公开(公告)号：US20060053342A1

公开(公告)日：2006-03-09

申请号：US10938244

申请日：2004-09-09

申请人： Michael Bazakos ,  Yunqian Ma ,  Vassilios Morellas

发明人： Michael Bazakos ,  Yunqian Ma ,  Vassilios Morellas

IPC分类号： G06F11/00

CPC分类号： G08B13/19606 ,  G06K9/00335 ,  G06K9/00771 ,  G08B13/19641 ,  G08B13/19673 ,  G08B13/19682 ,  G08B13/19693 ,  G08B21/0423 ,  G08B21/0476

摘要： Methods and systems for the unsupervised learning of events contained within a video sequence, including apparatus and interfaces for implementing such systems and methods, are disclosed. An illustrative method in accordance with an exemplary embodiment of the present invention may include the steps of providing a behavioral analysis engine, initiating a training phase mode within the behavioral analysis engine and obtaining a feature vector including one or more parameters relating to an object located within an image sequence, and then analyzing the feature vector to determine a number of possible event candidates. The behavioral analysis engine can be configured to prompt the user to confirm whether an event candidate is a new event, an existing event, or an outlier. Once trained, a testing/operational phase mode of the behavioral analysis engine can be further implemented to detect the occurrence of one or more learned events, if desired.

公开(公告)号：US20060285723A1

公开(公告)日：2006-12-21

申请号：US11154839

申请日：2005-06-16

申请人： Vassilios Morellas ,  Michael Bazakos ,  Yunqian Ma ,  Andrew Johnson

发明人： Vassilios Morellas ,  Michael Bazakos ,  Yunqian Ma ,  Andrew Johnson

IPC分类号： G06K9/00 ,  H04N7/18

CPC分类号： G06K9/32 ,  G06K9/00369 ,  G06K9/00771 ,  G06T7/246 ,  G06T7/254 ,  G06T7/292

摘要： A system for tracking objects across an area having a network of cameras with overlapping and non-overlapping fields of view. The system may use a combination of color, shape, texture and/or multi-resolution histograms for object representation or target modeling for the tacking of an object from one camera to another. The system may include user and output interfacing.

摘要翻译： 一种用于在具有重叠和非重叠视场的摄像机网络的区域上跟踪对象的系统。 系统可以使用颜色，形状，纹理和/或多分辨率直方图的组合来进行对象表示或目标建模，用于将对象从一个摄像机固定到另一个摄像机。 该系统可以包括用户和输出接口。

公开(公告)号：US20060102843A1

公开(公告)日：2006-05-18

申请号：US10987806

申请日：2004-11-12

申请人： Michael Bazakos ,  Vassilios Morellas ,  Yunqian Ma

发明人： Michael Bazakos ,  Vassilios Morellas ,  Yunqian Ma

IPC分类号： G01J5/02

CPC分类号： G06K9/00255 ,  G01J3/36

摘要： A face detection and recognition system having several arrays imaging a scene in the infrared and visible spectrums. The system may use weighted subtracting and thresholding to distinguish human skin in a sensed image. A feature selector may locate a face in the image. The image may be cropped with a frame or border incorporating essentially only the face. The border may be superimposed on images from an infrared imaging array and the visible imaging array. Sub-images containing the face may be extracted from within the border on the infrared and visible images, respectively, and compared with a database of face information to attain recognition of the face. Confidence levels of recognition for infrared and visible imaged faces may be established. A resultant confidence level of recognition may be determined from these confidence levels. Infrared lighting may be used as needed to illuminate the scene.

公开(公告)号：US20060082439A1

公开(公告)日：2006-04-20

申请号：US11290524

申请日：2005-12-01

申请人： Michael Bazakos ,  David Meyers ,  Vassilios Morellas

发明人： Michael Bazakos ,  David Meyers ,  Vassilios Morellas

IPC分类号： G05B19/00 ,  G06K9/00

CPC分类号： G06K9/00228 ,  G06K9/6289 ,  G07B15/06 ,  G07C9/00087

摘要： A system for providing stand-off biometric verification of a driver of a vehicle while the vehicle is moving and/or a person on foot at a control gate, including an RFID vehicle tag reader, an RFID personal smart card reader and a facial detection and recognition (verification) system. The driver carries a RFID personal smart card that stores personal information of the driver and a face template of the driver. The vehicle carries a RFID vehicle tag that stores information regarding the vehicle. When the vehicle approaches the control gate, the RFID vehicle tag reader reads data from the RFID vehicle tag and the RFID personal tag reader reads data from the RFID personal smart card. The facial detection and verification system scans and reads a facial image for the driver. All the data and facial images detected by the readers are sent to a local computer at the control gate for further processing (final face verification). The local computer at the control gate decodes and retrieves the face template from the data read from the RFID personal smart card.

