Hyperspectral image classification method based on long short-term memory network

Abstract

The invention discloses a hyperspectral image classification method based on a long-short-term memory network, which overcomes the disadvantages in the prior art that only use the spectral information of the hyperspectral image and cannot effectively utilize the neighborhood information of the hyperspectral image for classification. The steps realized by the present invention are: (1) input hyperspectral image; (2) dimensionality reduction of hyperspectral image; (3) perform morphological filtering on principal component grayscale image; (4) determine training sample set and test sample set; (5) Construct local spatial sequence specialization; (6) Train long short-term memory network; (7) Classify hyperspectral images; (8) Output classified images. The invention has the advantage of making full use of the spatial context relationship of the hyperspectral image to make the classification effect more accurate, and can be used for the classification of the hyperspectral image.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a hyperspectral image classification method based on a long short-term memory network in the technical field of hyperspectral image classification. The invention can be used to classify the hyperspectral images. Background technique [0002] The deep learning model highly abstracts the low-level features in a hierarchical manner, so as to obtain a better representation of the features. At present, scholars have introduced stacked self-encoder network SAE, deep belief network DBN, convolutional neural network CNN and recurrent neural network RNN ​​deep learning model into hyperspectral image classification. [0003] In their paper "Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks" (IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016), Yushi Chen et al proposed a hyperspectral feature extraction method ba...

AI Technical Summary

Problems solved by technology

Although this method improves the classification accuracy compared with the traditional classification method, it still has the disadvantage that when extracting local spatial features, all the pixels in the neighborhood are simply selected without processing. seriously affected the classification accuracy

Although this method improves the classification accuracy to a certain extent, it still has the disadvantage that the long-term dependence of the RNN model itself will affect the classification accuracy to a certain extent.

Images