Hyperspectral Anomaly Detection Based on Low-Rank Representation and Learned Dictionary
In this paper, a novel hyperspectral anomaly detector based on low-rank representation (LRR) and learned dictionary (LD) has been proposed. This method assumes that a two-dimensional matrix transformed from a three-dimensional hyperspectral imagery can be decomposed into two parts: a low rank matrix...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2016-03-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | http://www.mdpi.com/2072-4292/8/4/289 |
id |
doaj-1d1c10f0f8944ab98c6def431e075a3d |
---|---|
record_format |
Article |
spelling |
doaj-1d1c10f0f8944ab98c6def431e075a3d2020-11-24T23:21:34ZengMDPI AGRemote Sensing2072-42922016-03-018428910.3390/rs8040289rs8040289Hyperspectral Anomaly Detection Based on Low-Rank Representation and Learned DictionaryYubin Niu0Bin Wang1Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaKey Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaIn this paper, a novel hyperspectral anomaly detector based on low-rank representation (LRR) and learned dictionary (LD) has been proposed. This method assumes that a two-dimensional matrix transformed from a three-dimensional hyperspectral imagery can be decomposed into two parts: a low rank matrix representing the background and a sparse matrix standing for the anomalies. The direct application of LRR model is sensitive to a tradeoff parameter that balances the two parts. To mitigate this problem, a learned dictionary is introduced into the decomposition process. The dictionary is learned from the whole image with a random selection process and therefore can be viewed as the spectra of the background only. It also requires a less computational cost with the learned dictionary. The statistic characteristic of the sparse matrix allows the application of basic anomaly detection method to obtain detection results. Experimental results demonstrate that, compared to other anomaly detection methods, the proposed method based on LRR and LD shows its robustness and has a satisfactory anomaly detection result.http://www.mdpi.com/2072-4292/8/4/289hyperspectral imageryanomaly detectionlow-rank matrix decompositionlearned dictionaryrobust PCAlow-rank representation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yubin Niu Bin Wang |
spellingShingle |
Yubin Niu Bin Wang Hyperspectral Anomaly Detection Based on Low-Rank Representation and Learned Dictionary Remote Sensing hyperspectral imagery anomaly detection low-rank matrix decomposition learned dictionary robust PCA low-rank representation |
author_facet |
Yubin Niu Bin Wang |
author_sort |
Yubin Niu |
title |
Hyperspectral Anomaly Detection Based on Low-Rank Representation and Learned Dictionary |
title_short |
Hyperspectral Anomaly Detection Based on Low-Rank Representation and Learned Dictionary |
title_full |
Hyperspectral Anomaly Detection Based on Low-Rank Representation and Learned Dictionary |
title_fullStr |
Hyperspectral Anomaly Detection Based on Low-Rank Representation and Learned Dictionary |
title_full_unstemmed |
Hyperspectral Anomaly Detection Based on Low-Rank Representation and Learned Dictionary |
title_sort |
hyperspectral anomaly detection based on low-rank representation and learned dictionary |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2016-03-01 |
description |
In this paper, a novel hyperspectral anomaly detector based on low-rank representation (LRR) and learned dictionary (LD) has been proposed. This method assumes that a two-dimensional matrix transformed from a three-dimensional hyperspectral imagery can be decomposed into two parts: a low rank matrix representing the background and a sparse matrix standing for the anomalies. The direct application of LRR model is sensitive to a tradeoff parameter that balances the two parts. To mitigate this problem, a learned dictionary is introduced into the decomposition process. The dictionary is learned from the whole image with a random selection process and therefore can be viewed as the spectra of the background only. It also requires a less computational cost with the learned dictionary. The statistic characteristic of the sparse matrix allows the application of basic anomaly detection method to obtain detection results. Experimental results demonstrate that, compared to other anomaly detection methods, the proposed method based on LRR and LD shows its robustness and has a satisfactory anomaly detection result. |
topic |
hyperspectral imagery anomaly detection low-rank matrix decomposition learned dictionary robust PCA low-rank representation |
url |
http://www.mdpi.com/2072-4292/8/4/289 |
work_keys_str_mv |
AT yubinniu hyperspectralanomalydetectionbasedonlowrankrepresentationandlearneddictionary AT binwang hyperspectralanomalydetectionbasedonlowrankrepresentationandlearneddictionary |
_version_ |
1725571234155986944 |