Multidimensional relation learning for hyperspectral image classification

doi:10.1016/j.neucom.2020.05.034

Return

Multidimensional relation learning for hyperspectral image classification

2020-10-01

PRE

方杰 (Jie Fang) *

Xiaoqian Cao *

DOI：10.1016/j.neucom.2020.05.034

Original

Original request for help

Save

Abstract

En 中文

Classification is a fundamental technique in hyperspectral image understanding field, which is to give each pixel a specific semantic label based on its characteristics automatically. Recently, even though convolutional neural network (CNN) based methods have been applied to hyperspectral image classification, their performances are not in accordance with our expectation. The reason is that, most of the existing methods can not exploit the intrinsic characteristics of different pixels in hyperspectral image effectively, they often ignore the inherent relationships among different spatial pixels, different spectral bands and different category dependencies. Specifically, the relationships among different spatial pixels mean that the similarities of attribute and location information among different pixels. The relationships among different spectral bands mean that the different contributions of them to the final classification. The relationships among different categories mainly mean that the severe sample imbalance problem in hyperspectral image classification task. To address the aforementioned problems, a deep convolutional network based multidimensional relation learning method is proposed in this paper. Firstly, we propose a weighted gaussian mask based spatial relation learning module to alleviate the spatial diffusion issue. Besides, we propose a channel attention alike spectral relation learning module to alleviate the interferences from noisy and redundant bands. Additionally, we propose an integrated decision based category relation learning module to alleviate the ill-conditioned classifying issue from imbalanced samples. Finally, we test the proposed method on four public and challenging datasets, and the experimental results validate the effectiveness and robustness of our method. (C) 2020 Published by Elsevier B.V.

Keywords:

Hyperspectral image classification

Spatial relation learning

Spectral relation learning

Category relation learning

Multidimensional relation learning

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.