An adaptive spatio-spectral domain correlation parallel framework for hyperspectral image classification

With the rapid development of hyperspectral image technology, the spectral resolution and spatial resolution of hyperspectral images are continuously increasing, which in turn leads to a rapid increase of data amount in hyperspectral images. The huge amount of data poses a big challenge to the rapid...

Full description

Saved in:
Bibliographic Details
Main Authors: Wang, Xianchen, Xie, Weixin
Format: Conference Proceeding
Language:English
Subjects:
Adaptive
Classification algorithms
Correlation
Feature extraction
Hyperspectral imaging
Image classification
Parallel Classification
Spatial resolution
Spectral Domain
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the rapid development of hyperspectral image technology, the spectral resolution and spatial resolution of hyperspectral images are continuously increasing, which in turn leads to a rapid increase of data amount in hyperspectral images. The huge amount of data poses a big challenge to the rapid processing of hyperspectral images. This paper proposes an adaptive spatio-spectral domain correlation parallel framework for hyperspectral image classification. The experimental results show that the classification accuracy and processing speed of our proposed framework are more efficient and higher than that of existing classification algorithms for hyperspectral images.
ISSN:2164-5221
DOI:10.1109/ICSP.2018.8652407