摘要翻译： 一种用于在车辆移动时提供车辆驾驶员的离线生物特征验证和/或在控制门上的人的行动的系统，包括RFID车辆标签读取器，RFID个人智能卡读取器和面部检测， 识别（验证）系统。 驾驶员携带RFID个人智能卡，其存储驾驶员的个人信息和驾驶员的面部模板。 车辆载有存储关于车辆的信息的RFID车辆标签。 当车辆接近控制门时，RFID车辆标签读取器从RFID车辆标签读取数据，并且RFID个人标签读取器从RFID个人智能卡读取数据。 面部检测和验证系统扫描并读取驾驶员的面部图像。 读取器检测到的所有数据和面部图像都将发送到控制门上的本地计算机进行进一步处理（最终面部验证）。 控制门上的本地计算机从RFID个人智能卡读取的数据解码并检索面部模板。

公开(公告)号：US20070092245A1

公开(公告)日：2007-04-26

申请号：US11163497

申请日：2005-10-20

申请人： Michael Bazakos ,  Vassilios Morellas

发明人： Michael Bazakos ,  Vassilios Morellas

IPC分类号： G03B17/00

CPC分类号： G06K9/00255

摘要： Facial detection and tracking systems and methods within a wide field of view are disclosed. A facial detection and tracking system in accordance with an illustrative embodiment of the present invention can include a wide field of view camera for detecting and tracking one or more objects within a wider field of view, and at least one narrower field of view camera for obtaining a higher-resolution image of each object located within a subset space of the wider field of view. The wide field of view camera can be operatively coupled to a computer or other such device that determines the subset space location of the individual within the wider field of view, and then tasks one or more of the narrower field of view cameras covering the subset space location to obtain a high-resolution image of the object.

摘要翻译： 公开了广泛的视野内的面部检测和跟踪系统和方法。 根据本发明的说明性实施例的面部检测和跟踪系统可以包括用于检测和跟踪更宽视场内的一个或多个对象的宽视场相机，以及用于获得的至少一个较窄的视野相机 位于更宽视场的子集空间内的每个对象的更高分辨率图像。 宽视场摄像机可以可操作地耦合到计算机或其他这样的设备，其确定个体在较宽视野范围内的子集空间位置，然后将覆盖子集空间的较窄视野摄像机中的一个或多个任务 位置以获得对象的高分辨率图像。

公开(公告)号：US20060116555A1

公开(公告)日：2006-06-01

申请号：US10991595

申请日：2004-11-18

申请人： Ioannis Pavlidis ,  Michael Bazakos ,  Vassilios Morellas

发明人： Ioannis Pavlidis ,  Michael Bazakos ,  Vassilios Morellas

IPC分类号： A61B5/00 ,  G08B23/00

CPC分类号： A61B5/01 ,  A61B5/015 ,  A61B5/16 ,  A61B5/164 ,  A61B5/6888

摘要： Thermal infrared image data of at least a region of a face of a person in an enclosure is provided. The enclosure, for example, may include a first enclosed volume and a second enclosed volume physically separated from the first enclosed volume. The first enclosed volume may include an entrance door sized to allow a person to enter the first enclosed volume. The enclosure provides a controlled environment for performing measurements (e.g., capturing thermal infrared image data) for use in determining a physiological state of a person (e.g., anxiety, deception, etc.).

摘要翻译： 提供至少在外壳中的人的脸部区域的热红外图像数据。 例如，外壳可以包括与第一封闭容积物理分离的第一封闭容积和第二封闭容积。 第一封闭容积可以包括大小允许人进入第一封闭容积的入口门。 外壳提供用于执行测量（例如，捕获热红外图像数据）的受控环境，以用于确定人的生理状态（例如，焦虑，欺骗等）。

公开(公告)号：US20060104488A1

公开(公告)日：2006-05-18

申请号：US10987368

申请日：2004-11-12

申请人： Michael Bazakos ,  Vassilios Morellas ,  Andrew Johnson ,  Yungian Ma

发明人： Michael Bazakos ,  Vassilios Morellas ,  Andrew Johnson ,  Yungian Ma

IPC分类号： G06K9/00 ,  G06K9/46

CPC分类号： H04N5/23219 ,  G06K9/00255

摘要： A face detection and recognition system having several arrays imaging a scene at different bands of the infrared spectrum. The system may use weighted subtracting and thresholding to distinguish human skin in a sensed image. A feature selector may locate a face in the image. The face may be framed or the image cropped with a frame or border to incorporate essentially only the face. The border may be superimposed on an image direct from an imaging array. A sub-image containing the face may be extracted from within the border and compared with a database of face information to attain recognition of the face. A level of recognition of the face may be established. Infrared lighting may be used as needed to illuminate the scene.

