Application of the Savitzky-Golay filter to land cover classification using temporal MODIS vegetation indices

So Ra Kim; Anup K. Prasad; Hesham El-Askary; Woo Kyun Lee; Doo Ahn Kwak; Seung Ho Lee; Menas Kafatos

doi:10.14358/PERS.80.7.675

Application of the Savitzky-Golay filter to land cover classification using temporal MODIS vegetation indices

So Ra Kim, Anup K. Prasad, Hesham El-Askary, Woo Kyun Lee, Doo Ahn Kwak, Seung Ho Lee, Menas Kafatos

Research output: Contribution to journal › Article › peer-review

38 Citations (Scopus)

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 on 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 K̂ (0.72) for all classes compared to those of the EVI (0.67), NDVI (0.63), and NDVIsg (0.62). Therefore, we conclude that the EVIsg is best suited for land cover classification compared to the other data sets in this study.

Original language	English
Pages (from-to)	675-685
Number of pages	11
Journal	Photogrammetric Engineering and Remote Sensing
Volume	80
Issue number	7
DOIs	https://doi.org/10.14358/PERS.80.7.675
Publication status	Published - 2014 Jul

ASJC Scopus subject areas

Computers in Earth Sciences

Access to Document

10.14358/PERS.80.7.675

Cite this

@article{8405b8e07f0e45aeb9582c6652be5eec,

title = "Application of the Savitzky-Golay filter to land cover classification using temporal MODIS vegetation indices",

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 on 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 NDVIsg (0.62). Therefore, we conclude that the EVIsg is best suited for land cover classification compared to the other data sets in this study.",

author = "Kim, {So Ra} and Prasad, {Anup K.} and Hesham El-Askary and Lee, {Woo Kyun} and Kwak, {Doo Ahn} and Lee, {Seung Ho} and Menas Kafatos",

year = "2014",

month = jul,

doi = "10.14358/PERS.80.7.675",

language = "English",

volume = "80",

pages = "675--685",

journal = "Photogrammetric Engineering and Remote Sensing",

issn = "0099-1112",

publisher = "American Society for Photogrammetry and Remote Sensing",

number = "7",

}

TY - JOUR

T1 - Application of the Savitzky-Golay filter to land cover classification using temporal MODIS vegetation indices

AU - Kim, So Ra

AU - Prasad, Anup K.

AU - El-Askary, Hesham

AU - Lee, Woo Kyun

AU - Kwak, Doo Ahn

AU - Lee, Seung Ho

AU - Kafatos, Menas

PY - 2014/7

Y1 - 2014/7

N2 - 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 on 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 K̂ (0.72) for all classes compared to those of the EVI (0.67), NDVI (0.63), and NDVIsg (0.62). Therefore, we conclude that the EVIsg is best suited for land cover classification compared to the other data sets in this study.

AB - 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 on 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 K̂ (0.72) for all classes compared to those of the EVI (0.67), NDVI (0.63), and NDVIsg (0.62). Therefore, we conclude that the EVIsg is best suited for land cover classification compared to the other data sets in this study.

UR - http://www.scopus.com/inward/record.url?scp=84904293223&partnerID=8YFLogxK

U2 - 10.14358/PERS.80.7.675

DO - 10.14358/PERS.80.7.675

M3 - Article

AN - SCOPUS:84904293223

SN - 0099-1112

VL - 80

SP - 675

EP - 685

JO - Photogrammetric Engineering and Remote Sensing

JF - Photogrammetric Engineering and Remote Sensing

IS - 7

ER -

Application of the Savitzky-Golay filter to land cover classification using temporal MODIS vegetation indices

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this