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：US20060174260A1

公开(公告)日：2006-08-03

申请号：US10549882

申请日：2004-03-02

申请人： Srinivas Gutta

发明人： Srinivas Gutta

IPC分类号： H04N7/16 ,  H04N7/10 ,  G06F3/00 ,  G06F13/00 ,  H04N5/445 ,  H04N7/025 ,  H04H9/00

CPC分类号： H04H60/47 ,  H04H60/46 ,  H04H60/65 ,  H04N5/44543 ,  H04N7/163 ,  H04N21/4532 ,  H04N21/454 ,  H04N21/4668 ,  H04N21/4755 ,  H04N21/482 ,  H04N21/84

摘要： A method for generating recommendations, the method including: prompting a user for feedback on at least one preference for generating a recommendation, the at least one preference having two or more categories associated therewith; displaying at least one visual cue corresponding to each of the two or more categories; selecting one of the two or more categories based at least in part on the corresponding at least one visual cue; and generating a recommendation based at least in part on the selecting. Preferably, the generating generates a recommendation for video content, such as a television program and the at least one preference is the genre of the television program, such as action, drama, comedy-action, suspense-action, comedy, documentary, or romance.

摘要翻译： 一种用于产生建议的方法，所述方法包括：提示用户对至少一个偏好以产生推荐的反馈，所述至少一个偏好具有与其相关联的两个或多个类别; 显示对应于两个或更多个类别中的每一个的至少一个视觉提示; 至少部分地基于对应的至少一个视觉提示来选择所述两个或多个类别中的一个; 以及至少部分地基于所述选择生成推荐。 优选地，生成产生诸如电视节目的视频内容的建议，并且至少一个偏好是电视节目的类型，诸如动作，戏剧，喜剧动作，悬念，喜剧，纪录片或浪漫 。

公开(公告)号：US07043075B2

公开(公告)日：2006-05-09

申请号：US10183821

申请日：2002-06-27

申请人： Srinivas Gutta

发明人： Srinivas Gutta

IPC分类号： G06K9/62

CPC分类号： G06K9/6273 ,  G06K9/00771 ,  G06K9/6282 ,  G06T7/20 ,  G08B13/19602 ,  G08B13/19613 ,  G08B21/0423 ,  G08B21/0476

摘要： A method and apparatus are disclosed for classifying objects using a hierarchical object classification scheme. The hierarchical object classification scheme provides candidate classes with an increasing degree of specificity as the hierarchy is traversed from the root node to the leaf nodes. Each node in the hierarchy has an associated classifier, such as a Radial Basis Function classifier, that determines a probability that an object is a member of the class associated with the node. The nodes of the hierarchical tree are individually trained by any learning technique, such as the exemplary Radial Basis Function Network, that uses appearance-based information of the objects under consideration to classify objects. A disclosed recognition scheme uses a decision criterion based upon recognition error to classify objects.

公开(公告)号：US06965394B2

公开(公告)日：2005-11-15

申请号：US09822625

申请日：2001-03-30

申请人： Srinivas Gutta ,  Miroslav Trajkovic ,  Antonio Colmenarez

发明人： Srinivas Gutta ,  Miroslav Trajkovic ,  Antonio Colmenarez

IPC分类号： H04N5/232 ,  H04N7/18 ,  H04N7/14

CPC分类号： H04N5/232 ,  H04N5/23293 ,  H04N7/18

摘要： A camera system comprising a camera, a monitor, an image detector, a touch screen, and a remote control. The monitor displays a field of view of a lens of the camera. The image detector provides a viewer image to the remote control whereby the remote control can determine a desired image within the field of view that the viewer is gazing upon. The touch screen enables a viewer of the monitor to point to the desired image of the field of view and provides signal(s) indicative of the pointing. The remote control is operable to activate various drives to pan and/or tilt the camera, or to zoom and/or focus the lens to the desired image and to follow any movement of the image within the field of view.

摘要翻译： 一种照相机系统，包括照相机，监视器，图像检测器，触摸屏和遥控器。 显示器显示相机镜头的视野。 图像检测器向遥控器提供观看者图像，由此遥控器可以在观看者注视的视野内确定期望的图像。 触摸屏使得监视器的观看者能够指向视场的所需图像并且提供指示指向的信号。 遥控器可操作以激活各种驱动器来平移和/或倾斜相机，或者将镜头缩放和/或聚焦到期望的图像并且跟随视场内的图像的任何移动。

公开(公告)号：US06778705B2

公开(公告)日：2004-08-17

申请号：US09794443

申请日：2001-02-27

申请人： Srinivas Gutta ,  Vasanth Philomin

发明人： Srinivas Gutta ,  Vasanth Philomin

IPC分类号： G06K962

CPC分类号： G06K9/6273 ,  G06T7/00

摘要： A method for classification of objects in video image data. The method including the steps of: detecting moving objects in the image data; extracting two or more features from each detected moving object in the image data; classifying each moving object for each of the two or more features according to a classification method; and deriving a classification for each moving object based on the classification method for each of the two or more features. Also provided is an apparatus for classification of objects in video image data.

