Exjobbsförslag från företag

Detta är ett uppsatsförslag hämtat från Nationella Exjobb-poolen. Klicka här för att komma tillbaka till samtliga exjobbsförslag.

Förslaget inkom 2006-06-01

Comparison of soft classification techniques for identification of different types of deciduous forest in Landsat remote sensing data

OBS! ANSÖKNINGSTIDEN FÖR DETTA EXJOBB HAR LÖPT UT.
One of the uses of multispectral satellite data is landcover mapping through classification. While hard classifiers make definitive decisions about the landcover class to which any pixel belongs, soft classification techniques consider the uncertainties inherent in the reflectance data, resulting in statements of the degree to which each pixel belongs to each of the landcover class. Different soft classification techniques are available in GIS Idrisi32, depending on the logic by which uncertainty is specified - Bayesian, Dempster-Shafer, and Fuzzy Sets. There is however no optimal classifier that suits all tasks. This project aims to study several soft classification techniques and compare their results for identification of specific types of forest in Landsat data over Stockholm area. The target class is so-called selected valuable broadleaved forest (SVBF). These trees have a specific signature in the remote sensing data, and the reflectance seems also to vary with other parameters such as density of the stand. Forest inventory data will be used to locate the broadleaved forest stands and the spectral signature of the corresponding pixels in Landsat imagery will be studied in detail.
Software: Idrisi32, (ArcGIS).
Language: English or Swedish.


  GÅ TILL XJOBB.NU FÖR FULLSTÄNDIG INFO OM DETTA EXJOBB




Informationen om uppsatsförslag är hämtad från Nationella Exjobb-poolen.