Hyperspectral anomaly detection based on low-rank representation with data-driven projection and dictionary construction

Xiaoxiao Ma; Xiangrong Zhang; Xu Tang; Huiyu Zhou; Licheng Jiao

doi:10.1109/JSTARS.2020.2990457

Hyperspectral anomaly detection based on low-rank representation with data-driven projection and dictionary construction

Xiaoxiao Ma, Xiangrong Zhang^*, Xu Tang, Huiyu Zhou, Licheng Jiao

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

7 Citations (Scopus)

41 Downloads (Pure)

Abstract

Hyperspectral image anomaly detection is an increasingly important research topic in remote sensing images understanding and interpretation. Recently, low-rank representation-based methods have attracted extensive attention and achieved promising performances in hyperspectral anomaly detection. These methods assume that the hyperspectral data can be decomposed into two parts: the low-rank component representing the background and the residual part indicating the anomaly. In order to improve the separability of the background and anomaly, we propose a novel hyperspectral anomaly detection based on low-rank representation with dictionary construction and data-driven projection. To construct a robust dictionary that contains all categories of the background objects whilst excluding the anomaly's influence, we adopt a superpixel-based tensor low-rank decomposition method to generate a comprehensive and pure background dictionary. Considering the spectral redundancy in the hyperspectral data, data-driven projection is introduced to the low-rank representation to project the original data to a low-dimensional feature space to better separate the anomaly and the background. Experimental results on four real hyperspectral datasets show that the proposed anomaly detection method outperforms the other anomaly detectors.

Original language	English
Pages (from-to)	2226-2239
Number of pages	14
Journal	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Volume	13
DOIs	https://doi.org/10.1109/JSTARS.2020.2990457
Publication status	Published - 11 May 2020
Externally published	Yes

Bibliographical note

Funding Information:
Thisworkwas supported in part by the National Natural Science Foundation ofChina underGrant 61772400

Funding Information:
Manuscript received January 21, 2020; revised March 31, 2020; accepted April 11, 2020. Date of publication May 11, 2020; date of current version May 29, 2020. This work was supported in part by the National Natural Science Foundation of China under Grant 61772400, Grant 61501353, Grant 61772399, Grant 91438201, and Grant 61573267 and in part by the Key Research and Development Program in the Shaanxi Province of China under Grant 2019ZDLGY03-08. The work of Huiyu Zhou was supported in part by the U.K. EPSRC under Grant EP/N011074/1, in part by the Royal Society Newton Advanced Fellowship under Grant NA160342, and in part by European Union’s Horizon 2020 research and innovation program under the Marie-Sklodowska-Curie under Grant 720325. (Corresponding author: Xiangrong Zhang.) Xiaoxiao Ma, Xiangrong Zhang, Xu Tang, and Licheng Jiao are with the Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi’an 710071, China (e-mail: xx_ma@stu.xidian.edu.cn; xrzhang@mail.xidian.edu.cn; tangxu128@gmail. com; lchjiao@mail.xidian.edu.cn).

Publisher Copyright:
© 2008-2012 IEEE.

Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.

Keywords

Data-driven projection
Hyperspectral image (hsi) anomaly detection
Low-rank representation (lrr)
Tensor decomposition

ASJC Scopus subject areas

Computers in Earth Sciences
Atmospheric Science

Access to Document

10.1109/JSTARS.2020.2990457Licence: CC BY

Hyperspectral Anomaly Detection Based on Low-Rank Representation With Data-Driven Projection and Dictionary Construction
Copyright 2020 the authors. This is an open access article published under a Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium, provided the author and source are cited.
Final published version, 3.35 MBLicence: CC BY

Cite this

@article{a2febf045861414e87eb213cd522bdd2,

title = "Hyperspectral anomaly detection based on low-rank representation with data-driven projection and dictionary construction",

abstract = "Hyperspectral image anomaly detection is an increasingly important research topic in remote sensing images understanding and interpretation. Recently, low-rank representation-based methods have attracted extensive attention and achieved promising performances in hyperspectral anomaly detection. These methods assume that the hyperspectral data can be decomposed into two parts: the low-rank component representing the background and the residual part indicating the anomaly. In order to improve the separability of the background and anomaly, we propose a novel hyperspectral anomaly detection based on low-rank representation with dictionary construction and data-driven projection. To construct a robust dictionary that contains all categories of the background objects whilst excluding the anomaly's influence, we adopt a superpixel-based tensor low-rank decomposition method to generate a comprehensive and pure background dictionary. Considering the spectral redundancy in the hyperspectral data, data-driven projection is introduced to the low-rank representation to project the original data to a low-dimensional feature space to better separate the anomaly and the background. Experimental results on four real hyperspectral datasets show that the proposed anomaly detection method outperforms the other anomaly detectors.",

keywords = "Data-driven projection, Hyperspectral image (hsi) anomaly detection, Low-rank representation (lrr), Tensor decomposition",

author = "Xiaoxiao Ma and Xiangrong Zhang and Xu Tang and Huiyu Zhou and Licheng Jiao",

