Debba, Pravesh2009-08-282009-08-282009-07Debba, P. 2009. Improving classification accuracy of spectrally similar tree species: a complex case study in the Kruger National Park. Rhodes University, South Africa, July 2009. pp 1-51http://hdl.handle.net/10204/3554This presentation was presented at Rhodes UniversityThis presentation to the SASA Eastern Cape Chapter at Rhodes University studies the variability within a species class and the variability between the species classes of seven spectrally similar tree species and presents ways in which the within-species class variability can be reduced compared to the between-species class variability. Furthermore, two classification approaches with spectral angle mapper: (i) using a spectral library composed of one spectrum (endmember) per species and (ii) a multiple endmember approach is presented, conventionally called K-nearest neighbour classifier.enTree classificationSpectral matchingKruger national parkClassification techniquesHyperspectral remote sensingIterated conditional modesICMSpectral angle mapper classifierSAMSpecies variabilityTree speciesK-nearest neighbour classifierConference PresentationDebba, P. (2009). Improving classification accuracy of spectrally similar tree species: a complex case study in the Kruger National Park. http://hdl.handle.net/10204/3554Debba, Pravesh. "Improving classification accuracy of spectrally similar tree species: a complex case study in the Kruger National Park." (2009): http://hdl.handle.net/10204/3554Debba P, Improving classification accuracy of spectrally similar tree species: a complex case study in the Kruger National Park; 2009. http://hdl.handle.net/10204/3554 .TY - Conference Presentation AU - Debba, Pravesh AB - This presentation to the SASA Eastern Cape Chapter at Rhodes University studies the variability within a species class and the variability between the species classes of seven spectrally similar tree species and presents ways in which the within-species class variability can be reduced compared to the between-species class variability. Furthermore, two classification approaches with spectral angle mapper: (i) using a spectral library composed of one spectrum (endmember) per species and (ii) a multiple endmember approach is presented, conventionally called K-nearest neighbour classifier. DA - 2009-07 DB - ResearchSpace DP - CSIR KW - Tree classification KW - Spectral matching KW - Kruger national park KW - Classification techniques KW - Hyperspectral remote sensing KW - Iterated conditional modes KW - ICM KW - Spectral angle mapper classifier KW - SAM KW - Species variability KW - Tree species KW - K-nearest neighbour classifier LK - https://researchspace.csir.co.za PY - 2009 T1 - Improving classification accuracy of spectrally similar tree species: a complex case study in the Kruger National Park TI - Improving classification accuracy of spectrally similar tree species: a complex case study in the Kruger National Park UR - http://hdl.handle.net/10204/3554 ER -