Publication
A Fully Automatic Method to Extract Rare Earth Mining Areas from Landsat Images
Publisher:
American Society for Photogrammetry and Remote Sensing
Date:
09-2016
DOI:
10.14358/PERS.82.9.729
Abstract: This paper proposes a new morphological mining feature index ( small MMFI /small ) by synthesizing multi-scale and multi-direction differential morphological profiles (DMPs) to effectively separate small REMAS /small from other land covers with similar spectral signals and local brightness contrast. The small MMFI /small enhances the local brightness contrast of rare earth mining areas ( small REMAS /small ) by highlighting the morphological characteristics of small REMA /small structure, and improves the identification of roads and bare soil, which have similar spectral signatures to small REMAS /small . Moreover, a new threshold optimization method that maximizes the histogram entropy is presented, whereby small REMAS /small can be automatically extracted from the small MMFI /small image without s le collection and machine learning. Therefore, it is a fully automatic method suitable for small REMA /small extraction over large areas. To validate the proposed method, three temporal Landsat images acquired of Changting County, China, were used to extract small REMA /small information. Our results demonstrate that the proposed method can achieve good classification accuracy compared with other methods.