公开(公告)号：US07847820B2

公开(公告)日：2010-12-07

申请号：US11082026

申请日：2005-03-15

申请人： Robert P. Vallone ,  Stephen G. Russell ,  Thomas W. Kirkman ,  Marcus S. Marinelli ,  J. Andrew Freeman

发明人： Robert P. Vallone ,  Stephen G. Russell ,  Thomas W. Kirkman ,  Marcus S. Marinelli ,  J. Andrew Freeman

IPC分类号： H04N7/12

CPC分类号： G06K9/00288 ,  G06K9/00268 ,  G06K9/00711 ,  G06K9/00771 ,  H04N5/77 ,  H04N5/781 ,  H04N7/181 ,  H04N21/44008

摘要： A method that determines whether a detected event is a significant event requiring action in a video surveillance system. Determined event attributes and object attributes are analyzed to determine if the potential event should trigger an action by the surveillance system. If the potential event should trigger an action, at least one action is triggered. Actions may include relevant event attribute and object attribute information.Potential event may include events detected by a sensor, or external events communicated by an external system to the surveillance system. Event attributes may include location and type of the potential event. Object attributes may include an identification of an object, and attributes associated with the identified object. If an object cannot be positively identified, object attributes may include potential object identifications or determined group associations of the object.

摘要翻译： 确定检测到的事件是否是需要在视频监控系统中动作的重要事件的方法。 分析确定的事件属性和对象属性，以确定潜在事件是否应触发监视系统的动作。 如果潜在的事件触发一个动作，则至少会触发一个动作。 动作可以包括相关的事件属性和对象属性信息。 潜在事件可能包括由传感器检测到的事件，或者由外部系统传送到监视系统的外部事件。 事件属性可能包括潜在事件的位置和类型。 对象属性可以包括对象的标识，以及与识别的对象相关联的属性。 如果对象无法被正确识别，对象属性可能包括对象的潜在对象标识或确定的组关联。

公开(公告)号：US07663661B2

公开(公告)日：2010-02-16

申请号：US10964977

申请日：2004-10-13

申请人： Robert P. Vallone ,  J. Andrew Freeman ,  Stephen G. Russell ,  Thomas W. Kirkman ,  Stephen D. Fleischer ,  Gordon T. Haupt

发明人： Robert P. Vallone ,  J. Andrew Freeman ,  Stephen G. Russell ,  Thomas W. Kirkman ,  Stephen D. Fleischer ,  Gordon T. Haupt

IPC分类号： H04N7/18

CPC分类号： H04N7/181 ,  G06K9/00711 ,  G06K9/00986

摘要： A pipeline architecture for analyzing multiple streams of video is embodied, in part, in a layer of application program interfaces (APIs) to each stage of processing. Buffer queuing is used between some stages, which helps moderate the load on the CPU(s). Through the layer of APIs, innumerable video analysis applications can access and analyze video data flowing through the pipeline, and can annotate portions of the video data (e.g., frames and groups of frames), based on the analyses performed, with information that describes the frame or group. These annotated frames and groups flow through the pipeline to subsequent stages of processing, at which increasingly complex analyses can be performed. At each stage, portions of the video data that are of little or no interest are removed from the video data. Ultimately, “events” are constructed and stored in a database, from which cross-event and historical analyses may be performed and associations with, and among, events may be made.

摘要翻译： 用于分析多个视频流的流水线架构部分地体现在每个处理阶段的应用程序接口（API）层中。 在一些阶段之间使用缓冲区排队，这有助于缓和CPU上的负载。 通过API层，无数视频分析应用程序可以访问和分析流经流水线的视频数据，并且可以基于所执行的分析来注释视频数据的一部分（例如，帧和帧组），其中描述 框架或组。 这些注释的帧和组流经管线到处理的后续阶段，在该阶段可以执行越来越复杂的分析。 在每个阶段，从视频数据中删除少量或不感兴趣的视频数据的部分。 最终，“事件”被构建并存储在数据库中，可以从该数据库中进行交叉事件和历史分析，并且可以进行与事件的关联以及事件之间的关联。