IPC分类号： H04L29/00 ,  H04L29/06

CPC分类号： H04L63/0272 ,  H04L63/0823 ,  H04L63/166

摘要： Distributed modules in a network dynamically select communication protocols to communicate in a secure or firewall-protected network. Applications register with a lookup service. The lookup service maintains a lookup table including registration information for multiple applications. Registration information may include, but is not limited to, IP address, firewall restrictions, tunnel protocol, port information, and proxy queue capabilities. An application seeking to communicate acquires the registration information for a desired recipient from the lookup table. The application uses the registration information to select communication protocols necessary to communicate with the recipient.

摘要翻译： 网络中的分布式模块动态选择通信协议，以在安全或防火墙保护的网络中进行通信。 应用程序注册一个查找服务。 查找服务维护包括多个应用的​​注册信息的查找表。 注册信息可以包括但不限于IP地址，防火墙限制，隧道协议，端口信息和代理队列功能。 寻求通信的应用从查找表获取期望的接收者的注册信息。 应用程序使用注册信息来选择与接收者通信所需的通信协议。

公开(公告)号：US08253564B2

公开(公告)日：2012-08-28

申请号：US12496724

申请日：2009-07-02

申请人： Kuo Chu Lee ,  Hasan Timucin Ozdemir ,  Juan Yu

发明人： Kuo Chu Lee ,  Hasan Timucin Ozdemir ,  Juan Yu

IPC分类号： G08B21/00

CPC分类号： G06K9/00771

摘要： A system and method for predictive abnormal behavior detection is disclosed. The system receives surveillance data such as video data and can create and update a plurality of prediction models. The system may also receive video data relating to a moving object and may generate a prediction of the future locations of the moving object based on the generated prediction models. The predicted motion may be scored by a scoring engine to determine if the predicted motion is unsafe or otherwise undesirable.

摘要翻译： 公开了一种用于预测性异常行为检测的系统和方法。 该系统接收诸如视频数据的监控数据，并且可以创建和更新多个预测模型。 该系统还可以接收与移动对象相关的视频数据，并且可以基于所生成的预测模型生成运动对象的未来位置的预测。 预测的运动可以由评分引擎评分，以确定预测的运动是不安全的还是不希望的。

公开(公告)号：US08169481B2

公开(公告)日：2012-05-01

申请号：US12034181

申请日：2008-05-05

申请人： Hasan Timucin Ozdemir ,  Hongbing Li ,  Lipin Liu ,  Kuo Chu Lee ,  Namsoo Joo

发明人： Hasan Timucin Ozdemir ,  Hongbing Li ,  Lipin Liu ,  Kuo Chu Lee ,  Namsoo Joo

IPC分类号： H04N7/18

CPC分类号： G06K9/00771 ,  G06K9/00335

摘要： A multi-perspective context sensitive behavior assessment system includes an adaptive behavior model builder establishing a real-time reference model that captures intention of motion behavior. It operates by modeling outputs of multiple user defined scoring functions with respect to multiple references of application specific target areas of interest. The target areas have criticality values representing a user's preference regarding the target areas with respect to one another. The outputs of the scoring functions are multiplied by the critically values to form high level sequences of representation that are communicated to the user.

摘要翻译： 多视角上下文敏感行为评估系统包括建立实时参考模型的自适应行为模型构建器，其捕获运动行为的意图。 它通过针对感兴趣的应用程序特定目标区域的多个引用对多个用户定义的评分函数的输出进行建模来进行操作。 目标区域具有表示用户相对于彼此的目标区域的偏好的临界值。 评分函数的输出乘以临界值以形成传达给用户的高级表示序列。

公开(公告)号：US20100207762A1

公开(公告)日：2010-08-19

申请号：US12496724

申请日：2009-07-02

申请人： Kuo Chu LEE ,  Hasan Timucin Ozdemir ,  Juan Yu

发明人： Kuo Chu LEE ,  Hasan Timucin Ozdemir ,  Juan Yu

IPC分类号： G08B13/00 ,  G06F15/18 ,  G06K9/00 ,  G06N5/02

CPC分类号： G06K9/00771

摘要： A system and method for predictive abnormal behavior detection is disclosed. The system receives surveillance data such as video data and can create and update a plurality of prediction models. The system may also receive video data relating to a moving object and may generate a prediction of the future locations of the moving object based on the generated prediction models. The predicted motion may be scored by a scoring engine to determine if the predicted motion is unsafe or otherwise undesirable.

摘要翻译： 公开了一种用于预测性异常行为检测的系统和方法。 该系统接收诸如视频数据的监控数据，并且可以创建和更新多个预测模型。 该系统还可以接收与移动对象相关的视频数据，并且可以基于所生成的预测模型生成运动对象的未来位置的预测。 预测的运动可以由评分引擎评分，以确定预测的运动是不安全的还是不希望的。

公开(公告)号：US20090210373A1

公开(公告)日：2009-08-20

申请号：US12034164

申请日：2008-02-20

申请人： Juan Yu ,  Hasan Timucin Ozdemir ,  Kuo Chu Lee

发明人： Juan Yu ,  Hasan Timucin Ozdemir ,  Kuo Chu Lee

IPC分类号： G06N5/02

CPC分类号： G06K9/00771 ,  A61B5/1128 ,  A61B5/16 ,  A61B5/7267 ,  G06K9/00785

摘要： A surveillance system implements an architecture and process to support real-time abnormal behavior assessment operations in a distributed scalable sensor network. An automated behavior model builder generates behavior models from sensor data. A plurality of abnormal behavior scoring engines operating concurrently to generate abnormal behavior assessment models by scoring the behavior models. An execution performance manager performs fast switching of behavior models for the abnormal behavior scoring engines. The execution performance manager performs detection of abnormal behavior score distribution characteristic deviation by comparing a current abnormal behavior assessment model to a pre-recorded abnormal behavior assessment model. The execution performance manager selects a pre-recorded behavior model for the abnormal behavior scoring engines when the deviation exceeds a predetermined threshold.

摘要翻译： 监控系统实现一种架构和过程，以支持分布式可扩展传感器网络中的实时异常行为评估操作。 自动行为模型构建器从传感器数据生成行为模型。 多个异常行为评分引擎同时运行，通过评分行为模型来产生异常行为评估模型。 执行性能管理员可以快速切换异常行为评分引擎的行为模型。 执行绩效管理者通过将当前的异常行为评估模型与预先记录的异常行为评估模型进行比较来执行异常行为评分分布特征偏差的检测。 当偏差超过预定阈值时，执行性能管理器为异常行为评分引擎选择预先记录的行为模型。