Method and system for extracting three elements of forest, shrub and grass in typical resource elements

Abstract

The present invention provides a method and system for extracting the three elements of forest, shrub, and grass among typical resource elements, including: obtaining the observation data of several frames in the image to be identified, using the observation data of each frame as a vector, and performing the extraction according to the time sequence of the frames The vectors are sorted to obtain a vector sequence; the category label and the vector sequence of the forward time series and the reverse time series are input into the preset time recurrent neural network, and the image to be recognized is obtained according to the output result of the time recurrent neural network land cover types in . On the one hand, the present invention can more accurately reflect the characteristics of ground objects in the image, and on the other hand, it provides support for meeting the accuracy requirements of land cover classification by extracting more time-dimensional information.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing, and more particularly, to a method and system for extracting three elements of forest, shrub and grass in typical resource elements. Background technique [0002] Land cover refers to the general term for vegetation cover and artificial cover on the earth's surface, which is a comprehensive reflection of the surface elements covered by natural vegetation and natural and artificial structures. Land cover is the necessary information for humans to understand nature and master natural laws, and it is also the most basic data required for various resource management and geographic information services. Therefore, the acquisition, analysis and update of land cover information is extremely important. [0003] Remote sensing image data has always been an important means of land cover detection due to its macroscopic and real-time characteristics. At present, land cover extracti...

AI Technical Summary

Problems solved by technology

With the emergence of advanced products of remote sensing data, especially a variety of land surface characteristic parameter products (representative GLASS (Global land surface satellite) products, for details, please refer to: http: / / glass-product.bnu.edu.cn / ) the emergence of existing land cover classification technology schemes have been unable to meet the accuracy requirements of land cover classification

Images