Sparse and Low-Rank Matrix Decomposition for Automatic Target Detection in Hyperspectral Imagery

Given a target prior information, our goal is to propose a method for automatically separating targets of interests from the background in hyperspectral imagery. More precisely, we regard the given hyperspectral image (HSI) as being made up of the sum of low-rank background HSI and a sparse target H...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on geoscience and remote sensing Vol. 57; no. 8; pp. 5239 - 5251
Main Authors Bitar, Ahmad W., Cheong, Loong-Fah, Ovarlez, Jean-Philippe
Format Journal Article
LanguageEnglish
Published New York IEEE 01.08.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Institute of Electrical and Electronics Engineers
Subjects
Atmospheric measurements
Detection
Detectors
Dictionaries
Engineering Sciences
Hyperspectral imaging
Hyperspectral target detection
Image detection
Imagery
low-rank background hyperspectral image (HSI)
Object detection
Physics
Shape
sparse target HSI
Target detection
Target recognition
target separation
HYPERSPECTRAL TARGET DETECTION
SPARSE TARGET HSI
DETECTION DE CIBLES EN IMAGERIE HYPERSPECTRALE
PARCIMONIE
LOW-RANK BACKGROUND HYPERSPECTRAL IMAGE (HSI)
TARGET SEPARATION
FOND HYPERSPECTRAL RANG FAIBLE
Online AccessGet full text

Cover

More Information
Summary:Given a target prior information, our goal is to propose a method for automatically separating targets of interests from the background in hyperspectral imagery. More precisely, we regard the given hyperspectral image (HSI) as being made up of the sum of low-rank background HSI and a sparse target HSI that contains the targets based on a prelearned target dictionary constructed from some online spectral libraries. Based on the proposed method, two strategies are briefly outlined and evaluated to realize the target detection on both synthetic and real experiments.
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2019.2897635