公开(公告)号：US07308133B2

公开(公告)日：2007-12-11

申请号：US09966408

申请日：2001-09-28

申请人： Srinivas Gutta ,  Miroslav Trajkovic ,  Vasanth Philomin

发明人： Srinivas Gutta ,  Miroslav Trajkovic ,  Vasanth Philomin

IPC分类号： G06K9/62 ,  G06K9/68

CPC分类号： G06K9/00288

摘要： A system and method for classifying facial image data, the method comprising the steps of: training a classifier device for recognizing one or more facial images and obtaining corresponding learned models the facial images used for training; inputting a vector including data representing a portion of an unknown facial image to be recognized into the classifier; classifying the portion of the unknown facial image according to a classification method; repeating inputting and classifying steps using a different portion of the unknown facial image at each iteration; and, identifying a single class result from the different portions input to the classifier.

摘要翻译： 一种用于分类面部图像数据的系统和方法，所述方法包括以下步骤：训练用于识别一个或多个面部图像的分类器装置，并获得用于训练的面部图像的相应学习模型; 将包含表示要识别的未知脸部图像的一部分的数据的向量输入到分类器中; 根据分类方法对未知面部图像的部分进行分类; 在每次迭代时，使用未知面部图像的不同部分重复输入和分类步骤; 并且从输入到分类器的不同部分识别单个类结果。

公开(公告)号：US20070228174A1

公开(公告)日：2007-10-04

申请号：US11395569

申请日：2006-03-31

申请人： Igor Vinogradov ,  Miroslav Trajkovic ,  Edward Barkan

发明人： Igor Vinogradov ,  Miroslav Trajkovic ,  Edward Barkan

IPC分类号： G06K7/10

CPC分类号： G06K7/14

摘要： An imaging-based bar code reader that includes an item guide to guide movement of an item including a target bar code such that target bar code passes through a field of view of the reader in a straight line. The reader further includes an imaging and decoding system to: 1) capture a series of images which include at least a part of the target bar code as the bar code is moved through the field of view of the reader; 2) sequentially analyze the series of captured images, for each captured image, identifying areas of the captured image representative of an image of the target bar code and decode decodable portions of the imaged target bar code; and 3) combining the decoded portions of the imaged target bar code using a sequence stitching method to obtain a full decode of the target bar code.

摘要翻译： 一种基于成像的条形码读取器，其包括用于引导包括目标条形码的项目的移动的项目指南，使得目标条形码以直线通过读取器的视野。 读取器还包括成像和解码系统，用于：1）当条形码移动通过读取器的视野时，捕获包括目标条形码的至少一部分的一系列图像; 2）对于每个捕获的图像，顺序地分析捕获的图像的系列，识别表示目标条形码的图像的捕获图像的区域，并对成像的目标条形码的可解码部分进行解码; 以及3）使用序列拼接方法组合成像的目标条形码的解码部分，以获得目标条形码的完全解码。

公开(公告)号：US20070201757A1

公开(公告)日：2007-08-30

申请号：US11361477

申请日：2006-02-24

申请人： Dariusz Madej ,  Miroslav Trajkovic

发明人： Dariusz Madej ,  Miroslav Trajkovic

IPC分类号： G06K9/40

CPC分类号： G06K9/4638 ,  G06K9/00456 ,  G06K2209/01 ,  G06Q20/208

摘要： Described is a system and method for optical character recognition in an image. The method comprising identifying a connected component in an image, computing at least one parameter for the connected component and selecting a portion of the image corresponding to the connected component for optical character recognition when the at least one parameter is within a predetermined threshold range.

摘要翻译： 描述了一种用于图像中的光学字符识别的系统和方法。 该方法包括识别图像中的连接分量，当至少一个参数在预定阈值范围内时，计算连接分量的至少一个参数并选择与所连接分量对应的图像的一部分用于光学字符识别。

公开(公告)号：US07202791B2

公开(公告)日：2007-04-10

申请号：US10184512

申请日：2002-06-28

申请人： Miroslav Trajkovic

发明人： Miroslav Trajkovic

IPC分类号： G08B23/00

CPC分类号： G08B13/19615 ,  G06K9/00335 ,  G06K9/00771 ,  G06K9/6218 ,  G06T7/20 ,  G08B13/19602 ,  G08B13/19613 ,  G08B13/19671 ,  G08B13/19673 ,  G08B21/0423 ,  G08B21/0476 ,  H04N7/181

摘要： A method and apparatus are disclosed for modeling patterns of behavior of humans or other animate objects and detecting a violation of a repetitive pattern of behavior. The behavior of one or more persons is observed over time and features of the behavior are recorded in a multi-dimensional space. Over time, the multi-dimensional data provides an indication of patterns of human behavior. Activities that are repetitive in terms of time, location and activity, such as sleeping and eating, would appear as a Gaussian distribution or cluster in the multi-dimensional data. Probability distribution functions can be analyzed using known Gaussian or clustering techniques to identify repetitive patterns of behavior and characteristics thereof, such as a mean and variance. Deviations from repetitive patterns of behavior can be detected and an alarm can be triggered, if appropriate.

