Disaster Assessment with High Resolution Remote Sensing Images Based on Hierarchical Knowledge Transfer Method

Abstract

High resolution remote sensing images are more detailed observation data of small targets on the earth's surface, and have become one of important data support for disaster monitoring and assessment. At present, some achievements have been got on the application of high resolution remote sensing images in the field of disasters. However, the existing methods needed professional data and professional staff, which limits the wide application of these methods in actual business. In order to improve the automation level of disaster assessment services and the accuracy of evaluation results, this paper proposed a hierarchical model, which named - rule - knowledge model on the basis of the full analysis of disaster assessment process and earthquake disaster assessment application. An implementation framework of dynamic acquisition and hierarchical transfer was designed, and some key technologies were described in detail, including hierarchical management model, sample matching, feature selection, spatial rules mining and historical application. Finally, taking Ludian, Yunnan Province as a study area, an automatic experiment of earthquake disaster assessment based on high resolution remote sensing images was carried out. The comparison between experimental results and field survey results showed that this method could basically automate the evaluation process and effectively enhance the capability of disaster emergency response. At the same time, the stability of evaluation results was improved by reducing manual participation in assessment process.