基于语义的遥感影像数据检索关键技术研究

发布时间：2018-04-01 05:25

  本文选题：元数据　切入点：遥感影像　出处：《国防科学技术大学》2013年硕士论文

【摘要】：随着空间信息科学的快速发展,遥感技术作为空间信息技术,其技术领域已经涵盖遥感、地理信息系统、全球定位系统等诸多技术范畴。其各类空间数据的获取方式更加多样化,获取的效率呈现出快速化的趋向,遥感影像数据属于空间数据,数据迅速增长在利于空间信息获取的同时,其庞大的数据存储也为其影像数据的处理和应用提出了亟待解决的问题。也正因为如此,人们对海量影像数据管理和应用的研究和讨论成为当今遥感技术应用中的一个热点。在本文中,在对遥感影像数据检索的有关技术问题进行研究和分析的基础上,针对遥感影像数据的存储、管理、检索和发布等问题,研究设计了基于语义的遥感影像数据检索解决方案。本文完成的主要工作如下:1、针对多源遥感影像数据,提出了基于语义的遥感影像数据检索系统的元数据参考标准,该参考标准对获取的遥感影像数据的存储和管理具有一定的普适性,有利于影像数据的检索和发布,从而促进遥感影像数据的共享,提高了影像数据的利用率。2、根据遥感影像的特点,使用元数据抽取技术实现对元数据的入库管理,并对遥感影像元数据和影像数据的组织存储进行了深入研究,针对遥感影像数据的存储管理问题给出了较好的解决方案。3、与基于语义的遥感影像数据检索元数据参考标准相对应,建立了遥感影像检索应用本体模型,定义了本体中的概念及属性,并描述了它们之间的关系;通过对遥感影像检索应用本体的查询,实现了对包含关系和等价关系的语义查询扩展。4、集成上述成果,设计并实现了基于语义的遥感影像数据检索原型系统——Rs Image Search。详细阐述了各个模块的设计和实现过程,实现了遥感数据库索引的自动重建与同步更新。实验结果表明该原型系统较好的实现了遥感影像数据的快速检索以及基于自然语言的人性化WEB服务,较好的解决了海量遥感影像数据的存储管理和共享发布等问题,提高了搜索引擎的搜索效果。
[Abstract]:With the rapid development of spatial information science, remote sensing technology, as a spatial information technology, has covered many technical fields such as remote sensing, geographic information system, global positioning system and so on.The methods of obtaining all kinds of spatial data are more diversified, and the efficiency of acquisition shows a tendency of quickening. Remote sensing image data belong to spatial data, and the rapid growth of data is conducive to the acquisition of spatial information at the same time.Its huge data storage also brings forward the problem to be solved urgently for its image data processing and application.Because of this, the research and discussion of mass image data management and application has become a hot spot in the application of remote sensing technology.In this paper, based on the research and analysis of the related technical problems of remote sensing image data retrieval, aiming at the storage, management, retrieval and publication of remote sensing image data,The solution of remote sensing image data retrieval based on semantics is studied and designed.The main work of this paper is as follows: 1. For multi-source remote sensing image data, the metadata reference standard of remote sensing image retrieval system based on semantics is put forward.This reference standard has a certain universality for the storage and management of remote sensing image data, which is conducive to the retrieval and publication of image data, thus promoting the sharing of remote sensing image data.According to the characteristics of remote sensing image, metadata extraction technology is used to realize the management of metadata, and the organization and storage of metadata and image data of remote sensing image are deeply studied.A better solution to the storage and management of remote sensing image data is given. The ontology model of remote sensing image retrieval is established in accordance with the semantic metadata reference standard for remote sensing image retrieval.The concepts and attributes of ontology are defined, and the relationships between them are described. By querying the ontology of remote sensing image retrieval application, the semantic query extension.The prototype system of remote sensing image retrieval based on semantics, RS Image search, is designed and implemented.The design and implementation of each module are described in detail, and the automatic reconstruction and synchronous updating of index of remote sensing database are realized.The experimental results show that the prototype system achieves the fast retrieval of remote sensing image data and the humanized WEB service based on natural language, and solves the problems of storage, management and sharing of massive remote sensing image data.Improved search engine search results.
【学位授予单位】：国防科学技术大学
【学位级别】：硕士
【学位授予年份】：2013
【分类号】：TP751
，

本文编号：1694176