摘要翻译： 公开了用于建模人类或其他动画对象的行为模式并检测违反重复行为模式的方法和装置。 随着时间的推移观察一个或多个人的行为，并且将行为的特征记录在多维空间中。 随着时间的推移，多维数据提供了人类行为模式的指示。 在时间，位置和活动（如睡眠和饮食）方面重复的活动将在多维数据中显示为高斯分布或聚类。 可以使用已知的高斯或聚类技术来分析概率分布函数，以识别其行为及其特征的重复模式，例如均值和方差。 如果适当，可以检测到重复行为模式的偏差，并且可以触发报警。

公开(公告)号：US07201321B2

公开(公告)日：2007-04-10

申请号：US10928470

申请日：2004-08-27

申请人： Duanfeng He ,  Miroslav Trajkovic

发明人： Duanfeng He ,  Miroslav Trajkovic

IPC分类号： G06K7/10 ,  G06K9/24 ,  G08C21/00

CPC分类号： G06K7/10861 ,  G06K7/10722 ,  G06K7/10811 ,  G06K2207/1011

摘要： Performance of an imaging reader for electro-optically reading direct part markings on workpieces is enhanced by ensuring that such markings are read in the vicinity of an ideal, focused, target plane, and by enhancing the contrast of such markings. Calibration and self-calibration of the reader improve performance.

摘要翻译： 通过确保在理想的，聚焦的目标平面附近读取这些标记，并且通过增强这种标记的对比度，增强了用于电工读取工件上的直接部件标记的成像读取器的性能。 阅读器的校准和自校准可提高性能。

公开(公告)号：US07183944B2

公开(公告)日：2007-02-27

申请号：US09879698

申请日：2001-06-12

申请人： Srinivas Gutta ,  Miroslav Trajkovic ,  Antonio Colmenarez, Jr.

发明人： Srinivas Gutta ,  Miroslav Trajkovic ,  Antonio Colmenarez, Jr.

IPC分类号： G08G1/07

CPC分类号： G08G1/0965 ,  B60R2300/101 ,  B60R2300/105 ,  B60R2300/301 ,  B60R2300/802 ,  B60R2300/8066

摘要： An apparatus for detecting an emergency/law enforcement vehicle from a secondary vehicle. The apparatus includes: at least one camera mounted on the secondary vehicle; a display surface mounted inside an interior of the secondary vehicle for displaying video image data from the at least one camera; at least one of a pan, tilt, and zoom motor operatively connected to the at least one camera for providing an enhanced view of an emergency/law enforcement vehicle displayed on the display surface; and a controller for controlling the at least one pan, tilt, and zoom motors to provide the enhanced view. The apparatus alternatively also has the capability to detect, track and/or classify an emergency/law enforcement vehicle in the video image data.

摘要翻译： 一种用于从二次车辆检测紧急/执法车辆的装置。 所述装置包括：安装在所述辅助车辆上的至少一个照相机; 安装在所述辅助车辆的内部内的显示表面，用于显示来自所述至少一个照相机的视频图像数据; 可操作地连接到所述至少一个相机的摇摄，倾斜和变焦马达中的至少一个，用于提供显示在所述显示表面上的紧急/执法车辆的增强视图; 以及用于控制所述至少一个摇摄，倾斜和变焦电机以提供增强视图的控制器。 该装置还具有在视频图像数据中检测，跟踪和/或分类紧急/执法车辆的能力。

公开(公告)号：US07173650B2

公开(公告)日：2007-02-06

申请号：US09819971

申请日：2001-03-28

申请人： Eric Cohen-Solal ,  Miroslav Trajkovic ,  Damian M Lyons

发明人： Eric Cohen-Solal ,  Miroslav Trajkovic ,  Damian M Lyons

IPC分类号： H04N9/47 ,  H04N5/225

CPC分类号： G01S3/7865 ,  G01S3/785

摘要： A method for reacquiring a target in an automated video tracking system is provided. The method includes the steps of: selecting a desired target to be tracked; switching the automated video tracking system to an automatic mode to initiate a tracking sequence to automatically track the selected desired target; switching the automated video tracking system from an automatic mode to a manual mode if the automated video tracking system encounters a period of difficulty in tracking the desired target; reacquiring the desired target in manual mode; and switching the automated video tracking system to the automatic mode for automatic tracking of the reacquired desired target without initiating a new tracking sequence. An apparatus and automated video tracking system for carrying out the methods of the present invention are also provided.

