Hyperspectral image classification method based on deep learning

Abstract

The invention discloses a hyperspectral image classification method based on deep learning, and belongs to the technical field of remote sensing image processing. The method comprises the steps that 1, dimension reduction treatment on a hyperspectral image is achieved by obtaining a data sample, conducting layer-by-layer training on an autoencoder network and further adjusting an initial weight value obtained through pre-training by adopting a BP algorithm; a data cube in each pixel neighbourhood in the hyperspectral image is taken as input of a convolutional neural network, a ground object type corresponding to a pixel serves as expected output of the convolutional neural network, the convolutional neural network is trained, the trained convolutional neural network acts on the whole hyperspectral image, and a final high-precision classification result is obtained. According to the method, the defects that in a traditional hyperspectral image classification problem, details are discarded in the dimension reduction process, space information is lost in the classification process, and the classification precision is low are overcome, the good classification precision is achieved, and the method is suitable for classification of various hyperspectral images.

Description

technical field [0001] The invention relates to a hyperspectral image classification method based on deep learning, which belongs to remote sensing and mapping, computer vision and pattern recognition technology, and is applicable to hyperspectral data obtained by any imaging spectrometer. Background technique [0002] The fine classification of hyperspectral images is one of the core contents of the application of hyperspectral remote sensing technology, and it is a problem of great concern in the fields of computer vision and pattern recognition, remote sensing and surveying and mapping. The existing classification methods suffer from the loss of nonlinear information in the hyperspectral image during the dimensionality reduction process and the need to artificially design the spatial characteristics of the image when using the spatial characteristics of the image, resulting in poor classification accuracy and poor classification of hyperspectral images. determinism, which...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved in the present invention is: to overcome the two deficiencies of the existing hyperspectral image classification method: (1) the existing linear dimensionality reduction method will cause the loss of nonlinear information in the hyperspectral image during the dimensionality reduction process ; (2) When using the spatial characteristics of the image, it is necessary to artificially design the spatial characteristics

Images