Extensible Land Use Classification Framework Based on Remotely Sensed Image Facing to Data Integration, Exchange and Sharing

Abstract

Land use information plays important role not only in social-economic development but also in scientific research area. With the development of the Information Technology, remotely sensed images provide main data sources for land use information and knowledge extraction in real time. While there are lots of land use classification systems in the world facing to different research or application purposes. And with the crossing of multi-disciplines and expanding of the research area, more and more land use classification systems are designed. This brings the difficulties for land use data setspsila integration, exchange and sharing under different classification systems. The problem faced to land use classification systems are similar with the problem of metadata standards in geographic information data management field. While ISO Metadata Standard 19115 designed by ISO TC 211 provides a perfect solution for geographic data integration, exchange and sharing. Enlightened by the ISO 19115 metadata extensible model, the paper brings forward the land use extensible classification framework. The framework is composed of 3 tiers, i.e., land use core classes, corpora classes and application profile classes. The core and corpora classes are derived from the main international land use classification systems in the world. Semantic exchange mechanism between core classes and other main classification in the world is designed supported by information techniques. Extension principle and methods are designed in this framework. This ensures many application classification profiles can be extended from the core classes and corpora classes easily.