公开(公告)号：US09507768B2

公开(公告)日：2016-11-29

申请号：US14457060

申请日：2014-08-11

Applicant: Behavioral Recognition Systems, Inc.

Inventor： Wesley Kenneth Cobb ,  Ming-Jung Seow ,  Curtis Edward Cole, Jr. ,  Cody Shay Falcon ,  Benjamin A. Konosky ,  Charles Richard Morgan ,  Aaron Poffenberger ,  Thong Toan Nguyen

IPC: G06F17/27 ,  H04L29/06 ,  G06N99/00

CPC classification number: H04L63/1425 ,  G06F17/2725 ,  G06F17/2735 ,  G06F17/274 ,  G06F17/277 ,  G06F17/2775 ,  G06F17/2785 ,  G06F17/2795 ,  G06F17/28 ,  G06N99/005 ,  H04L63/1408

Abstract: Embodiments presented herein describe a method for processing streams of data of one or more networked computer systems. According to one embodiment of the present disclosure, an ordered stream of normalized vectors corresponding to information security data obtained from one or more sensors monitoring a computer network is received. A neuro-linguistic model of the information security data is generated by clustering the ordered stream of vectors and assigning a letter to each cluster, outputting an ordered sequence of letters based on a mapping of the ordered stream of normalized vectors to the clusters, building a dictionary of words from of the ordered output of letters, outputting an ordered stream of words based on the ordered output of letters, and generating a plurality of phrases based on the ordered output of words.

Abstract translation: 本文提出的实施例描述了一种用于处理一个或多个联网的计算机系统的数据流的方法。 根据本公开的一个实施例，接收与从监视计算机网络的一个或多个传感器获得的信息安全数据相对应的归一化向量的有序流。 信息安全数据的神经语言模型是通过将有序的向量流聚类并分配给每个聚类的一个字母来生成的，其基于归一化向量的有序流向集群的映射输出有序的字母序列，构建一个 根据有序输出的字母的字的词典，基于字母的有序输出输出有序的单词流，并且基于单词的有序输出生成多个短语。

公开(公告)号：US20140050355A1

公开(公告)日：2014-02-20

申请号：US13971027

申请日：2013-08-20

Applicant: Behavioral Recognition Systems, Inc.

Inventor： Wesley Kenneth COBB

IPC: G06K9/00

CPC classification number: G06T7/0004 ,  G06K9/00664 ,  G06K9/00718 ,  G06K9/00771 ,  G06T7/10 ,  G06T7/194 ,  G06T2207/30108

Abstract: A behavioral recognition system may include both a computer vision engine and a machine learning engine configured to observe and learn patterns of behavior in video data. Certain embodiments may be configured to detect and evaluate the presence of sea-surface oil on the water surrounding an offshore oil platform. The computer vision engine may be configured to segment image data into detected patches or blobs of surface oil (foreground) present in the field of view of an infrared camera (or cameras). A machine learning engine may evaluate the detected patches of surface oil to learn to distinguish between sea-surface oil incident to the operation of an offshore platform and the appearance of surface oil that should be investigated by platform personnel.

Abstract translation: 行为识别系统可以包括计算机视觉引擎和被配置为观察和学习视频数据中的行为模式的机器学习引擎。 某些实施例可以被配置为检测和评估在海上石油平台周围的水面上的海面油的存在。 计算机视觉引擎可以被配置为将图像数据分割成在红外线照相机（或照相机）的视野中存在的检测到的表面油（前景）的斑块或斑块。 机器学习引擎可以评估检测到的地表油块，以学习区分海上平台操作的海面油和平台人员应该调查的表面油的外观。

公开(公告)号：US20130243252A1

公开(公告)日：2013-09-19

申请号：US13836372

申请日：2013-03-15

Applicant: BEHAVIORAL RECOGNITION SYSTEMS, INC.

