Cho, Moses AMathieu, Renaud SADebba, Pravesh2009-09-102009-09-102009-08Cho, M.A., Mathieu, R. and Debba, P. 2009. Multiple endmember spectral-angle-mapper (SAM) analysis improves discrimination of Savanna tree species. 1st Workshop on Hyperspectral Image and Signal processing: Evolution in Remote Sensing (WHISPERS), Grenoble, France, 26-28 August, 2009. pp 1-4978-1-4244-4687-2http://hdl.handle.net/10204/35751st Workshop on Hyperspectral Image and Signal processing:Evolution in Remote Sensing (WHISPERS), Grenoble, France 26-28 August 2009Differences in within-species phenology and structure driven by factors including topography, edaphic properties, and climatic variables across the landscape present important challenges to species differentiation with remote sensing. The objective of this paper was to evaluate the classification performance of a multiple-endmember spectral angle mapper (SAM) classification approach in discriminating seven common African savanna tree species and to compare the results with the traditional SAM classifier based on a single endmember per species or class. The leaf spectral reflectances of seven common tree species in the Kruger National Park, South Africa, Combretum apiculatum, Combretum hereroense, Combretum zeyheri, Gymnosporia buxifolia, Gymnosporia senegalensis, Lonchocarpus capassa and Terminalia sericea were used in this study. Discriminating species using all training spectra for each species as reference endmembers (the multiple endmember approach or more conventionally termed K-nearest neighbour classifier) yielded a higher classification accuracy of 60% compared to the conventional SAM classifier based on the mean of the training spectra for each species (overall accuracy = 44%). Further analysis using endmembers selected after cluster analysis of all the spectra for each species yielded the highest classification accuracy for the species (overall accuracy = 74%). This study underscores two important phenomena; (i) within-species spectral variability affects the discrimination of savanna tree species with the SAM classifier and (ii) the effect of within-species spectral variability can be minimised by adopting a multiple endmember approach with the SAM classifier. This study further highlights the importance of the quality of the reference endmember or spectral library.enMultiple endmember approachSpectral angle mapperSAMSavanna tree speciesSpectral variabilityHyperspectral imageSignal processingRemote sensingCombretum apiculatumCombretum hereroenseCombretum zeyheriGymnosporia buxifoliaGymnosporia senegalensisLonchocarpus capassaTerminalia sericeaConference PresentationCho, M. A., Mathieu, R. S., & Debba, P. (2009). Multiple endmember spectral-angle-mapper (SAM) analysis improves discrimination of Savanna tree species. http://hdl.handle.net/10204/3575Cho, Moses A, Renaud SA Mathieu, and Pravesh Debba. "Multiple endmember spectral-angle-mapper (SAM) analysis improves discrimination of Savanna tree species." (2009): http://hdl.handle.net/10204/3575Cho MA, Mathieu RS, Debba P, Multiple endmember spectral-angle-mapper (SAM) analysis improves discrimination of Savanna tree species; 2009. http://hdl.handle.net/10204/3575 .TY - Conference Presentation AU - Cho, Moses A AU - Mathieu, Renaud SA AU - Debba, Pravesh AB - Differences in within-species phenology and structure driven by factors including topography, edaphic properties, and climatic variables across the landscape present important challenges to species differentiation with remote sensing. The objective of this paper was to evaluate the classification performance of a multiple-endmember spectral angle mapper (SAM) classification approach in discriminating seven common African savanna tree species and to compare the results with the traditional SAM classifier based on a single endmember per species or class. The leaf spectral reflectances of seven common tree species in the Kruger National Park, South Africa, Combretum apiculatum, Combretum hereroense, Combretum zeyheri, Gymnosporia buxifolia, Gymnosporia senegalensis, Lonchocarpus capassa and Terminalia sericea were used in this study. Discriminating species using all training spectra for each species as reference endmembers (the multiple endmember approach or more conventionally termed K-nearest neighbour classifier) yielded a higher classification accuracy of 60% compared to the conventional SAM classifier based on the mean of the training spectra for each species (overall accuracy = 44%). Further analysis using endmembers selected after cluster analysis of all the spectra for each species yielded the highest classification accuracy for the species (overall accuracy = 74%). This study underscores two important phenomena; (i) within-species spectral variability affects the discrimination of savanna tree species with the SAM classifier and (ii) the effect of within-species spectral variability can be minimised by adopting a multiple endmember approach with the SAM classifier. This study further highlights the importance of the quality of the reference endmember or spectral library. DA - 2009-08 DB - ResearchSpace DP - CSIR KW - Multiple endmember approach KW - Spectral angle mapper KW - SAM KW - Savanna tree species KW - Spectral variability KW - Hyperspectral image KW - Signal processing KW - Remote sensing KW - Combretum apiculatum KW - Combretum hereroense KW - Combretum zeyheri KW - Gymnosporia buxifolia KW - Gymnosporia senegalensis KW - Lonchocarpus capassa KW - Terminalia sericea LK - https://researchspace.csir.co.za PY - 2009 SM - 978-1-4244-4687-2 T1 - Multiple endmember spectral-angle-mapper (SAM) analysis improves discrimination of Savanna tree species TI - Multiple endmember spectral-angle-mapper (SAM) analysis improves discrimination of Savanna tree species UR - http://hdl.handle.net/10204/3575 ER -