note = "Funding Information: Thisworkwas supported in part by the National Natural Science Foundation ofChina underGrant 61772400 Funding Information: Manuscript received January 21, 2020; revised March 31, 2020; accepted April 11, 2020. Date of publication May 11, 2020; date of current version May 29, 2020. This work was supported in part by the National Natural Science Foundation of China under Grant 61772400, Grant 61501353, Grant 61772399, Grant 91438201, and Grant 61573267 and in part by the Key Research and Development Program in the Shaanxi Province of China under Grant 2019ZDLGY03-08. The work of Huiyu Zhou was supported in part by the U.K. EPSRC under Grant EP/N011074/1, in part by the Royal Society Newton Advanced Fellowship under Grant NA160342, and in part by European Union{\textquoteright}s Horizon 2020 research and innovation program under the Marie-Sklodowska-Curie under Grant 720325. (Corresponding author: Xiangrong Zhang.) Xiaoxiao Ma, Xiangrong Zhang, Xu Tang, and Licheng Jiao are with the Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi{\textquoteright}an 710071, China (e-mail: xx_ma@stu.xidian.edu.cn; xrzhang@mail.xidian.edu.cn; tangxu128@gmail. com; lchjiao@mail.xidian.edu.cn). Publisher Copyright: {\textcopyright} 2008-2012 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.",

year = "2020",

month = may,

day = "11",

doi = "10.1109/JSTARS.2020.2990457",

language = "English",

volume = "13",

pages = "2226--2239",

journal = "IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing",

issn = "1939-1404",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Hyperspectral anomaly detection based on low-rank representation with data-driven projection and dictionary construction

AU - Ma, Xiaoxiao

AU - Zhang, Xiangrong

AU - Tang, Xu

AU - Zhou, Huiyu

AU - Jiao, Licheng

N1 - Funding Information: Thisworkwas supported in part by the National Natural Science Foundation ofChina underGrant 61772400 Funding Information: Manuscript received January 21, 2020; revised March 31, 2020; accepted April 11, 2020. Date of publication May 11, 2020; date of current version May 29, 2020. This work was supported in part by the National Natural Science Foundation of China under Grant 61772400, Grant 61501353, Grant 61772399, Grant 91438201, and Grant 61573267 and in part by the Key Research and Development Program in the Shaanxi Province of China under Grant 2019ZDLGY03-08. The work of Huiyu Zhou was supported in part by the U.K. EPSRC under Grant EP/N011074/1, in part by the Royal Society Newton Advanced Fellowship under Grant NA160342, and in part by European Union’s Horizon 2020 research and innovation program under the Marie-Sklodowska-Curie under Grant 720325. (Corresponding author: Xiangrong Zhang.) Xiaoxiao Ma, Xiangrong Zhang, Xu Tang, and Licheng Jiao are with the Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi’an 710071, China (e-mail: xx_ma@stu.xidian.edu.cn; xrzhang@mail.xidian.edu.cn; tangxu128@gmail. com; lchjiao@mail.xidian.edu.cn). Publisher Copyright: © 2008-2012 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2020/5/11

Y1 - 2020/5/11

N2 - Hyperspectral image anomaly detection is an increasingly important research topic in remote sensing images understanding and interpretation. Recently, low-rank representation-based methods have attracted extensive attention and achieved promising performances in hyperspectral anomaly detection. These methods assume that the hyperspectral data can be decomposed into two parts: the low-rank component representing the background and the residual part indicating the anomaly. In order to improve the separability of the background and anomaly, we propose a novel hyperspectral anomaly detection based on low-rank representation with dictionary construction and data-driven projection. To construct a robust dictionary that contains all categories of the background objects whilst excluding the anomaly's influence, we adopt a superpixel-based tensor low-rank decomposition method to generate a comprehensive and pure background dictionary. Considering the spectral redundancy in the hyperspectral data, data-driven projection is introduced to the low-rank representation to project the original data to a low-dimensional feature space to better separate the anomaly and the background. Experimental results on four real hyperspectral datasets show that the proposed anomaly detection method outperforms the other anomaly detectors.

AB - Hyperspectral image anomaly detection is an increasingly important research topic in remote sensing images understanding and interpretation. Recently, low-rank representation-based methods have attracted extensive attention and achieved promising performances in hyperspectral anomaly detection. These methods assume that the hyperspectral data can be decomposed into two parts: the low-rank component representing the background and the residual part indicating the anomaly. In order to improve the separability of the background and anomaly, we propose a novel hyperspectral anomaly detection based on low-rank representation with dictionary construction and data-driven projection. To construct a robust dictionary that contains all categories of the background objects whilst excluding the anomaly's influence, we adopt a superpixel-based tensor low-rank decomposition method to generate a comprehensive and pure background dictionary. Considering the spectral redundancy in the hyperspectral data, data-driven projection is introduced to the low-rank representation to project the original data to a low-dimensional feature space to better separate the anomaly and the background. Experimental results on four real hyperspectral datasets show that the proposed anomaly detection method outperforms the other anomaly detectors.

KW - Data-driven projection

KW - Hyperspectral image (hsi) anomaly detection

KW - Low-rank representation (lrr)

KW - Tensor decomposition

U2 - 10.1109/JSTARS.2020.2990457

DO - 10.1109/JSTARS.2020.2990457

M3 - Article

AN - SCOPUS:85086308813

VL - 13

SP - 2226

EP - 2239

JO - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

JF - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

SN - 1939-1404

ER -

Hyperspectral anomaly detection based on low-rank representation with data-driven projection and dictionary construction

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this