An Efficient and Robust Framework for Hyperspectral Anomaly Detection

Hyperspectral images contain distinguishing spectral information and show great potential in the anomaly detection (AD) task which aims to extract discrepant targets from the background. However, most of the popular hyperspectral AD techniques are time consuming and suffer from poor detection perfor...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Linbo Tang, Zhen Li, Wenzheng Wang, Baojun Zhao, Yu Pan, Yibing Tian
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	hyperspectral image anomaly detection principal component analysis robustness Science Q
Acceso en línea:	https://doaj.org/article/0cb8843729ac48469c44da49039502af
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0cb8843729ac48469c44da49039502af
record_format	dspace
spelling	oai:doaj.org-article:0cb8843729ac48469c44da49039502af2021-11-11T18:51:25ZAn Efficient and Robust Framework for Hyperspectral Anomaly Detection10.3390/rs132142472072-4292https://doaj.org/article/0cb8843729ac48469c44da49039502af2021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4247https://doaj.org/toc/2072-4292Hyperspectral images contain distinguishing spectral information and show great potential in the anomaly detection (AD) task which aims to extract discrepant targets from the background. However, most of the popular hyperspectral AD techniques are time consuming and suffer from poor detection performance due to noise disturbance. To address these issues, we propose an efficient and robust AD method for hyperspectral images. In our framework, principal component analysis (PCA) is adopted for spectral dimensionality reduction and to enhance the anti-noise ability. An improved guided filter with edge weight is constructed to purify the background and highlight the potential anomalies. Moreover, a diagonal matrix operation is designed to quickly accumulate the energy of each pixel and efficiently locate the abnormal targets. Extensive experiments conducted on the real-world hyperspectral datasets qualitatively and quantitatively demonstrate that, compared with the existing state-of-the-art approaches, the proposed method achieves higher detection accuracy with faster detection speed which verifies the superiority and effectiveness of the proposed method.Linbo TangZhen LiWenzheng WangBaojun ZhaoYu PanYibing TianMDPI AGarticlehyperspectral imageanomaly detectionprincipal component analysisrobustnessScienceQENRemote Sensing, Vol 13, Iss 4247, p 4247 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	hyperspectral image anomaly detection principal component analysis robustness Science Q
spellingShingle	hyperspectral image anomaly detection principal component analysis robustness Science Q Linbo Tang Zhen Li Wenzheng Wang Baojun Zhao Yu Pan Yibing Tian An Efficient and Robust Framework for Hyperspectral Anomaly Detection
description	Hyperspectral images contain distinguishing spectral information and show great potential in the anomaly detection (AD) task which aims to extract discrepant targets from the background. However, most of the popular hyperspectral AD techniques are time consuming and suffer from poor detection performance due to noise disturbance. To address these issues, we propose an efficient and robust AD method for hyperspectral images. In our framework, principal component analysis (PCA) is adopted for spectral dimensionality reduction and to enhance the anti-noise ability. An improved guided filter with edge weight is constructed to purify the background and highlight the potential anomalies. Moreover, a diagonal matrix operation is designed to quickly accumulate the energy of each pixel and efficiently locate the abnormal targets. Extensive experiments conducted on the real-world hyperspectral datasets qualitatively and quantitatively demonstrate that, compared with the existing state-of-the-art approaches, the proposed method achieves higher detection accuracy with faster detection speed which verifies the superiority and effectiveness of the proposed method.
format	article
author	Linbo Tang Zhen Li Wenzheng Wang Baojun Zhao Yu Pan Yibing Tian
author_facet	Linbo Tang Zhen Li Wenzheng Wang Baojun Zhao Yu Pan Yibing Tian
author_sort	Linbo Tang
title	An Efficient and Robust Framework for Hyperspectral Anomaly Detection
title_short	An Efficient and Robust Framework for Hyperspectral Anomaly Detection
title_full	An Efficient and Robust Framework for Hyperspectral Anomaly Detection
title_fullStr	An Efficient and Robust Framework for Hyperspectral Anomaly Detection
title_full_unstemmed	An Efficient and Robust Framework for Hyperspectral Anomaly Detection
title_sort	efficient and robust framework for hyperspectral anomaly detection
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/0cb8843729ac48469c44da49039502af
work_keys_str_mv	AT linbotang anefficientandrobustframeworkforhyperspectralanomalydetection AT zhenli anefficientandrobustframeworkforhyperspectralanomalydetection AT wenzhengwang anefficientandrobustframeworkforhyperspectralanomalydetection AT baojunzhao anefficientandrobustframeworkforhyperspectralanomalydetection AT yupan anefficientandrobustframeworkforhyperspectralanomalydetection AT yibingtian anefficientandrobustframeworkforhyperspectralanomalydetection AT linbotang efficientandrobustframeworkforhyperspectralanomalydetection AT zhenli efficientandrobustframeworkforhyperspectralanomalydetection AT wenzhengwang efficientandrobustframeworkforhyperspectralanomalydetection AT baojunzhao efficientandrobustframeworkforhyperspectralanomalydetection AT yupan efficientandrobustframeworkforhyperspectralanomalydetection AT yibingtian efficientandrobustframeworkforhyperspectralanomalydetection
_version_	1718431686079807488

An Efficient and Robust Framework for Hyperspectral Anomaly Detection

Ejemplares similares