Hyperspectral anomaly detection using background learning and structured sparse representation

Fei Li; Yanning Zhang; Lei Zhang; Xiuwei Zhang; Dongmei Jiang

doi:10.1109/IGARSS.2016.7729413

Hyperspectral anomaly detection using background learning and structured sparse representation

Fei Li, Yanning Zhang, Lei Zhang, Xiuwei Zhang, Dongmei Jiang

School of Computer Science

Northwestern Polytechnical University Xian

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Scopus citations

Abstract

A novel background dictionary learning and structured sparse representation based anomaly detection method is proposed for hyperspectral imagery. First, a robust PCA spectrum dictionary is learned from the plausible background area detected by the local RX detector. With the learned dictionary, the reweighted Laplace prior based structured sparse representation model is then employed to reconstruct the spectrum of each pixel in the image. Due to considering the structured sparsity in representation, the background spectra can be reconstructed more accurately than anomaly ones. Thus, reconstruction error is utilized to separate the anomaly pixels and background ones. Experimental results on both simulated and real-world datasets demonstrate that the proposed method outperforms several state-of-the-art hyperspectral anomaly detection methods.

Original language	English
Title of host publication	2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1618-1621
Number of pages	4
ISBN (Electronic)	9781509033324
DOIs	https://doi.org/10.1109/IGARSS.2016.7729413
State	Published - 1 Nov 2016
Event	36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Beijing, China Duration: 10 Jul 2016 → 15 Jul 2016

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2016-November

Conference

Conference	36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016
Country/Territory	China
City	Beijing
Period	10/07/16 → 15/07/16

Keywords

Anomaly detection
dictionary learning
reweighted Laplace prior
structured sparse representation

Access to Document

10.1109/IGARSS.2016.7729413

Cite this

Li, F., Zhang, Y., Zhang, L., Zhang, X., & Jiang, D. (2016). Hyperspectral anomaly detection using background learning and structured sparse representation. In 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings (pp. 1618-1621). Article 7729413 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2016-November). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2016.7729413

Li, Fei ; Zhang, Yanning ; Zhang, Lei et al. / Hyperspectral anomaly detection using background learning and structured sparse representation. 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1618-1621 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{8c748e63d4ad4273a94c233791591ed3,

title = "Hyperspectral anomaly detection using background learning and structured sparse representation",

abstract = "A novel background dictionary learning and structured sparse representation based anomaly detection method is proposed for hyperspectral imagery. First, a robust PCA spectrum dictionary is learned from the plausible background area detected by the local RX detector. With the learned dictionary, the reweighted Laplace prior based structured sparse representation model is then employed to reconstruct the spectrum of each pixel in the image. Due to considering the structured sparsity in representation, the background spectra can be reconstructed more accurately than anomaly ones. Thus, reconstruction error is utilized to separate the anomaly pixels and background ones. Experimental results on both simulated and real-world datasets demonstrate that the proposed method outperforms several state-of-the-art hyperspectral anomaly detection methods.",

keywords = "Anomaly detection, dictionary learning, reweighted Laplace prior, structured sparse representation",

author = "Fei Li and Yanning Zhang and Lei Zhang and Xiuwei Zhang and Dongmei Jiang",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 ; Conference date: 10-07-2016 Through 15-07-2016",

year = "2016",

month = nov,

day = "1",

doi = "10.1109/IGARSS.2016.7729413",

language = "英语",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

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

pages = "1618--1621",

booktitle = "2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings",

}

Li, F, Zhang, Y , Zhang, L, Zhang, X & Jiang, D 2016, Hyperspectral anomaly detection using background learning and structured sparse representation. in 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings., 7729413, International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2016-November, Institute of Electrical and Electronics Engineers Inc., pp. 1618-1621, 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016, Beijing, China, 10/07/16. https://doi.org/10.1109/IGARSS.2016.7729413

Hyperspectral anomaly detection using background learning and structured sparse representation. / Li, Fei; Zhang, Yanning ; Zhang, Lei et al.
2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1618-1621 7729413 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2016-November).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Hyperspectral anomaly detection using background learning and structured sparse representation

AU - Li, Fei

AU - Zhang, Yanning

AU - Zhang, Lei

AU - Zhang, Xiuwei

AU - Jiang, Dongmei

PY - 2016/11/1

Y1 - 2016/11/1

N2 - A novel background dictionary learning and structured sparse representation based anomaly detection method is proposed for hyperspectral imagery. First, a robust PCA spectrum dictionary is learned from the plausible background area detected by the local RX detector. With the learned dictionary, the reweighted Laplace prior based structured sparse representation model is then employed to reconstruct the spectrum of each pixel in the image. Due to considering the structured sparsity in representation, the background spectra can be reconstructed more accurately than anomaly ones. Thus, reconstruction error is utilized to separate the anomaly pixels and background ones. Experimental results on both simulated and real-world datasets demonstrate that the proposed method outperforms several state-of-the-art hyperspectral anomaly detection methods.

AB - A novel background dictionary learning and structured sparse representation based anomaly detection method is proposed for hyperspectral imagery. First, a robust PCA spectrum dictionary is learned from the plausible background area detected by the local RX detector. With the learned dictionary, the reweighted Laplace prior based structured sparse representation model is then employed to reconstruct the spectrum of each pixel in the image. Due to considering the structured sparsity in representation, the background spectra can be reconstructed more accurately than anomaly ones. Thus, reconstruction error is utilized to separate the anomaly pixels and background ones. Experimental results on both simulated and real-world datasets demonstrate that the proposed method outperforms several state-of-the-art hyperspectral anomaly detection methods.

KW - Anomaly detection

KW - dictionary learning

KW - reweighted Laplace prior

KW - structured sparse representation

UR - http://www.scopus.com/inward/record.url?scp=85007478279&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2016.7729413

DO - 10.1109/IGARSS.2016.7729413

M3 - 会议稿件

AN - SCOPUS:85007478279

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 1618

EP - 1621

BT - 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016

Y2 - 10 July 2016 through 15 July 2016

ER -

Li F, Zhang Y , Zhang L, Zhang X, Jiang D. Hyperspectral anomaly detection using background learning and structured sparse representation. In 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1618-1621. 7729413. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS.2016.7729413

Hyperspectral anomaly detection using background learning and structured sparse representation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this