Hyperspectral image compression and classification method based on discriminative feature learning

Abstract

The invention discloses a hyperspectral image compression and classification method based on discriminative feature learning, which is used for solving the technical problem of poor practicability ofthe existing hyperspectral image compression and classification method. According to the technical scheme, the end-to-end compressed classification network comprises two branch structures, wherein onepath is a stack self-encoding module and is used for learning data identifiability features, the encoder is used for feature compression, and the decoder is used for feature decompression. A mean square error loss function of all data is calculated through an encoder and a decoder; and the other path is a classification module which is used for classifying identifiable features, the encoder and the classifier use a shared module, and the classifier performs classification by utilizing identifiable compression features obtained by the encoder so as to complete end-to-end feature compression and classification tasks. The shared encoder module not only can obtain identifiable characteristics, but also can efficiently perform a hyperspectral image classification task according to the identifiable characteristics, and is good in practicability.

Description

technical field [0001] The invention relates to a hyperspectral image compression and classification method, in particular to a hyperspectral image compression and classification method for discriminative feature learning. Background technique [0002] Different from traditional images, each pixel of hyperspectral images contains a series of continuous spectral bands, and the rich spectral information makes it widely used in many fields. Due to the abundance of spectral bands, hyperspectral images consume more storage and computing costs than conventional color images, especially in the field of satellite remote sensing. In recent years, deep learning methods have been used more and more in hyperspectral image classification tasks, but models based on fully connected or convolutional neural networks usually require huge parameters and calculations. How to maintain discrimination while, Reducing the amount of model parameters or the amount of hyperspectral data is an urgent ...

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the disadvantages of poor practicability of existing hyperspectral image compression and classification methods, the present invention provides a hyperspectral image compression and classification method with discriminative feature learning

Images