Hyperspectral image classification method based on deep learning space-spectrum joint network

Abstract

The invention discloses a hyperspectral image classification method based on a deep learning space-spectrum joint network, and the method comprises the steps: firstly carrying out the data partitioning of an original hyperspectral image, and then training the deep learning space-spectrum joint network through a small amount of label data; simultaneously carrying out spectral dimension feature extraction processing on the input hyperspectral original image by a bidirectional long-short-term memory model with an attention mechanism and a 1D hole convolutional neural network to obtain a final spectral feature map; performing data normalization processing on an input image, performing PCA dimension reduction, extracting input features, sending the input features into a multi-scale multi-levelfilter convolutional network to extract spatial features, and performing global average pooling layer processing to obtain a final spatial feature map; and finally, carrying out classification by combining the trained network parameters. According to the method, spectral dimension features and spatial features are processed separately, richer and more effective spectral feature maps and richer feature expressions can be obtained, and the classification precision is further improved.

Description

technical field [0001] The invention belongs to the field of remote sensing image processing, and in particular 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 feature information from hundreds of continuous spectral bands, which makes them have a strong ability to distinguish ground targets. In the past few decades, hyperspectral images have played an important role in military target detection, ocean monitoring, and disaster prevention and control. However, the identification and classification of hyperspectral images is always a key issue in hyperspectral image analysis, and it plays a very important role in the advancement and development of hyperspectral remote sensing technology. The application potential of spectral remote sensing technology is of great significance. [0003] So far, researchers have proposed many methods t...

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