Active Contour Method for Hyperspectral Remote Sensing Image Segmentation Constrained by Spectral Angle

Abstract

The invention discloses a hyperspectral remote-sensing-image active contour segmentation method based on a spectral angle constraint. A spectral angle is used to measure a spectral similarity among index measurement pixels. According to a class separability principle, an optimal wave band suitable for being segmented is selected. And then, a hyperspectral remote-sensing-image active contour segmentation model based on a spectral angle constraint function is designed. A segmentation method which is applied to a two-dimensional image is expanded to and applied to a multidimensional hyperspectral remote sensing image. In the invention, the model can comprehensively use space information and spectrum information of the hyperspectral remote sensing image during a segmentation process; and influences of insufficient spatial resolution, a fuzzy target edge, a heterogeneous area and the like on a segmentation result are reduced.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method for segmenting active contours of hyperspectral remote sensing images constrained by spectral angles. Background technique [0002] In recent years, remote sensing image segmentation has been paid attention to as a key issue in remote sensing image analysis and understanding, region of interest detection, and object recognition. Many effective remote sensing image segmentation methods have emerged, such as principal component analysis, histogram, and Gaussian mixture model. , fast independent component analysis, spectral angle mapping models based on kernel methods, etc. In addition, some traditional image segmentation models such as support vector machines, Markov chains and neural networks have also achieved good segmentation results in remote sensing image segmentation. [0003] Different from traditional remote sensing images, hyperspectral remote sensing images incl...

AI Technical Summary

Problems solved by technology

However, so far, there has been no report on an improved method based on the C-V model combined with the design of the hyperspectral remote sensing image itself.

Images