公开(公告)号：US20150023602A1

公开(公告)日：2015-01-22

申请号：US14332371

申请日：2014-07-15

申请人： Kamil Wnuk ,  Bing Song ,  Matheen Siddiqui ,  David McKinnon ,  Jeremi Sudol ,  Patrick Soon-Shiong ,  Orang Dialameh

发明人： Kamil Wnuk ,  Bing Song ,  Matheen Siddiqui ,  David McKinnon ,  Jeremi Sudol ,  Patrick Soon-Shiong ,  Orang Dialameh

IPC分类号： G06K9/62 ,  G06F17/30 ,  G06K9/46

CPC分类号： G06K9/00671 ,  G06F17/30247 ,  G06F19/00 ,  G06F19/321 ,  G06K9/00718 ,  G06K9/6202 ,  G06T7/0014 ,  G06T11/60 ,  G06T2207/10016 ,  G06T2207/20004 ,  G16H30/40

摘要： Systems and methods of quickly recognizing or differentiating many objects are presented. Contemplated systems include an object model database storing recognition models associated with known modeled objects. The object identifiers can be indexed in the object model database based on recognition features derived from key frames of the modeled object. Such objects are recognized by a recognition engine at a later time. The recognition engine can construct a recognition strategy based on a current context where the recognition strategy includes rules for executing one or more recognition algorithms on a digital representation of a scene. The recognition engine can recognize an object from the object model database, and then attempt to identify key frame bundles that are contextually relevant, which can then be used to track the object or to query a content database for content information.

摘要翻译： 提出了快速识别或区分许多物体的系统和方法。 考虑的系统包括存储与已知建模对象相关联的识别模型的对象模型数据库。 可以基于从建模对象的关键帧导出的识别特征，在对象模型数据库中对对象标识符进行索引。 这样的对象在稍后的时间被识别引擎识别。 识别引擎可以基于当前上下文构建识别策略，其中识别策略包括用于在场景的数字表示上执行一个或多个识别算法的规则。 识别引擎可以识别来自对象模型数据库的对象，然后尝试识别与上下文相关的关键帧束，然后可以将其用于跟踪对象或查询内容数据库以获得内容信息。