Application of the Savitzky-Golay Filter to Land Cover Classification Using Temporal MODIS Vegetation Indices

Authors

So-Ra Kim, Korea University
Anup K. Prasad, Chapman UniversityFollow
Hesham el-Askary, Chapman UniversityFollow
Woo- Kyun Lee, Korea UniversityFollow
Doo- Ahn Kwak, Korea UniversityFollow
Seung- Ho Lee, Korea Forest Research InstituteFollow
Menas Kafatos, Chapman UniversityFollow

Document Type

Article

Publication Date

7-2014

Abstract

In this study, the Savitzky-Golay filter was applied to smooth observed unnatural variations in the temporal profiles of the Normalized Difference Vegetation Index (NDVI} and the Enhanced Vegetation Index {EVI} time series from the MODerate Resolution Imaging Spectroradiometer (MODIS}. We computed two sets of land cover classifications based 011 the NDVI and EVI time series before and after applying the Savitzky-Golay filter. The resulting classification from the filtered versions of the vegetation indices showed a substantial improvement in accuracy when compared to the classifications from the unfiltered versions. The classification by the EVIsg had the highest K (0.72} for all classes compared to those of the EVI (0.67}, NDVI (0.63}, and NDV/sg (0.62). Therefore, we conclude that the EVIsg is best suited for land cover classification compared to the other data sets in this study.

Comments

This article was originally published in Photogrammetric Engineering & Remote Sensing, volume 80, number 7, in July 2014. DOI: 10.14358/PERS.80.7.675

Published by the American Society for Photogrammetry and Remote Sensing.

Recommended Citation

Kim, So-Ra, Anup K. Prasad, Hesham El-Askary, Woo-Kyun Lee, Doo-Ahn Kwak, Seung-Ho Lee, and Menas Kafatos, 2014. Application of the Savitzky-Golay filter to land cover classification using temporal MODIS vegetation indices, Photogrammetric Engineering & Remote Sensing, 80(7): 675-685.
DOI: 10.1016/j.jcis.2014.11.033

Copyright

American Society for Photogrammetry and Remote Sensing (ASPRS)