Spatial spectrum attention hyperspectral image classification method based on Octave convolution

Abstract

The invention discloses a spatial spectrum attention hyperspectral image classification method based on Octave convolution, and solves the problems of large class spacing, small different class spacing and low classification accuracy in the prior art. The scheme is as follows: inputting images to be classified and preprocessing data, dividing a training set and a test set, constructing an Octave convolutional neural network, determining a loss function of the Octave convolutional neural network, training and updating the Octave convolutional neural network, testing the data of the test set, and completing hyperspectral image classification. According to the method, Octave convolution operation is used to reinforce feature representation, and a spatial attention mechanism and a spectral attention mechanism are introduced, so that the network can more accurately find an area which is more beneficial to classification and contains more comprehensive and detailed information. The method ishigh in classification precision and strong in robustness, and can be applied to analysis and management of hyperspectral image data.

Description

Technical field [0001] The invention belongs to the technical field of image processing, and particularly relates to the content classification of hyperspectral images. Specifically, it is a spatial spectrum attention hyperspectral image classification method based on Octave convolution, which can be applied to the analysis and management of hyperspectral image data. Background technique [0002] With the continuous improvement of the pixel resolution of hyperspectral images, more useful data and information can be obtained from hyperspectral images. According to the needs of different applications, the processing of hyperspectral images also has different requirements. Therefore, in order to effectively analyze and manage these hyperspectral image data, it is necessary to attach a semantic label to each pixel of the hyperspectral image. The classification of hyperspectral images is an important way to solve such problems. Hyperspectral image classification refers to distinguish...

AI Technical Summary

Problems solved by technology

The deep residual convolutional neural network effectively solves the problem that the features extracted by the image classification task contain insufficient information and the network training gradient disappears. However, this network still has large distances between the same category and small distances between different categories due to the complexity of the image data. , the problem of low image classification accuracy and the low robustness of the network caused by the small number of training samples, and the problem of easy to fall into overfitting

[0004]Although the existing convolutional neural network can achieve the task of hyperspectral pixel-level classification, there are still three deficiencies in learning image semantic information: one is Due to the inaccurate positioning of classification information caused by the complexity of hyperspectral images, the distance between the same category is large and the distance between different categories is small when performing classification tasks; the second is that when extracting hyperspectral features, the utilization rate of the extracted features is insufficient It causes information loss or retains too much irrelevant information, resulting in information redundancy, which affects the classification results. At the same time, the convolutional neural network often falls into the local optimal area during training; the third is that there are relatively few hyperspectral data available, and the training convolutional neural network A large amount of training data is usually required, and a small amount of hyperspectral data cannot meet the data requirements of convolutional neural networks

These three deficiencies will lead to problems of poor robustness and misclassification in the classification process of actual hyperspectral images

Images