多层次地理视频语义模型

Hierarchical Semantic Model of Geovideo

针对公共安全应急响应中支持推理、挖掘和关联分析的地理视频建模难题,提出了一种显式表达视频变化的多层次地理视频语义模型,并用UML图进行描述。该模型的特点是:改变了传统视频流整体语义描述方法,通过面向变化的三域(特征域-行为过程域-事件域)定义地理视频语义的层次结构和数据的层次表达;在各层次语义描述中将地理环境语义与视频内容语义有机结合,支持多地理视频数据的关联表示。以公共安全事件监控视频为例阐明了模型的实用性和有效性。

The publ ic security incidents were getting increasingly chal lenging with regard to thei r new features, including multi-scale mobility, multistage dynamic evolution, as well as spatiotemporal concurrency and uncertainty in the complex urban envi ronment.However,the existing video models,which were used/designed for independent archive or local analysis of surveil lance video,have seriously inhibited emergency response to the urgent requi rements.Aiming at the expl icit representation of change mechanism in video,the paper proposed a novel hierarchical geovideo semantic model using UML.This model was characterized by the hierarchical representation of both data structure and semantics based on the change-oriented three domains (feature domain,process domain and event domain)instead of overall semantic description of video streaming;combining both geographical semantics and video content semantics,in support of global semantic association between multiple geovideo data.The publ ic security incidents by video surveil lance are inspected as an example to illustrate the val idity of this model.