A CNN hyperspectral image classification method based on edge preserving filtering

Abstract

The invention discloses a CNN hyperspectral image classification method based on edge preserving filtering, and in order to enhance the classification effect, edge preserving filtering is adopted to carry out spatial feature extraction. Meanwhile, in order to solve the problem of unbalanced features of the classified samples, the original loss function is changed, the classification penalty of a small number of samples is increased, and the classification effect is further improved.

Description

technical field [0001] The present invention relates to the technical field of hyperspectral image classification, and more specifically relates to a CNN hyperspectral image classification method based on edge-preserving filtering. Background technique [0002] With the development of hyperspectral imagers, hyperspectral images have become readily available. Due to its rich spatial and spectral features, hyperspectral images have been widely used in land cover, environmental monitoring, military reconnaissance, etc. As a key issue in hyperspectral image applications, hyperspectral image classification has received more and more attention. [0003] Hyperspectral image classification is to classify each pixel according to its spectral characteristics. In the past few decades, many pixel-sensitive classification methods have emerged, such as K-Nearest Neighbors (KNN), Support Vector Machines (SVM), sparse representation, etc. However, these traditional methods only consider ...

AI Technical Summary

Problems solved by technology

Therefore, this method is very dependent on the previous classification results and cannot make full use of spatial features.

Images