Landsat 8 vs. Landsat 5: a comparison based on urban and peri-urban land cover mappingInternational Journal of Applied Earth Observation and Geoinformation (2015)
AbstractAn image dataset from the Landsat OLI spaceborne sensor is compared with the Landsat TM in order toevaluate the excellence of the new imagery in urban landcover classification. Widely known pixel-basedand object-based image analysis methods have been implemented in this work like Maximum Likeli-hood, Support Vector Machine, k-Nearest Neighbor, Feature Analyst and Sub-pixel. Classification resultsfrom Landsat OLI provide more accurate results comparing to the Landsat TM. Object-based classifica-tions produced a more uniform result, but suffer from the absorption of small rare classes into largehomogenous areas, as a consequence of the segmentation, merging and the spatial parameters in thespatial resolution (30 m) of Landsat images. Based exclusively on the overall accuracy reports, the SVMpixel-based classification from Landsat 8 proved to be the most accurate for the purpose of mappingurban land cover, using medium spatial resolution imagery.
- Landsat 8SVMGEOBIAPeri-urbanClassification
Citation InformationPoursanidis, D., Chrysoulakis, N. and Mitraka, Z., 2015. Landsat 8 vs. Landsat 5: a comparison based on urban and peri-urban land cover mapping. International Journal of Applied Earth Observation and Geoinformation, 25, 259 - 269.