Inventor： Gang XU ,  Wesley Kenneth COBB

IPC: G06K9/32

CPC classification number: G08B29/185 ,  G06K9/00369 ,  G06K9/00771 ,  G06K9/00778 ,  G06K9/3241 ,  G06K9/52 ,  G06K9/6254 ,  G08B13/19608 ,  G08B21/182 ,  G08B23/00 ,  H04N7/002

Abstract: A behavioral recognition system may include both a computer vision engine and a machine learning engine configured to observe and learn patterns of behavior in video data. Certain embodiments may be configured to learn patterns of behavior consistent with a person loitering and generate alerts for same. Upon receiving information of a foreground object remaining in a scene over a threshold period of time, a loitering detection module evaluates the whether the object trajectory corresponds to a random walk. Upon determining that the trajectory does correspond, the loitering detection module generates a loitering alert.

Abstract translation: 行为识别系统可以包括计算机视觉引擎和被配置为观察和学习视频数据中的行为模式的机器学习引擎。 某些实施例可以被配置为学习与人游荡相一致的行为模式，并为其产生警报。 一旦在阈值时间段内接收到场景中剩余的前景物体的信息，则游荡检测模块评​​估对象轨迹是否对应于随机游走。 在确定轨迹确实对应时，游荡检测模块产生漂流警报。

公开(公告)号：US20130121533A1

公开(公告)日：2013-05-16

申请号：US13722812

申请日：2012-12-20

Applicant: BEHAVIORAL RECOGNITION SYSTEMS, INC.

Inventor： Wesley Kenneth COBB ,  David Samuel FRIEDLANDER ,  Kishor Adinath SAITWAL

IPC: G06K9/00

CPC classification number: G06K9/00771 ,  G06K9/6222 ,  G06K9/6296 ,  G06T7/248 ,  G06T2207/10016 ,  G06T2207/30196 ,  G06T2207/30232 ,  G06T2207/30236 ,  G06T2207/30241

Abstract: A sequence layer in a machine-learning engine configured to learn from the observations of a computer vision engine. In one embodiment, the machine-learning engine uses the voting experts to segment adaptive resonance theory (ART) network label sequences for different objects observed in a scene. The sequence layer may be configured to observe the ART label sequences and incrementally build, update, and trim, and reorganize an ngram trie for those label sequences. The sequence layer computes the entropies for the nodes in the ngram trie and determines a sliding window length and vote count parameters. Once determined, the sequence layer may segment newly observed sequences to estimate the primitive events observed in the scene as well as issue alerts for inter-sequence and intra-sequence anomalies.

Abstract translation: 机器学习引擎中的序列层，被配置为从计算机视觉引擎的观察中学习。 在一个实施例中，机器学习引擎使用投票专家来分割在场景中观察到的不同对象的自适应共振理论（ART）网络标签序列。 序列层可以被配置为观察ART标签序列并且逐渐地构建，更新和修整和重组那些标记序列的ngram特里。 序列层计算ngram trie中节点的熵，并确定滑动窗口长度和投票计数参数。 一旦确定，序列层可以划分新观察到的序列以估计在场景中观察到的原始事件以及发出序列间和序列内异常的警报。

公开(公告)号：US20120275649A1

公开(公告)日：2012-11-01

申请号：US13545950

申请日：2012-07-10

Applicant: Wesley Kenneth COBB ,  Ming-Jung SEOW ,  Tao YANG

Inventor： Wesley Kenneth COBB ,  Ming-Jung SEOW ,  Tao YANG

IPC: G06K9/62

CPC classification number: G06K9/00771 ,  G06T7/215 ,  G06T7/254 ,  G06T2207/10016 ,  G06T2207/30196 ,  G06T2207/30236 ,  G06T2207/30241 ,  G08B13/19608

Abstract: Techniques are disclosed for detecting foreground objects in a scene captured by a surveillance system and tracking the detected foreground objects from frame to frame in real time. A motion flow field is used to validate foreground objects(s) that are extracted from the background model of a scene. Spurious foreground objects are filtered before the foreground objects are provided to the tracking stage. The motion flow field is also used by the tracking stage to improve the performance of the tracking as needed for real time surveillance applications.