摘要翻译： 提供了一种在自动视频跟踪系统中重新获取目标的方法。 该方法包括以下步骤：选择要跟踪的期望目标; 将自动视频跟踪系统切换到自动模式以启动跟踪序列以自动跟踪所选择的期望目标; 如果自动视频跟踪系统在跟踪期望的目标时遇到困难的时段，则将自动视频跟踪系统从自动模式切换到手动模式; 在手动模式下重新获得所需的目标; 并将自动视频跟踪系统切换到自动模式，以自动跟踪重新获得的所需目标，而不启动新的跟踪序列。 还提供了一种用于实施本发明的方法的设备和自动化视频跟踪系统。

公开(公告)号：US20070028266A1

公开(公告)日：2007-02-01

申请号：US10547091

申请日：2003-11-24

申请人： Miroslav Trajkovic ,  Srinivas Gutta ,  Vassanth Philomin

发明人： Miroslav Trajkovic ,  Srinivas Gutta ,  Vassanth Philomin

IPC分类号： H04N7/10 ,  G06F3/00 ,  G06F13/00 ,  H04N7/025 ,  H04N5/445

CPC分类号： H04N21/4661 ,  G06Q30/02 ,  H04N7/163 ,  H04N21/252 ,  H04N21/4147 ,  H04N21/44222 ,  H04N21/4668 ,  H04N21/6582

摘要： A method for recommending a video content to a viewer. The method including the steps of: determining a user profile of the viewer, the user profile indicating the viewing preferences of the viewer, providing a plurality of user profiles; comparing the user profile of the viewer to each of the plurality of user profiles to determine if each of the plurality of user profiles contains at least one common characteristic with the user profile of the viewer; and determining a recommendation for the video content based on the plurality of user profiles, wherein user profiles having the at least one common characteristic are assigned a greater recommendation weight than user profiles not having the at least one common characteristic.

摘要翻译： 一种用于向观看者推荐视频内容的方法。 该方法包括以下步骤：确定观众的用户简档，指示观众的观看偏好的用户简档，提供多个用户简档; 将观众的用户简档与多个用户简档中的每一个比较，以确定多个用户简档中的每一个是否包含与观众的用户简档的至少一个共同特征; 以及基于所述多个用户简档来确定对所述视频内容的推荐，其中具有所述至少一个共同特征的用户简档被分配比不具有所述至少一个共同特征的用户简档更大的推荐权重。

公开(公告)号：US07136479B2

公开(公告)日：2006-11-14

申请号：US10175408

申请日：2002-06-19

申请人： Srinivas Gutta ,  Miroslav Trajkovic ,  Vasanth Philomin

发明人： Srinivas Gutta ,  Miroslav Trajkovic ,  Vasanth Philomin

IPC分类号： H04M5/00 ,  H04M3/00 ,  H04M3/42 ,  H04L12/66

CPC分类号： H04M1/82 ,  H04M1/006 ,  H04M1/65 ,  H04M1/80 ,  H04M3/428

摘要： A telephone user who is at a first telephone station and is placed on hold at a second station is prevented from listening to an objectionable audio signal while a call is in process between the user and the second telephone station. The objectionable audio signal is detected while the call is in process and the user is prevented from hearing the objectionable audio signal while the objectionable audio signal is being detected. In response to detection of the end of the objectionable audio signal, the user is coupled to the second telephone station.

公开(公告)号：US06968294B2

公开(公告)日：2005-11-22

申请号：US09808848

申请日：2001-03-15

申请人： Srinivas Gutta ,  Eric Cohen-Solal ,  Miroslav Trajkovic

发明人： Srinivas Gutta ,  Eric Cohen-Solal ,  Miroslav Trajkovic

IPC分类号： A61G12/00 ,  A61B5/00 ,  A61B5/113 ,  A61B5/16 ,  G06T1/00 ,  G08B21/04 ,  G08B25/04 ,  H04N7/18 ,  G08B21/00 ,  G08B23/00

CPC分类号： G08B21/0423 ,  A61B5/0013 ,  A61B5/113 ,  A61B5/167 ,  A61B5/7264 ,  A61B5/7267 ,  A61B2503/06 ,  G06F19/00 ,  G08B21/0453 ,  G08B21/0476

摘要： A monitoring system for an infant, child, invalid, or other person requiring care uses computer vision and hearing, and inputs of other modalities, to analyze the status of a caretaker and/or cared-for person and its environment. The conditions are classified as normal or alarm conditions and an informative alarm signal is generated which may include records of the vision audio and other inputs. The system also has the ability to solicit responses from the occupants to stimulate a classifiable input to reduce ambiguity in its state signal.

摘要翻译： 婴儿，儿童，无效或其他需要照顾的人的监测系统使用计算机视觉和听力，以及其他方式的输入，分析看守者和/或照顾人及其环境的状态。 条件被分类为正常或报警条件，并且产生可能包括视觉音频和其他输入的记录的信息性报警信号。 该系统还具有征求居民的反应以刺激可分类输入以减少其状态信号的模糊性的能力。