摘要翻译： 具有若干阵列的人脸检测和识别系统对红外光谱的不同频带的场景进行成像。 系统可以使用加权减法和阈值来区分感测图像中的人皮肤。 特征选择器可以在图像中定位一个面。 脸部可能被框起来，或者用框架或边框裁剪的图像基本上只包括脸部。 边界可以直接从成像阵列叠加在图像上。 可以从边框内提取包含脸部的子图像，并与面部信息的数据库进行比较以获得脸部的识别。 可以建立对面部的认可程度。 可以根据需要使用红外线照明来照亮场景。

公开(公告)号：US20070121999A1

公开(公告)日：2007-05-31

申请号：US11287627

申请日：2005-11-28

申请人： Yunqian Ma ,  Michael Bazakos

发明人： Yunqian Ma ,  Michael Bazakos

IPC分类号： G06K9/00

CPC分类号： G06K9/00771 ,  G06K9/00342 ,  G06T7/254

摘要： A system and method detects the intent and/or motivation of two or more persons or other animate objects in a video scene. In one embodiment, the system forms a blob of the two or more persons, draws a bounding box around said blob, calculates an entropy value for said blob, and compares that entropy value to a threshold to determine if the two or more persons are involved in a fight or other altercation.

摘要翻译： 系统和方法检测视频场景中两个或多个人或其他动画对象的意图和/或动机。 在一个实施例中，系统形成两个或更多个人的斑块，在所述斑点周围绘制边界框，计算所述斑点的熵值，并将该熵值与阈值进行比较，以确定是否涉及两个或多个人 在一场战斗或其他的争吵中。

公开(公告)号：US20070177792A1

公开(公告)日：2007-08-02

申请号：US11343658

申请日：2006-01-31

申请人： Yunqian Ma ,  Michael Bazakos

发明人： Yunqian Ma ,  Michael Bazakos

IPC分类号： G06K9/62

CPC分类号： G06K9/00348

摘要： In an embodiment, one or more sequences of learning video data is provided. The learning video sequences include an action. One or more features of the action are extracted from the one or more sequences of learning video data. Thereafter, a reception of a sequence of operational video data is enabled, and an extraction of the one or more features of the action from the sequence of operational video data is enabled. A comparison is then enabled between the extracted one or more features of the action from the one or more sequences of learning video data and the one or more features of the action from the sequence of operational video data. In an embodiment, this comparison allows the determination of whether the action in present in the operational video data.

摘要翻译： 在一个实施例中，提供学习视频数据的一个或多个序列。 学习视频序列包括动作。 从学习视频数据的一个或多个序列中提取动作的一个或多个特征。 此后，启用操作视频数据序列的接收，并且能够从操作视频数据序列中提取动作的一个或多个特征。 然后，从所述学习视频数据的一个或多个序列以及来自所述操作视频数据序列的所述动作的所述一个或多个特征，提取所述动作的一个或多个特征之间的比较。 在一个实施例中，该比较允许确定当前在操作视频数据中的动作。

公开(公告)号：US20070122040A1

公开(公告)日：2007-05-31

申请号：US11289886

申请日：2005-11-30

申请人： Kwong Au ,  Michael Bazakos ,  Yunqian Ma

发明人： Kwong Au ,  Michael Bazakos ,  Yunqian Ma

IPC分类号： G06K9/62 ,  G06K9/46

CPC分类号： G06K9/00771 ,  G06K9/46

摘要： An image is processed by a sensed-feature-based classifier to generate a list of objects assigned to classes. The most prominent objects (those objects whose classification is most likely reliable) are selected for range estimation and interpolation. Based on the range estimation and interpolation, the sensed features are converted to physical features for each object. Next, that subset of objects is then run through a physical-feature-based classifier that re-classifies the objects. Next, the objects and their range estimates are re-run through the processes of range estimation and interpolation, sensed-feature-to-physical-feature conversion, and physical-feature-based classification iteratively to continuously increase the reliability of the classification as well as the range estimation. The iterations are halted when the reliability reaches a predetermined confidence threshold. In a preferred embodiment, a next subset of objects having the next highest prominence in the same image is selected and the entire iterative process is repeated. This set of iterations will include evaluation of both of the first and second subsets of objects. The process can be repeated until all objects have been classified.

摘要翻译： 图像由基于感测特征的分类器处理以生成分配给类的对象的列表。 选择最突出的对象（那些分类最可靠的对象）用于范围估计和插值。 基于范围估计和内插，感测到的特征被转换为每个对象的物理特征。 接下来，该对象的子集然后通过基于物理特征的分类器来运行，该分类器重新分类对象。 接下来，通过范围估计和插值，感测特征到物理特征转换和基于物理特征的分类的过程重新运行对象及其范围估计，以不断提高分类的可靠性 作为范围估计。 当可靠性达到预定的置信阈值时，迭代停止。 在优选实施例中，选择具有相同图像中的下一个最高突出的对象的下一个子集，并重复整个迭代过程。 这组迭代将包括评估对象的第一和第二子集。 可以重复该过程，直到所有对象都被分类为止。