Hyperspectral image space-spectral domain classification method based on mean value drifting and group sparse coding

Abstract

The invention discloses a hyperspectral image space-spectral domain classification method based on mean value drifting and group sparse coding and mainly solves the problems that a hyperspectral image is low in classification accuracy and poor in robustness in the conventional method. The method is implemented by the steps of: inputting a hyperspectral image, and representing hyperspectral samples by feature vectors; randomly selecting marked samples in the hyperspectral samples, and carrying out over-segmentation on the hyperspectral image; grouping the hyperspectral samples according to the segmentation result of the hyperspectral image; carrying out sparse coding on the hyperspectral samples by utilizing the group sparse coding; constructing a sample set by utilizing the hyperspectral samples and sparse coding coefficients of the hyperspectral samples; and carrying out classification on the hyperspectral samples by utilizing a support vector machine and the constructed sample set. According to the hyperspectral image space-spectral domain classification method based on the mean value drifting and the group sparse coding, the sparse characteristics and space-domain contextual information of the hyperspectral image are adequately utilized, the relatively high classification accuracy can be obtained, and the method can be applied to the fields of precision agriculture, geological investigation, survey and military reconnaissance and the like.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to image segmentation and sparse representation, and is used for hyperspectral image classification in the context of high local spatial variation. Background technique [0002] Hyperspectral remote sensing technology was born in the 1980s. It combines imaging technology and spectral technology, and can obtain the radiation characteristics of ground objects of interest in tens to hundreds of narrow continuous bands from the ultraviolet to the near infrared of electromagnetic waves. An important cutting-edge technology for Earth observation. Compared with traditional spectral imaging technology, hyperspectral remote sensing not only has a higher number of bands and resolution, but also has almost continuous bands, which can generate a continuous spectral curve for each pixel. , and spectrum triple information, which has the characteristics of spectrum integration. [0003] At pr...

AI Technical Summary

Problems solved by technology

[0006] The performance of feature extraction methods often depends on the quality of feature extraction, and hyperspectral images have a high feature dimension, combining the extracted features and original spectral features will further increase the feature dimension, thereby increasing the computational complexity , and exacerbate the dimensionality disaster effect; the performance of the post-processing method is limited by the quality of image over-segmentation and the classification accuracy based on pixels, and the classification based on pixels only uses the original spectral features, which restricts the improvement of classification performance

Images