Hyperspectral image robustness classification method based on segmentation depth characteristics and low-rank representation

Abstract

The invention provides a hyperspectral image robustness classification method based on segmentation depth characteristics and low-rank representation. The method comprises the following steps that: firstly, in order to lower an influence of noise on feature extraction as far as possible, using a stack-based denoising autoencoder netework to carry out unsupervised feature extraction on a hyperspectral image; then, fully mining an intra-class similarity and an inter-class difference in the hyperspectral image to establish a robust classifier based on the low-rank representation; and finally, adopting an effective optimization method to carry out optimal solving on a target function. Under a situation that training data contains noise, a good classification effect can be obtained.

Description

technical field [0001] The invention belongs to the technical field of hyperspectral image processing, and in particular relates to a hyperspectral image robust classification method based on segmented depth features and low-rank representation. Background technique [0002] At present, hyperspectral images have been widely used in the fields of resource exploration, environmental monitoring and target recognition, but in practical applications, due to the influence of imaging environment and transmission process, hyperspectral images are susceptible to noise interference, resulting in image quality degradation, thus Affects the accuracy of hyperspectral image interpretation. How to effectively complete the hyperspectral image classification task in the presence of widespread noise has gradually attracted widespread attention from scholars at home and abroad. A large number of experiments have shown that stacked autoencoders are an effective unsupervised feature learning me...

AI Technical Summary

Problems solved by technology

However, this method only considers the inter-spectral correlation, and does not fully exploit the spatial correlation of hyperspectral images, as well as intra-class similarity and inter-class difference, thus limiting the accuracy of hyperspectral image classification

Images