Case library construction method using high-resolution remote sensing land cover classification information

ABSTRACT

Using high-resolution remote sensing images, we propose a case classification method using a land cover classification case library. Case-based reasoning is applied to several aspects of this approach: case representation, case feature selection, case weight, case structure and a similarity measurement model. A detailed study and discussion of the construction of a land cover classification case are presented. Worldview-2 satellite images with 0.5-m spatial resolution are used and the case library construction process for land cover classification information is applied; the effectiveness of the proposed method is then verified using the library. Land cover classification information is thus successfully extracted.

KEYWORDS:

• High-resolution image
• case-based reasoning
• land cover classification
• remote sensing
• case library

Acknowledgements

We would like to thank Editage [www.editage.cn] for English-language editing.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by the Guangxi Bureau of Surveying Mapping and Geoinformation under Grant Number 2014-A-01.