Object classification-oriented rare earth mining area remote sensing information extraction method

Abstract

The invention relates to an object classification-oriented rare earth mining area remote sensing information extraction method. An object classification-oriented method is adopted to extract rare earth mining area remote sensing information; comparative analysis is performed on the extraction result of the object classification-oriented method and the extraction result of a traditional supervision classification method; and the feasibility and advantages of the object-oriented classification method in rare earth mine information extraction are discussed, and a foundation is laid for the follow-up study of the present situation investigation, dynamic monitoring of rare earth and the like. The method comprises the following steps that: 1) the remote sensing data source of a selected study area is preprocessed, and an edge-based segmentation algorithm is adopted to perform image segmentation; 2) a series of rules is established based on terrain information, spectral information and geometric information, and feature extraction is realized; and 3) object-oriented classification is performed, and the rare earth mining area of the study area is extracted.

Description

technical field [0001] The invention belongs to the technical field of geological and mineral resource research, in particular to a method for extracting remote sensing information of rare earth mining areas based on object-oriented classification. Background technique [0002] Remote sensing image classification is a method of image information extraction, and it is also one of the most widely used fields of remote sensing. Traditional image classification methods mainly include supervised classification and unsupervised classification, as well as fuzzy classification, support vector machine classification and decision tree classification developed on this basis. However, these methods are mainly based on the classification at the pixel level, and do not consider the object's space, texture and other information. In recent years, with the continuous development of high-resolution remote sensing image technology, traditional classification methods can no longer meet the cla...

AI Technical Summary

Problems solved by technology

In recent years, with the continuous development of high-resolution remote sensing image technology, traditional classification methods can no longer meet the classification requirements of high-resolution remote sensing images.

At present, there is no report on the research on remote sensing information extraction method of rare earth mining area using object-oriented classification method

Images