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 journalArticlepeer-review

3 Citations (Scopus)

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 languageEnglish
Pages (from-to)2226-2239
Number of pages14
JournalIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Volume13
DOIs
Publication statusPublished - 11 May 2020
Externally publishedYes

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

Fingerprint Dive into the research topics of 'Hyperspectral anomaly detection based on low-rank representation with data-driven projection and dictionary construction'. Together they form a unique fingerprint.

Cite this