Hyperspectral image classification method based on depth feature cross fusion

Abstract

The invention puts forward a hyperspectral image classification method based on depth feature cross fusion, and mainly solves the problem of spatial feature loss of a traditional convolutional neuralnetwork during hyperspectral data classification. According to the technical scheme, the method comprises the following steps: 1, reading hyperspectral data and preprocessing each spectral band; 2, constructing a data sample by using the preprocessed hyperspectral data, and generating a training set and test set data; 3, constructing a hyperspectral image classification network based on depth feature cross fusion; 4, training the network by using the training set data; and 5, performing classification prediction on the test set data by using the trained network. According to the method, depthfeatures of different branch stages and different scales are fused for multi-channel original data, information exchange is continuously carried out among multi-scale representation, and then the depth feature expression capability of the model is improved; the multi-scale spatial information of different layer depth features of the hyperspectral data is effectively utilized, and the classification precision is improved.

Description

technical field [0001] The invention belongs to the technical field of remote sensing information processing, and further relates to a hyperspectral image classification method, specifically a hyperspectral image classification method based on depth feature cross fusion, which can realize ground object recognition and is used in the fields of environmental monitoring, geological exploration and the like. Background technique [0002] With the development of spectral imaging technology, the spatial resolution of hyperspectral images has been continuously improved, and there are more and more spectral bands, making the information of hyperspectral images more and more abundant. Rich spectral and spatial features make hyperspectral image classification more promising, and at the same time, the classification accuracy requirements are more stringent. [0003] Hyperspectral image classification technology mainly includes data feature engineering and classification. Feature engine...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that it does not consider the strong correlation between deep features, and as the depth of the network increases, the serial convolutional neural network will extract features from high spatial resolution to low spatial resolution, resulting in spatial features. loss of

Images