Discrimination of blackberry (Rubus fruticosus sp. agg.)using hyperspectral imagery in Kosciuszko National Park, NSW, Australia

Remy Dehaan, John Louis, Andrea Wilson, Andrew Hall, Rod Rumbachs

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Blackberry, Rubus fruticosus sp. agg., is a perennial, semi-deciduous shrub which forms dense thickets that infest approximately 8.8 million ha of land in Australia. It is highly invasive with a high potential for spread, and causes significant negative economic and environmental impacts. During 2004, HyMap hyperspectral imagery was acquired across the foreshores of Blowering Dam in Kosciuszko National Park, NSW, Australia to evaluate its utility for mapping the distribution of blackberry.Strategies for mapping image-derived blackberry spectra using hyperspectral imagery were assessed using Spectral Angle Mapper,Spectral Feature Fitting, Matched Filter, and Mixture-Tuned Matched Filter mapping algorithms. A Mixture-Tuned Matched Filter(MTMF) approach using the blackberry spectrum with a restricted wavelength range was adopted. MTMF distribution maps showed the highest agreement to the distribution of blackberry as assessed using an error matrix and independent groundtruth data.The MTMF distribution map generated a producer's accuracy of 91%, user's accuracy of 81%, overall accuracy of 92% and a Kappa coefficient of 0.715. This study has demonstrated that hyperspectral imagery can effectively quantify the distribution of blackberry in open canopies.
Original languageEnglish
Pages (from-to)13-24
Number of pages12
JournalISPRS Journal of Photogrammetry and Remote Sensing
Volume62
Issue number1
DOIs
Publication statusPublished - May 2007

Fingerprint

national parks
matched filters
Matched filters
imagery
discrimination
national park
filter
economic impact
dams
canopies
Dams
Environmental impact
shrub
environmental impact
dam
distribution
canopy
wavelength
Wavelength
Economics

Cite this

@article{089a4e6d83044ea7b78ec151f0dce114,
title = "Discrimination of blackberry (Rubus fruticosus sp. agg.)using hyperspectral imagery in Kosciuszko National Park, NSW, Australia",
abstract = "Blackberry, Rubus fruticosus sp. agg., is a perennial, semi-deciduous shrub which forms dense thickets that infest approximately 8.8 million ha of land in Australia. It is highly invasive with a high potential for spread, and causes significant negative economic and environmental impacts. During 2004, HyMap hyperspectral imagery was acquired across the foreshores of Blowering Dam in Kosciuszko National Park, NSW, Australia to evaluate its utility for mapping the distribution of blackberry.Strategies for mapping image-derived blackberry spectra using hyperspectral imagery were assessed using Spectral Angle Mapper,Spectral Feature Fitting, Matched Filter, and Mixture-Tuned Matched Filter mapping algorithms. A Mixture-Tuned Matched Filter(MTMF) approach using the blackberry spectrum with a restricted wavelength range was adopted. MTMF distribution maps showed the highest agreement to the distribution of blackberry as assessed using an error matrix and independent groundtruth data.The MTMF distribution map generated a producer's accuracy of 91{\%}, user's accuracy of 81{\%}, overall accuracy of 92{\%} and a Kappa coefficient of 0.715. This study has demonstrated that hyperspectral imagery can effectively quantify the distribution of blackberry in open canopies.",
keywords = "Blackberry, Ecosystem management, Hyperspectral imagery, Weeds",
author = "Remy Dehaan and John Louis and Andrea Wilson and Andrew Hall and Rod Rumbachs",
note = "Imported on 12 Apr 2017 - DigiTool details were: month (773h) = May 2007; Journal title (773t) = ISPRS Journal of Photogrammetry and Remote Sensing. ISSNs: 0924-2716;",
year = "2007",
month = "5",
doi = "10.1016/j.isprsjprs.2007.01.004",
language = "English",
volume = "62",
pages = "13--24",
journal = "Photogrammetria",
issn = "0924-2716",
publisher = "Elsevier",
number = "1",

}

Discrimination of blackberry (Rubus fruticosus sp. agg.)using hyperspectral imagery in Kosciuszko National Park, NSW, Australia. / Dehaan, Remy; Louis, John; Wilson, Andrea; Hall, Andrew; Rumbachs, Rod.

In: ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 62, No. 1, 05.2007, p. 13-24.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Discrimination of blackberry (Rubus fruticosus sp. agg.)using hyperspectral imagery in Kosciuszko National Park, NSW, Australia

AU - Dehaan, Remy

AU - Louis, John

AU - Wilson, Andrea

AU - Hall, Andrew

AU - Rumbachs, Rod

N1 - Imported on 12 Apr 2017 - DigiTool details were: month (773h) = May 2007; Journal title (773t) = ISPRS Journal of Photogrammetry and Remote Sensing. ISSNs: 0924-2716;

PY - 2007/5

Y1 - 2007/5

N2 - Blackberry, Rubus fruticosus sp. agg., is a perennial, semi-deciduous shrub which forms dense thickets that infest approximately 8.8 million ha of land in Australia. It is highly invasive with a high potential for spread, and causes significant negative economic and environmental impacts. During 2004, HyMap hyperspectral imagery was acquired across the foreshores of Blowering Dam in Kosciuszko National Park, NSW, Australia to evaluate its utility for mapping the distribution of blackberry.Strategies for mapping image-derived blackberry spectra using hyperspectral imagery were assessed using Spectral Angle Mapper,Spectral Feature Fitting, Matched Filter, and Mixture-Tuned Matched Filter mapping algorithms. A Mixture-Tuned Matched Filter(MTMF) approach using the blackberry spectrum with a restricted wavelength range was adopted. MTMF distribution maps showed the highest agreement to the distribution of blackberry as assessed using an error matrix and independent groundtruth data.The MTMF distribution map generated a producer's accuracy of 91%, user's accuracy of 81%, overall accuracy of 92% and a Kappa coefficient of 0.715. This study has demonstrated that hyperspectral imagery can effectively quantify the distribution of blackberry in open canopies.

AB - Blackberry, Rubus fruticosus sp. agg., is a perennial, semi-deciduous shrub which forms dense thickets that infest approximately 8.8 million ha of land in Australia. It is highly invasive with a high potential for spread, and causes significant negative economic and environmental impacts. During 2004, HyMap hyperspectral imagery was acquired across the foreshores of Blowering Dam in Kosciuszko National Park, NSW, Australia to evaluate its utility for mapping the distribution of blackberry.Strategies for mapping image-derived blackberry spectra using hyperspectral imagery were assessed using Spectral Angle Mapper,Spectral Feature Fitting, Matched Filter, and Mixture-Tuned Matched Filter mapping algorithms. A Mixture-Tuned Matched Filter(MTMF) approach using the blackberry spectrum with a restricted wavelength range was adopted. MTMF distribution maps showed the highest agreement to the distribution of blackberry as assessed using an error matrix and independent groundtruth data.The MTMF distribution map generated a producer's accuracy of 91%, user's accuracy of 81%, overall accuracy of 92% and a Kappa coefficient of 0.715. This study has demonstrated that hyperspectral imagery can effectively quantify the distribution of blackberry in open canopies.

KW - Blackberry

KW - Ecosystem management

KW - Hyperspectral imagery

KW - Weeds

U2 - 10.1016/j.isprsjprs.2007.01.004

DO - 10.1016/j.isprsjprs.2007.01.004

M3 - Article

VL - 62

SP - 13

EP - 24

JO - Photogrammetria

JF - Photogrammetria

SN - 0924-2716

IS - 1

ER -