Local similarity preserving-based hyperspectral image extreme learning machine clustering method

Abstract

The invention discloses a local similarity preserving-based hyperspectral image extreme learning machine clustering method. The method comprises the steps of organizing a hyperspectral pixel matrix; calculating a linear random response of a hidden layer neuron; calculating a nonlinear activation value of the hidden layer neuron; performing three-dimensional reconstruction of hidden layer feature data; performing spatial guided filtering; performing two-dimensional reconstruction of the filtered hidden layer feature data; building local similarity preserving regular terms and an optimization model; and calculating local similarity preserving projection features, and performing K-means clustering to obtain a final clustering tag. Based on a conventional extreme learning machine, hyperspectral image spatial information of local neighborhoods is integrated through the guided filtering, and spectral local similarity of a hyperspectrum is fully utilized; projection with local preservabilityis calculated through model optimization; spatial spectral joint information is extracted; the clustering precision is improved; the calculation complexity is lowered; and the method can be widely applied to the hyperspectral unsupervised classification in the fields of territorial resources, mineral survey and precision agriculture.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates to a hyperspectral image extreme learning machine clustering method with local similarity preservation. Background technique [0002] Due to its spectral correlation and rich spatial information, hyperspectral images are widely used in military monitoring, precision agriculture and mineral monitoring, among which hyperspectral image clustering is one of the most important research contents. The basic principle of hyperspectral image clustering is to perform unsupervised classification of target images on the basis of image clustering, combined with the spectral characteristics of hyperspectral images. The theoretical basis is that the same pixel has the same or similar spectral characteristics, and conversely, different pixels correspond to different spectral characteristics. [0003] At present, many clustering algorithms for hyperspectral image...

AI Technical Summary

Problems solved by technology

However, the above method only utilizes the hyperspectral pixel-by-pixel spectral information, does not effectively combine spatial-spectral information, the clustering accuracy is low, and the performance of the algorithm decreases when there is noise in the data

Images