摘要翻译： 一种视频图像数据中对象分类的方法。 该方法包括以下步骤：检测图像数据中的移动物体; 从所述图像数据中的每个检测到的移动对象中提取两个或更多个特征; 根据分类方法对两个或多个特征中的每一个分类每个移动对象; 并且基于用于两个或更多个特征中的每一个的分类方法，为每个运动对象导出分类。 还提供了一种用于对视频图像数据中的对象进行分类的装置。

公开(公告)号：US06778226B1

公开(公告)日：2004-08-17

申请号：US09686795

申请日：2000-10-11

申请人： Larry J. Eshelman ,  Srinivas Gutta ,  John Milanski ,  Hugo J. Strubbe

发明人： Larry J. Eshelman ,  Srinivas Gutta ,  John Milanski ,  Hugo J. Strubbe

IPC分类号： H04N564

CPC分类号： H04N5/64 ,  H05B37/0227

摘要： The appearance of a cabinet for a device (e.g., a television) is dynamically controlled. One way of controlling the appearance of the cabinet is by providing a display panel on the cabinet. At least one input is obtained from an input device and processed by a controller. Based on these inputs, the controller sends signals to the display panel to change the appearance of the display panel. Lamps and heat-sensitive materials may be used to effectuate the desired change in appearance. The cabinet display features may be controlled to give the device the appearance of having a persona or of being an independent animate being. For example, lights in the cabinet could flash to suggest the device is laughing in response to the detection of a laugh track in a sitcom being displayed on the device. Patterns and colors can be generated to reflect moods according to the preferences of an interaction-design programmer.

摘要翻译： 用于设备（​​例如，电视机）的机柜的外观是动态控制的。 控制柜体外观的一种方式是在机柜上设置显示面板。 从输入设备获得至少一个输入并由控制器处理。 基于这些输入，控制器向显示面板发送信号以改变显示面板的外观。 可以使用灯和热敏材料来实现期望的外观变化。 可以控制橱柜显示功能，使设备具有人物或独立动画的外观。 例如，柜内的指示灯可能会闪烁，表示设备正在笑，以响应在设备上显示的情景喜剧中的笑声的检测。 可以根据交互设计程序员的喜好，生成模式和颜色以反映情绪。

公开(公告)号：US06766035B1

公开(公告)日：2004-07-20

申请号：US09564016

申请日：2000-05-03

申请人： Srinivas Gutta

发明人： Srinivas Gutta

IPC分类号： G06K900

CPC分类号： G06K9/0057 ,  G06K9/32 ,  H04N7/142 ,  H04N7/15 ,  H04N7/18

摘要： Methods and apparatus are disclosed for tracking an object of interest in a video processing system, using clustering techniques. An area is partitioned into approximate regions, referred to as clusters, each associated with an object of interest. Each cluster has associated average pan, tilt and zoom values. Audio or video information, or both, are used to identify the cluster associated with a speaker (or another object of interest). Once the cluster of interest is identified, the camera is focused on the cluster, using the recorded pan, tilt and zoom values, if available. An event accumulator initially accumulates audio (and optionally video) events for a specified time, to allow several speakers to speak. The accumulated audio events are then used by a cluster generator to generate clusters associated with the various objects of interest. After initialization of the clusters, the illustrative event accumulator gathers events at periodic intervals. The mean of the pan and tilt values (and zoom value, if available) occurring in each time interval are then used to compute the distance between the various clusters in the database by a similarity estimator, based on an empirically-set threshold. If the distance is greater than the established threshold, then a new cluster is formed, corresponding to a new speaker, and indexed into the database. Fuzzy clustering techniques allow the camera to be focused on more than one cluster at a given time, when the object of interest may be located in one or more clusters.

