TY - GEN
T1 - Vegetation classification in eastern china using time series NDVI images
AU - Han, Guifeng
AU - Xu, Jianhua
PY - 2007
Y1 - 2007
N2 - 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.
AB - 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.
KW - Eastern China
KW - Principal component analysis
KW - Time series NDVI dataset
KW - Unsupervised classification
KW - Vegetation classification
UR - https://www.scopus.com/pages/publications/42549155664
U2 - 10.1117/12.749124
DO - 10.1117/12.749124
M3 - 会议稿件
AN - SCOPUS:42549155664
SN - 9780819469540
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - MIPPR 2007
T2 - MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications
Y2 - 15 November 2007 through 17 November 2007
ER -