Sequential classification of MODIS time series

Author

Grobler, T.L. ; Ackermann, E.R. ; van Zyl, A.J. ; Kleynhans, W. ; Salmon, B.P. ; Olivier, J.C.

Author_Institution

Dept. of Electr., Electron. & Comput. Eng., Univ. of Pretoria, Tshwane, South Africa

fYear

2012

fDate

22-27 July 2012

Firstpage

6236

Lastpage

6239

Abstract

In this paper a sequential time-varying maximum likelihood classifier is applied on coarse resolution MODIS surface reflectance data. It is shown that good class separability can be obtained after considering only one year of data. Finally it is shown that after NDVI, band 2 has the highest separability of all the MODIS land bands, and band 6 has the lowest separability for the presented case study.

Keywords

geophysical image processing; image classification; image resolution; maximum likelihood estimation; radiometry; terrain mapping; MODIS land band; MODIS time series; NDVI; class separability; coarse resolution MODIS surface reflectance data; land cover classification; sequential classification; sequential time-varying maximum likelihood classifier; Educational institutions; MODIS; Maximum likelihood detection; Probability density function; Time series analysis; Vegetation; Vegetation mapping; Land cover classification; MODIS; sequential; time series; time-varying maximum likelihood classifier;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium (IGARSS), 2012 IEEE International

Conference_Location

Munich

ISSN

2153-6996

Print_ISBN

978-1-4673-1160-1

Electronic_ISBN

2153-6996

Type

conf

DOI

10.1109/IGARSS.2012.6352683

Filename

6352683