摘要翻译： 公开了使用聚类技术来跟踪视频处理系统中的感兴趣对象的方法和装置。 区域被划分为近似区域，被称为簇，每个区域与感兴趣对象相关联。 每个群集都具有关联的平移，倾斜和缩放值。 音频或视频信息或两者都用于识别与扬声器（或另一个感兴趣对象）相关联的群集。 一旦识别出感兴趣的群集，相机就会聚焦在群集上，使用记录的平移，倾斜和缩放值（如果可用）。 事件累加器最初在指定时间内累积音频（和可选的视频）事件，以允许多个扬声器发言。 然后，集群生成器使用累积的音频事件来生成与感兴趣的各种对象相关联的集群。 在集群初始化之后，说明性事件累加器以周期性间隔收集事件。 然后，使用每个时间间隔内出现的平移和倾斜值（和缩放值，如果可用）的平均值，基于经验设定的阈值，通过相似度估计器计算数据库中的各种群集之间的距离。 如果距离大于建立的阈值，则形成一个新的集群，对应一个新的发言者，并将其编入数据库。 当感兴趣对象可能位于一个或多个集群中时，模糊聚类技术允许相机在给定时间聚焦在多于一个集群上。

公开(公告)号：US06728679B1

公开(公告)日：2004-04-27

申请号：US09699578

申请日：2000-10-30

申请人： Hugo J. Strubbe ,  Larry J. Eshelman ,  Srinivas Gutta ,  John Milanski ,  Daniel Pelletier

发明人： Hugo J. Strubbe ,  Larry J. Eshelman ,  Srinivas Gutta ,  John Milanski ,  Daniel Pelletier

IPC分类号： G10L1522

CPC分类号： G06F3/011

摘要： An interaction simulator has the ability to dynamically update response templates and response data by retrieving current information from a data source. The interaction simulator may interact verbally or by other means such as gesture, typed text, or other means to generate a “dialogue. ” The interaction simulator, by dynamically updating its responses, is able to be more interesting and useful to users and also more personally relevant than prior art, so-called chatterbots. The device also reduces the required number of rules and library of response data that must be retained compared to prior art conversation simulators. The criteria used to create new response data can come from fixed specifications, for example, the current weather, or from the content of previous conversations (for example, the system creating a new template about a topic indicated by the user to be of interest to him/her).

摘要翻译： 交互模拟器能够通过从数据源检索当前信息来动态地更新响应模板和响应数据。 交互模拟器可以口头交流或通过其他手段（例如手势，打字文本或其他手段）进行交互以产生“对话”。通过动态更新其响应，交互模拟器能够对用户更有趣和更有用 与现有技术相关的所谓chatterbots。 该装置还减少了与现有技术的对话模拟器相比必须保留的所需数量的响应数据规则和库。 用于创建新的响应数据的标准可以来自固定的规范，例如当前的天气，或者来自前一个对话的内容（例如，系统创建一个关于用户指示的话题的新模板，以使用户感兴趣） 他她）。

公开(公告)号：US06604059B2

公开(公告)日：2003-08-05

申请号：US09902215

申请日：2001-07-10

申请人： Hugo J. Strubbe ,  Srinivas Gutta

发明人： Hugo J. Strubbe ,  Srinivas Gutta

IPC分类号： G06F1500

CPC分类号： G06Q10/109 ,  G06Q30/02

摘要： A method and system for recommending future events or appointments are disclosed. The inventive system stores a repeat rate provided by users in the system, then recommends future events or appointments based on what the user has rated and the past frequency of those events or appointments which the user has attended. This invention is based on the fact that people have a tendency to attend or observe similar events as in the past and will show such tendency in the future.

摘要翻译： 公开了推荐未来事件或约会的方法和系统。 本发明的系统存储用户在系统中提供的重复率，然后根据用户评级以及用户所参与的那些事件或约会的过去频率推荐未来事件或约会。 本发明是基于以下事实：人们倾向于参加或观察与过去类似的事件，并将在将来表现出这种倾向。

公开(公告)号：US06442474B1

公开(公告)日：2002-08-27

申请号：US09731539

申请日：2000-12-07

申请人： Miroslav Trajkovic ,  Srinivas Gutta

发明人： Miroslav Trajkovic ,  Srinivas Gutta

IPC分类号： G06G776

CPC分类号： G08G1/0175

摘要： A method and apparatus are disclosed for monitoring traffic using vision-based technologies to recognize events and violations. The disclosed traffic monitoring system includes one or more image capture devices focused on a roadway where vehicles travel. The captured images are processed by the traffic monitoring system to identify one or more predefined events or traffic violations. A number of rules can be utilized to define various traffic-related events, including traffic violations. Each rule contains one or more conditions, and, optionally, a corresponding action-item that should be performed when the rule is satisfied. Upon detection of a predefined traffic event, the corresponding action, if any, is performed by the traffic monitoring system.

摘要翻译： 公开了一种用于使用基于视觉的技术监视交通以识别事件和违规的方法和装置。 公开的交通监控系统包括一个或多个集中在车辆行驶的道路上的图像捕获设备。 捕获的图像由交通监控系统处理以识别一个或多个预定义的事件或交通违规。 可以使用许多规则来定义各种与交通有关的事件，包括交通违规。 每个规则包含一个或多个条件，以及可选地，当满足规则时应该执行的相应动作项。 在检测到预定义的交通事件时，交通监控系统执行相应的动作（如果有的话）。