Abstract translation: 公开了用于检测由监视系统捕获的场景中的前景物体并且实时地从帧到帧跟踪检测到的前景物体的技术。 运动流场用于验证从场景的背景模型中提取的前景对象。 在将前景对象提供给跟踪阶段之前，会对前景对象进行过滤。 跟踪阶段还使用运动流场来提高实时监控应用所需的跟踪性能。

公开(公告)号：US08285046B2

公开(公告)日：2012-10-09

申请号：US12388409

申请日：2009-02-18

Applicant: Wesley Kenneth Cobb ,  Kishor Adinath Saitwal ,  Bobby Ernest Blythe ,  Tao Yang

Inventor： Wesley Kenneth Cobb ,  Kishor Adinath Saitwal ,  Bobby Ernest Blythe ,  Tao Yang

IPC: G06K9/34

CPC classification number: G06K9/00771

Abstract: Techniques are disclosed for a computer vision engine to update both a background model and thresholds used to classify pixels as depicting scene foreground or background in response to detecting that a sudden illumination changes has occurred in a sequence of video frames. The threshold values may be used to specify how much pixel a given pixel may differ from corresponding values in the background model before being classified as depicting foreground. When a sudden illumination change is detected, the values for pixels affected by sudden illumination change may be used to update the value in the background image to reflect the value for that pixel following the sudden illumination change as well as update the threshold for classifying that pixel as depicting foreground/background in subsequent frames of video.

Abstract translation: 公开了用于计算机视觉引擎的技术，用于更新背景模型和用于将像素分类为描绘场景前景或背景的阈值，以响应于检测到在视频帧序列中已经发生突然的照明变化。 可以使用阈值来指定给定像素在分类为描绘前景之前可能与背景模型中的对应值不同的像素。 当检测到突然的照明变化时，可以使用受突然照明改变影响的像素的值来更新背景图像中的值，以反映在突然照射变化之后该像素的值，并且更新用于对该像素进行分类的阈值 作为描绘后续视频帧中的前景/背景。

公开(公告)号：US08218819B2

公开(公告)日：2012-07-10

申请号：US12552210

申请日：2009-09-01

Applicant: Wesley Kenneth Cobb ,  Ming-Jung Seow ,  Tao Yang

Inventor： Wesley Kenneth Cobb ,  Ming-Jung Seow ,  Tao Yang

IPC: G06K9/00

CPC classification number: G06K9/00771 ,  G06T7/215 ,  G06T7/254 ,  G06T2207/10016 ,  G06T2207/30196 ,  G06T2207/30232 ,  G06T2207/30236 ,  G06T2207/30241 ,  G08B13/19608

Abstract: Techniques are disclosed for detecting foreground objects in a scene captured by a surveillance system and tracking the detected foreground objects from frame to frame in real time. A motion flow field is used to validate foreground objects(s) that are extracted from the background model of a scene. Spurious foreground objects are filtered before the detected foreground objects are provided to the tracking stage. The motion flow field is also used by the tracking stage to improve the performance of the tracking as needed for real time surveillance applications.

Abstract translation: 公开了用于检测由监视系统捕获的场景中的前景物体并且实时地从帧到帧跟踪检测到的前景物体的技术。 运动流场用于验证从场景的背景模型中提取的前景对象。 在检测到的前景对象提供给跟踪阶段之前，会对前景对象进行过滤。 跟踪阶段还使用运动流场来提高实时监控应用所需的跟踪性能。

公开(公告)号：US08189905B2

公开(公告)日：2012-05-29

申请号：US12170283

申请日：2008-07-09

Applicant: John Eric Eaton ,  Wesley Kenneth Cobb ,  Dennis G. Urech ,  David S. Friedlander ,  Gang Xu ,  Ming-Jung Seow ,  Lon W. Risinger ,  David M. Solum ,  Tao Yang ,  Rajkiran K. Gottumukkal ,  Kishor Adinath Saitwal

