Vegetation classification in eastern china using time series NDVI images

  • Guifeng Han*
  • , Jianhua Xu
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The SPOT/VGT NDVI (S10) time series data of eastern China (1998-2005) are smoothed with two methods, the moving average and the Savitzky-Golay filter, after they are downloaded from the official website of VITO. Then the monthly maximal NDVI images (total 93 images) are extracted from 279 NDVI (S10) images and the Principal Component Analysis (PCA) is applied on the 93 images. There are 3 components that each explains more than 1% of the variance, in which the principal components 1, 2 and 3 explain respectively 93.25%, 2.77% and 1.21% of the variance in the original 93 maximum NDVI images. The principal component 1 is interpreted as the "climate" component, and principal components 2 and 3 are interpreted as the "growth season" and "non-growth season" components respectively. Principal components 1, 2 and 3 are composed to a 3-band color image which is classified into 7 classes (including 18 subclasses) by ISODATA. The overall accuracy of classification in five samples is 83.6%, and the kappa index is 0.82. Finally, the unique intra-annual NDVI curve of each vegetation class is displayed.

Original languageEnglish
Title of host publicationMIPPR 2007
Subtitle of host publicationRemote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications
DOIs
StatePublished - 2007
EventMIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications - Wuhan, China
Duration: 15 Nov 200717 Nov 2007

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume6790
ISSN (Print)0277-786X

Conference

ConferenceMIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications
Country/TerritoryChina
CityWuhan
Period15/11/0717/11/07

Keywords

  • Eastern China
  • Principal component analysis
  • Time series NDVI dataset
  • Unsupervised classification
  • Vegetation classification

Fingerprint

Dive into the research topics of 'Vegetation classification in eastern china using time series NDVI images'. Together they form a unique fingerprint.

Cite this