A Fast Hyperplane-Based Minimum-Volume Enclosing Simplex Algorithm for Blind Hyperspectral Unmixing

Chia Hsiang Lin, Chong Yung Chi, Yu Hsiang Wang, Tsung Han Chan

研究成果: Article

22 引文 (Scopus)

摘要

Hyperspectral unmixing (HU) is a crucial signal processing procedure to identify the underlying materials (or endmembers) and their corresponding proportions (or abundances) from an observed hyperspectral scene. A well-known blind HU criterion, advocated by Craig during the early 1990s, considers the vertices of the minimum-volume enclosing simplex of the data cloud as good endmember estimates, and it has been empirically and theoretically found effective even in the scenario of no pure pixels. However, such kinds of algorithms may suffer from heavy simplex volume computations in numerical optimization, etc. In this paper, without involving any simplex volume computations, by exploiting a convex geometry fact that a simplest simplex of N vertices can be defined by N associated hyperplanes, we propose a fast blind HU algorithm, for which each of the N hyperplanes associated with the Craig's simplex of N vertices is constructed from N-1 affinely independent data pixels, together with an endmember identifiability analysis for its performance support. Without resorting to numerical optimization, the devised algorithm searches for the N(N-1) active data pixels via simple linear algebraic computations, accounting for its computational efficiency. Monte Carlo simulations and real data experiments are provided to demonstrate its superior efficacy over some benchmark Craig-criterion-based algorithms in both computational efficiency and estimation accuracy.

原文English
文章編號7355384
頁(從 - 到)1946-1961
頁數16
期刊IEEE Transactions on Signal Processing
64
發行號8
DOIs
出版狀態Published - 2016 四月 15

指紋

Pixels
Computational efficiency
Signal processing
Geometry
Experiments
Monte Carlo simulation

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering

引用此文

Lin, Chia Hsiang ; Chi, Chong Yung ; Wang, Yu Hsiang ; Chan, Tsung Han. / A Fast Hyperplane-Based Minimum-Volume Enclosing Simplex Algorithm for Blind Hyperspectral Unmixing. 於: IEEE Transactions on Signal Processing. 2016 ; 卷 64, 編號 8. 頁 1946-1961.
@article{d98c9126404e4664b1b840a72c2588cd,
title = "A Fast Hyperplane-Based Minimum-Volume Enclosing Simplex Algorithm for Blind Hyperspectral Unmixing",
abstract = "Hyperspectral unmixing (HU) is a crucial signal processing procedure to identify the underlying materials (or endmembers) and their corresponding proportions (or abundances) from an observed hyperspectral scene. A well-known blind HU criterion, advocated by Craig during the early 1990s, considers the vertices of the minimum-volume enclosing simplex of the data cloud as good endmember estimates, and it has been empirically and theoretically found effective even in the scenario of no pure pixels. However, such kinds of algorithms may suffer from heavy simplex volume computations in numerical optimization, etc. In this paper, without involving any simplex volume computations, by exploiting a convex geometry fact that a simplest simplex of N vertices can be defined by N associated hyperplanes, we propose a fast blind HU algorithm, for which each of the N hyperplanes associated with the Craig's simplex of N vertices is constructed from N-1 affinely independent data pixels, together with an endmember identifiability analysis for its performance support. Without resorting to numerical optimization, the devised algorithm searches for the N(N-1) active data pixels via simple linear algebraic computations, accounting for its computational efficiency. Monte Carlo simulations and real data experiments are provided to demonstrate its superior efficacy over some benchmark Craig-criterion-based algorithms in both computational efficiency and estimation accuracy.",
author = "Lin, {Chia Hsiang} and Chi, {Chong Yung} and Wang, {Yu Hsiang} and Chan, {Tsung Han}",
year = "2016",
month = "4",
day = "15",
doi = "10.1109/TSP.2015.2508778",
language = "English",
volume = "64",
pages = "1946--1961",
journal = "IEEE Transactions on Signal Processing",
issn = "1053-587X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "8",

}

A Fast Hyperplane-Based Minimum-Volume Enclosing Simplex Algorithm for Blind Hyperspectral Unmixing. / Lin, Chia Hsiang; Chi, Chong Yung; Wang, Yu Hsiang; Chan, Tsung Han.

於: IEEE Transactions on Signal Processing, 卷 64, 編號 8, 7355384, 15.04.2016, p. 1946-1961.

研究成果: Article

TY - JOUR

T1 - A Fast Hyperplane-Based Minimum-Volume Enclosing Simplex Algorithm for Blind Hyperspectral Unmixing

AU - Lin, Chia Hsiang

AU - Chi, Chong Yung

AU - Wang, Yu Hsiang

AU - Chan, Tsung Han

PY - 2016/4/15

Y1 - 2016/4/15

N2 - Hyperspectral unmixing (HU) is a crucial signal processing procedure to identify the underlying materials (or endmembers) and their corresponding proportions (or abundances) from an observed hyperspectral scene. A well-known blind HU criterion, advocated by Craig during the early 1990s, considers the vertices of the minimum-volume enclosing simplex of the data cloud as good endmember estimates, and it has been empirically and theoretically found effective even in the scenario of no pure pixels. However, such kinds of algorithms may suffer from heavy simplex volume computations in numerical optimization, etc. In this paper, without involving any simplex volume computations, by exploiting a convex geometry fact that a simplest simplex of N vertices can be defined by N associated hyperplanes, we propose a fast blind HU algorithm, for which each of the N hyperplanes associated with the Craig's simplex of N vertices is constructed from N-1 affinely independent data pixels, together with an endmember identifiability analysis for its performance support. Without resorting to numerical optimization, the devised algorithm searches for the N(N-1) active data pixels via simple linear algebraic computations, accounting for its computational efficiency. Monte Carlo simulations and real data experiments are provided to demonstrate its superior efficacy over some benchmark Craig-criterion-based algorithms in both computational efficiency and estimation accuracy.

AB - Hyperspectral unmixing (HU) is a crucial signal processing procedure to identify the underlying materials (or endmembers) and their corresponding proportions (or abundances) from an observed hyperspectral scene. A well-known blind HU criterion, advocated by Craig during the early 1990s, considers the vertices of the minimum-volume enclosing simplex of the data cloud as good endmember estimates, and it has been empirically and theoretically found effective even in the scenario of no pure pixels. However, such kinds of algorithms may suffer from heavy simplex volume computations in numerical optimization, etc. In this paper, without involving any simplex volume computations, by exploiting a convex geometry fact that a simplest simplex of N vertices can be defined by N associated hyperplanes, we propose a fast blind HU algorithm, for which each of the N hyperplanes associated with the Craig's simplex of N vertices is constructed from N-1 affinely independent data pixels, together with an endmember identifiability analysis for its performance support. Without resorting to numerical optimization, the devised algorithm searches for the N(N-1) active data pixels via simple linear algebraic computations, accounting for its computational efficiency. Monte Carlo simulations and real data experiments are provided to demonstrate its superior efficacy over some benchmark Craig-criterion-based algorithms in both computational efficiency and estimation accuracy.

UR - http://www.scopus.com/inward/record.url?scp=84963757025&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963757025&partnerID=8YFLogxK

U2 - 10.1109/TSP.2015.2508778

DO - 10.1109/TSP.2015.2508778

M3 - Article

AN - SCOPUS:84963757025

VL - 64

SP - 1946

EP - 1961

JO - IEEE Transactions on Signal Processing

JF - IEEE Transactions on Signal Processing

SN - 1053-587X

IS - 8

M1 - 7355384

ER -