Tree species classification using support vector machine on hyperspectral images
Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesisAlternative title
Trädslagsklassificering med en stödvektormaskin på hyperspektrala bilder (Swedish)
For several years, FORAN Remote Sensing in Linköping has been using pulseintense laser scannings together with multispectral imaging for developing analysismethods in forestry. One area these laser scannings and images are used for is toclassify the species of single trees in forests. The species have been divided intopine, spruce and deciduous trees, classified by a Maximum Likelihood classifier.This thesis presents the work done on a more spectrally high-resolution imagery,hyperspectral images. These images are divided into more, and finer gradedspectral components, but demand more signal processing. A new classifier, SupportVector Machine, is tested against the previously used Maximum LikelihoodClassifier, to see if it is possible to increase the performance. The classifiers arealso set to divide the deciduous trees into aspen, birch, black alder and gray alder.The thesis shows how the new data set is handled and processed to the differentclassifiers, and shows how a better result can be achieved using a Support VectorMachine.
Place, publisher, year, edition, pages
2010. , 38 p.
remote sensing, classification, support vector machine, maximum likelihood, principal component analysis, t-test, hyperspectral, multispectral
IdentifiersURN: urn:nbn:se:liu:diva-54648ISRN: LiTH-ISY-EX - - 10/4214 - - SEOAI: oai:DiVA.org:liu-54648DiVA: diva2:321942
2010-02-17, Glashuset, 15:15 (Swedish)
Skoglar, Per, Doktorand
Gustafsson, Fredrik, Professor