A land cover remote sensing classification method and system

Abstract

An embodiment of the present invention provides a land cover remote sensing classification method and system, the method comprising: acquiring image data collected by the Gaofen-1 satellite wide-field imager, and preprocessing the image data to obtain each image The surface albedo of element; According to the surface albedo, construct the NDVI time series variable reflecting the change of land cover type with time; According to the NDVI time series variable, extract the time phase feature of the land cover type; According to the land cover type The spectral features and the temporal features are used to classify the remote sensing images to be classified. The system performs the method described above. The land cover remote sensing classification method and system provided by the embodiments of the present invention effectively improve the land cover classification accuracy by introducing the temporal characteristics of land cover types, and solve the problem that the current land cover classification accuracy, especially the vegetation type classification accuracy is not high.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of land surface remote sensing, and in particular to a land cover remote sensing classification method and system. Background technique [0002] Land cover refers to various types of biological or physical coverage on the earth's land surface, including surface vegetation (natural or artificial), construction land (buildings, roads), lakes, glaciers, bare rocks, and deserts, etc., mainly describing the earth's surface natural attributes. Land cover plays an important role in the human-land interaction system that reflects the relationship between humans and nature, affects all aspects of the earth system process, and is an important parameter of the climate, biochemistry and other models of the earth system. In addition, in terms of land cover application, at present, various industry departments in the country need land cover information. For example, land management departments need ...

AI Technical Summary

Problems solved by technology

However, the relatively mature and widely used land cover remote sensing classification generally only uses spectral features to classify land cover types, resulting in low classification accuracy, especially the classification accuracy of vegetation types, which is not conducive to popularization and meeting the needs of commercial product production.

Images