Please use this identifier to cite or link to this item: https://hdl.handle.net/1959.11/15641
Title: Improving image classification in a complex wetland ecosystem through image fusion techniques
Contributor(s): Kumar, Lalit  (author)orcid ; Sinha, Priyakant  (author); Taylor, Subhashni  (author)orcid 
Publication Date: 2014
DOI: 10.1117/1.JRS.8.083616
Handle Link: https://hdl.handle.net/1959.11/15641
Abstract: The aim of this study was to evaluate the impact of image fusion techniques on vegetation classification accuracies in a complex wetland system. Fusion of panchromatic (PAN) and multispectral (MS) Quickbird satellite imagery was undertaken using four image fusion techniques: Brovey, hue-saturation-value (HSV), principal components (PC), and Gram-Schmidt (GS) spectral sharpening. These four fusion techniques were compared in terms of their mapping accuracy to a normal MS image using maximum-likelihood classification (MLC) and support vector machine (SVM) methods. Gram-Schmidt fusion technique yielded the highest overall accuracy and kappa value with both MLC (67.5% and 0.63, respectively) and SVM methods (73.3% and 0.68, respectively). This compared favorably with the accuracies achieved using the MS image. Overall, improvements of 4.1%, 3.6%, 5.8%, 5.4%, and 7.2% in overall accuracies were obtained in case of SVM over MLC for Brovey, HSV, GS, PC, and MS images, respectively. Visual and statistical analyses of the fused images showed that the Gram-Schmidt spectral sharpening technique preserved spectral quality much better than the principal component, Brovey, and HSV fused images. Other factors, such as the growth stage of species and the presence of extensive background water in many parts of the study area, had an impact on classification accuracies.
Publication Type: Journal Article
Source of Publication: Journal of Applied Remote Sensing, 8(1), p. 083616-1-083616-16
Publisher: International Society for Optical Engineering (SPIE)
Place of Publication: United States of America
ISSN: 1931-3195
Fields of Research (FoR) 2008: 090903 Geospatial Information Systems
090905 Photogrammetry and Remote Sensing
050209 Natural Resource Management
Fields of Research (FoR) 2020: 401302 Geospatial information systems and geospatial data modelling
401304 Photogrammetry and remote sensing
410406 Natural resource management
Socio-Economic Objective (SEO) 2008: 960802 Coastal and Estuarine Flora, Fauna and Biodiversity
960604 Environmental Management Systems
960503 Ecosystem Assessment and Management of Coastal and Estuarine Environments
Socio-Economic Objective (SEO) 2020: 180203 Coastal or estuarine biodiversity
189999 Other environmental management not elsewhere classified
180601 Assessment and management of terrestrial ecosystems
Peer Reviewed: Yes
HERDC Category Description: C1 Refereed Article in a Scholarly Journal
Appears in Collections:Journal Article
School of Environmental and Rural Science

Files in This Item:
2 files
File Description SizeFormat 
Show full item record

SCOPUSTM   
Citations

31
checked on Mar 2, 2024

Page view(s)

1,674
checked on Mar 17, 2024
Google Media

Google ScholarTM

Check

Altmetric


Items in Research UNE are protected by copyright, with all rights reserved, unless otherwise indicated.