Spectral-spatial approaches for hyperspectral data classification

Simple item page
dc.contributor.authorRoy, Sathi
dc.contributor.authorUniversity of Lethbridge. Faculty of Arts and Science
dc.contributor.supervisorCheng, Howard
dc.contributor.supervisorStaenz, Karl
dc.date.accessioned2015-09-30T04:02:37Z
dc.date.available2015-09-30T04:02:37Z
dc.date.issued2014
dc.degree.levelMastersen_US
dc.description.abstractClassification of hyperspectral data is very challenging and mapping of land cover is one of its applications. Improving the classification accuracy and computation time of hyperspectral data were achieved incorporating contextual information in combination with spectral information for correcting classification errors along class boundaries and within class. In the proposed method, the original hyperspectral image was first classified using the Support Vector Machine (SVM) classifier, followed by the Markov Random Field (MRF) approach applied to the boundary areas and Unsupervised Extraction and Classification of Homogeneous Objects (UnECHO) classifier used for the interior parts of regions to produce the final classification map. In this study two agricultural (Hyperion and AVIRIS) and one urban (ROSIS) datasets were used. Investigations of the spectral and various contextual approaches including feature reduction show that the SVM-MRF method with grid search works best for all of the datasets. The highest overall accuracy of 97.35% was achieved for the urban dataset.en_US
dc.description.sponsorshipNatural Sciences and Engineering Research Council of Canada (NSERC) and the University of Lethbridge.en_US
dc.embargoNoen_US
dc.identifier.urihttps://hdl.handle.net/10133/3757
dc.language.isoen_CAen_US
dc.proquest.subject0984en_US
dc.proquest.subject0799en_US
dc.proquest.subject0366en_US
dc.proquestyesYesen_US
dc.publisherLethbridge, Alta. : University of Lethbridge, Dept. of Mathematics and Computer Scienceen_US
dc.publisher.departmentDepartment of Mathematics and Computer Scienceen_US
dc.publisher.facultyArts and Scienceen_US
dc.relation.ispartofseriesThesis (University of Lethbridge. Faculty of Arts and Science)en_US
dc.subjectSpectral-Spatial Classificationen_US
dc.subjectImage Classificationen_US
dc.subjectSupport Vector Machine (SVM)en_US
dc.subjectMarkov Random Field (MRF)en_US
dc.subjectUnsupervised Extraction and Classification for Homogenous Objects (UnECHO)en_US
dc.subjectSVM-Recursive Feature Elimination (SVM-RFE)en_US
dc.subjectCorrelation based Feature Selection (CFS)en_US
dc.subjectMinimum-Redundancy–Maximum-Relevance (mRMR)en_US
dc.subjectRemote Sensingen_US
dc.subjectErosion Techniqueen_US
dc.subjectGrid Searchen_US
dc.titleSpectral-spatial approaches for hyperspectral data classificationen_US
dc.typeThesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ROY_SATHI_MSC_2014.pdf
Size:
11.07 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Arts and Science, Faculty of
University of Lethbridge Theses