Remote sensing texture information processing method and device, terminal and storage medium

Abstract

The invention provides a remote sensing texture information processing method and device, a terminal and a storage medium, and the method comprises: obtaining a three-dimensional remote sensing imagepair, and generating a digital terrain model based on the three-dimensional remote sensing image pair; obtaining a slope image based on the digital terrain model, wherein each pixel of the slope imagecorresponds to a slope value; determining the gray value of each pixel based on the slope value corresponding to each pixel in the slope image, and generating a corresponding gray image; and obtaining texture feature information based on the grayscale image. The texture feature / information extracted by the method is more accurate and finer, so that the classification precision based on the texture feature / information is improved.

Description

technical field [0001] The present invention relates to the technical field of remote sensing information processing, in particular to a remote sensing texture information processing method, device, terminal and storage medium. Background technique [0002] The classification of remote sensing ground objects is an important application field of remote sensing images. The remote sensing features in the existing remote sensing image analysis mainly refer to spatial features, geometric features, spectral features and texture features. The texture features refer to texture features based on spectral features. For the surface For remote sensing images in areas with small morphological changes, spectral texture features can be used to classify remote sensing images better. Texture features based on topographic features play an important role, but the existing texture information processing methods do not make full use of topographic features, resulting in the inability to accurate...

AI Technical Summary

Problems solved by technology

[0002] The classification of remote sensing ground objects is an important application field of remote sensing images. The remote sensing features in the existing remote sensing image analysis mainly refer to spatial features, geometric features, spectral features and texture features. The texture features refer to texture features based on spectral features. For the surface For remote sensing images in areas with small morphological changes, spectral texture features can be used to classify remote sensing images better. Texture features based on topographic features play an important role, but the existing texture information processing methods do not make full use of topographic features, resulting in the inability to accurately describe the feature features of corresponding areas in remote sensing images, which restricts the improvement of remote sensing classification accuracy

Images