Opin vísindi

Hyperspectral Feature Extraction Using Sparse and Smooth Low-Rank Analysis

Hyperspectral Feature Extraction Using Sparse and Smooth Low-Rank Analysis

Title: Hyperspectral Feature Extraction Using Sparse and Smooth Low-Rank Analysis
Author: Rasti, Behnood   orcid.org/0000-0002-1091-9841
Ghamisi, Pedram   orcid.org/0000-0003-1203-741X
Ulfarsson, Magnus   orcid.org/0000-0002-0461-040X
Date: 2019-01-10
Language: English
Scope: 121
University/Institute: Háskóli Íslands
University of Iceland
School: Verkfræði- og náttúruvísindasvið (HÍ)
School of Engineering and Natural Sciences (UI)
Department: Rafmagns- og tölvuverkfræðideild (HÍ)
Faculty of Electrical and Computer Engineering (UI)
Series: Remote Sensing;11(2)
ISSN: 2072-4292
DOI: 10.3390/rs11020121
Subject: Classification; Constrained penalized cost function; Feature extraction; Hyperspectral image; Low-rank; Smooth features; Sparse features; Total variation; Myndgreining (upplýsingatækni); Litrófsgreining
URI: https://hdl.handle.net/20.500.11815/2112

Show full item record


Rasti, B.; Ghamisi, P.; Ulfarsson, M.O. Hyperspectral Feature Extraction Using Sparse and Smooth Low-Rank Analysis. Remote Sens. 2019, 11, 121.


In this paper, we develop a hyperspectral feature extraction method called sparse and smooth low-rank analysis (SSLRA). First, we propose a new low-rank model for hyperspectral images (HSIs) where we decompose the HSI into smooth and sparse components. Then, these components are simultaneously estimated using a nonconvex constrained penalized cost function (CPCF). The proposed CPCF exploits total variation penalty, ℓ 1 penalty, and an orthogonality constraint. The total variation penalty is used to promote piecewise smoothness, and, therefore, it extracts spatial (local neighborhood) information. The ℓ 1 penalty encourages sparse and spatial structures. Additionally, we show that this new type of decomposition improves the classification of the HSIs. In the experiments, SSLRA was applied on the Houston (urban) and the Trento (rural) datasets. The extracted features were used as an input into a classifier (either support vector machines (SVM) or random forest (RF)) to produce the final classification map. The results confirm improvement in classification accuracy compared to the state-of-the-art feature extraction approaches.


Publisher's version (útgefin grein)


This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited

Files in this item

This item appears in the following Collection(s)