Inventor： John Eric Eaton ,  Wesley Kenneth Cobb ,  Dennis G. Urech ,  David S. Friedlander ,  Gang Xu ,  Ming-Jung Seow ,  Lon W. Risinger ,  David M. Solum ,  Tao Yang ,  Rajkiran K. Gottumukkal ,  Kishor Adinath Saitwal

IPC: G06K9/62 ,  G06K9/00

CPC classification number: G06K9/00718 ,  G06F17/30598 ,  G06K9/00335 ,  G06K9/00751 ,  G06K9/00771 ,  G06K9/6215 ,  G06K9/66 ,  G06K2009/00738 ,  G06N99/005

Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.

Abstract translation: 公开了一种机器学习引擎，其被配置为通过随时间分析移动和/或活动（或不存在）来识别和学习行为，以及识别和区分场景内的正常和异常行为。 机器学习引擎可以被配置为评估为视频帧序列和相关向量表示中描绘的对象生成的原始事件序列和相关联的运动学数据序列。 从原始事件符号流和相位空间符号流生成向量表示，并且流描述在视频帧序列中描绘的对象的动作。

公开(公告)号：US08175333B2

公开(公告)日：2012-05-08

申请号：US12208526

申请日：2008-09-11

Applicant: John Eric Eaton ,  Wesley Kenneth Cobb ,  Rajkiran K. Gottumukkal ,  Ming-Jung Seow ,  Tao Yang ,  Kishor Adinath Saitwal

Inventor： John Eric Eaton ,  Wesley Kenneth Cobb ,  Rajkiran K. Gottumukkal ,  Ming-Jung Seow ,  Tao Yang ,  Kishor Adinath Saitwal

IPC: G06K9/00

CPC classification number: G06F15/16

Abstract: An estimator/identifier component for a computer vision engine of a machine-learning based behavior-recognition system is disclosed. The estimator/identifier component may be configured to classify an object being one of two or more classification types, e.g., as being a vehicle or a person. Once classified, the estimator/identifier may evaluate the object to determine a set of kinematic data, static data, and a current pose of the object. The output of the estimator/identifier component may include the classifications assigned to a tracked object, as well as the derived information and object attributes.

Abstract translation: 公开了一种基于机器学习的行为识别系统的计算机视觉引擎的估计/标识符组件。 估计器/标识符组件可以被配置为将作为两个或更多个分类类型之一的对象进行分类，例如，作为车辆或人。 一旦分类，估计器/标识符可以评估对象以确定一组运动学数据，静态数据和对象的当前姿态。 估计器/标识符组件的输出可以包括分配给跟踪对象的分类以及派生的信息和对象属性。

公开(公告)号：US08167430B2

公开(公告)日：2012-05-01

申请号：US12551364

申请日：2009-08-31

Applicant: Wesley Kenneth Cobb ,  Ming-Jung Seow

Inventor： Wesley Kenneth Cobb ,  Ming-Jung Seow

IPC: G03B1/48 ,  G06K9/00

CPC classification number: G06K9/00771 ,  G06K9/00986

Abstract: Techniques are described for analyzing a stream of video frames to identify temporal anomalies. A video surveillance system configured to identify when agents depicted in the video stream engage in anomalous behavior, relative to the time-of-day (TOD) or day-of-week (DOW) at which the behavior occurs. A machine-learning engine may establish the normalcy of a scene by observing the scene over a specified period of time. Once the observations of the scene have matured, the actions of agents in the scene may be evaluated and classified as normal or abnormal temporal behavior, relative to the past observations.

Abstract translation: 描述了用于分析视频帧流以识别时间异常的技术。 视频监视系统被配置为识别视频流中描绘的代理何时涉及相对于行为发生的时间（TOD）或星期几（DOW）的异常行为。 机器学习引擎可以通过在指定的时间段内观察场景来建立场景的正常状态。 一旦场景的观察结果已经成熟，相对于过去的观察，场景中的代理人的动作可以被评估并且被分类为正常或异常的时间行为。