A hyperspectral image classification method based on deep learning space-spectral joint network

Abstract

The invention discloses a hyperspectral image classification method based on a deep learning space-spectrum joint network. First, the original hyperspectral image is divided into data, and then a small amount of label data is used to train the deep learning space-spectrum joint network. The input hyperspectral original The image will be processed by a bidirectional long short-term memory model with an attention mechanism and a 1D dilated convolutional neural network for spectral dimension feature extraction at the same time to obtain the final spectral feature map; the input image is processed by data normalization, and then PCA reduction is performed. dimension, extract input features, and send the input features into the multi-scale multi-level filter convolution network to extract spatial features, and then process them through the global average pooling layer to obtain the final spatial feature map; finally, combine the trained network parameters sort. The present invention processes spectral dimension features and spatial features separately, can obtain richer and more effective spectral feature maps and richer feature expressions, and the classification accuracy is further improved.

Description

Technical field [0001] The invention belongs to the field of remote sensing image processing, and specifically relates to a hyperspectral image classification method based on deep learning space-spectrum joint network. Background technique [0002] Hyperspectral remote sensing images can extract ground object information from hundreds of continuous spectral bands, which makes them powerful in distinguishing ground targets. In the past few decades, hyperspectral images have played an important role in military target detection, ocean monitoring, disaster prevention and other aspects. However, the identification and classification of hyperspectral images has always been a key issue in hyperspectral image analysis. It plays a very important role in the advancement and development of hyperspectral remote sensing technology. Therefore, studying efficient and practical HIS classification methods is crucial to fully exploring high-frequency spectral images. The application potenti...

AI Technical Summary

Problems solved by technology

However, the former has made band selection, which leads to a large loss of features, and the continuous context information in the spectral dimension will also be destroyed, while the latter cannot completely extract the entire spectral information, and both of them only use convolutional neural network extraction. feature, the network has outstanding advantages in extracting local related features, but cannot extract complete feature information

Images