测绘学报 ›› 2015, Vol. 44 ›› Issue (5): 555-562.doi: 10.11947/j.AGCS.2015.20140176

• 地图学与地理信息 • 上一篇    下一篇

多层次地理视频语义模型

谢潇1,2, 朱庆1,3, 张叶廷1, 周艳4, 许伟平1, 吴晨1   

  1. 1. 武汉大学测绘遥感信息工程国家重点实验室, 湖北 武汉 430079;
    2. 慕尼黑工业大学地图制图系, 德国 慕尼黑 80333;
    3. 西南交通大学地球科学与环境工程学院, 四川 成都 610031;
    4. 电子科技大学资源与环境学院, 四川 成都 611731
  • 收稿日期:2014-04-08 修回日期:2014-06-17 出版日期:2015-05-20 发布日期:2015-05-27
  • 通讯作者: 朱庆 E-mail: zhuq66@263.net E-mail:zhuq66@263.net
  • 作者简介:谢潇(1986—),女,博士生,研究方向为虚拟地理环境与视频GIS。E-mail: xiexiaolmars@gmail.com
  • 基金资助:

    绿洲生态教育部重点实验室开放课题(XJDX0201-2013-01);国家科技支撑计划(2012BAH35B02);国家自然科学基金(41261086;41471320; 41471332)

Hierarchical Semantic Model of Geovideo

XIE Xiao1,2, ZHU Qing1,3, ZHANG Yeting1, ZHOU Yan4, XU Weiping1, WU Chen1   

  1. 1. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;
    2. Department of Cartography, Technical University of Munich, Munich 80333, Germany;
    3. Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 610031, China;
    4. School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, China
  • Received:2014-04-08 Revised:2014-06-17 Online:2015-05-20 Published:2015-05-27
  • Supported by:

    Open Foundation Funded by Key Laboratory of Oasis Ecology of Xinjiang University, China (No.XJDX0201-2013-01);The National Key Technology Research and Development Program of the Ministry of Science and Technology of China (No.2012BAH35B02);The National Natural Science Foundation of China (Nos.41261086;41471320; 41471332)

摘要:

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。

关键词: 视频GIS, 地理视频, 语义模型, 事件, 时空关联

Abstract:

The public security incidents were getting increasingly challenging with regard to their new features, including multi-scale mobility, multistage dynamic evolution, as well as spatiotemporal concurrency and uncertainty in the complex urban environment. However, the existing video models, which were used/designed for independent archive or local analysis of surveillance video, have seriously inhibited emergency response to the urgent requirements.Aiming at the explicit 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 public security incidents by video surveillance are inspected as an example to illustrate the validity of this model.

Key words: video GIS, geovideo, semantic model, event, spatiotemporal association

中图分类号: