Hyperspectral Image Classification Method Based on Vector Probability Diffusion and Markov Random Field

Abstract

The invention discloses a hyperspectral image classification method based on vector probability diffusion and Markov random field, comprising the following steps: S1 inputting hyperspectral images to be classified into a sample acquisition unit; S2 extracting images corresponding to coordinate positions in the hyperspectral images , and then constitute a reference data sample set; S3 randomly selects a training sample set; S4 uses a support vector machine classifier to classify, obtains the initial classification map of the hyperspectral image, and calculates the attribute binary label map of each category according to the initial classification map; S5 filtering to obtain the posterior probability estimation of the initial category attributes, and construct the Markov random field model based on the maximum posterior probability estimation framework; S6 uses the graph cut algorithm to solve the energy minimization of the constructed Markov random field model, and obtains the final Class attribute posterior probability estimation; S7 processes the final class attribute posterior probability estimation to obtain the final class attribute label and output the final classification map. The invention provides a reliable information source for hyperspectral remote sensing.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a hyperspectral image classification method based on vector probability diffusion and Markov random field. Background technique [0002] Compared with multispectral remote sensing images, hyperspectral remote sensing images have more abundant spectral and spatial information, which can accurately reflect the attribute differences between different types of ground features, and realize accurate extraction and identification of ground features, providing a more accurate hyperspectral image. It has laid a good foundation for remote sensing image analysis and industrial application. However, hyperspectral imagery has high dimensionality, large band correlation, and noise, which brings great challenges to the analysis and processing of hyperspectral remote sensing information. Image classification methods based on spectral features only determine the category of pixels based...

Images