A hyperspectral remote sensing image classification method based on six-layer convolutional neural network and joint spectral-spatial information

Abstract

The invention discloses a hyperspectral remote sensing image classification method based on a combination of six-layer convolutional neural network and spectral-spatial information, which selects hyperspectral remote sensing image data of a certain number of bands, and performs spatial analysis on the selected two-dimensional image data of each band. Mean filtering, and then convert the format of the multi-band data corresponding to each pixel, and convert the one-dimensional vector into a square matrix, that is, each pixel corresponds to a square matrix data. Then design a six-layer classifier based on deep learning template, including input layer, first convolutional layer, maximum pooling layer, second convolutional layer, fully connected layer, output layer; extract the square matrix corresponding to several pixels The data is used as the training set, input the classifier and train the classifier; extract the square matrix data corresponding to several pixels as the test set, input it into the trained classifier, observe the classification results output by the trainer, and compare with the real The classification information is compared to verify the performance of the classifier. The classification accuracy rate of the present invention is higher than the existing 5-CNN method.

Description

technical field [0001] The invention belongs to the field of remote sensing image processing, and relates to a classification method for different object categories in a hyperspectral image, in particular to a hyperspectral remote sensing image classification method based on a six-layer convolutional neural network and spectral-spatial information combination. Background technique [0002] The current hyperspectral remote sensing data can obtain dozens or even hundreds of spectral band information at the same time, and the rich spectral information greatly improves the ability to identify and distinguish various types of ground objects. Moreover, with the improvement of the spatial resolution of hyperspectral sensors, researchers can use hyperspectral remote sensing images to analyze ground objects with small spatial structures. Due to the rich surface information of hyperspectral remote sensing images, wide coverage, and multi-temporal characteristics, its application techn...

AI Technical Summary

Problems solved by technology

Aiming at the problem of insufficient labeled samples caused by the difficulty and high cost of labeling samples in hyperspectral remote sensing images, the existing research proposes a semi-supervised classification model using a stacked denoising autoencoder, which is combined with an edge-preserving denoising filtering algorithm. Combined with hyperspectral remote sensing images for classification [Reference: Wang Qiaoyu. Hyperspectral remote sensing image classification based on deep learning [D]. Huaqiao University, 2016]

Among the methods proposed by existing studies, some use deep learning methods, but only consider the spectral information without combining the spatial information of the image, and some combine spectral-spatial information, but do not use the convolutional neural network structure as a classifier. Without combining the spatial filtering algorithm with the convolutional neural network, the classification effect is limited

Images