Share Email Print

Proceedings Paper

Statistics analysis on SPOT 5 classification accuracy of different data fusion methods
Author(s): Guifang Liu; Heli Lu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In recent years, data fusion has become a very popular method in remote sensing image enhancement. In this paper, a comparative study was conducted on data fusion methods based upon SPOT5 image. First land types of forest, paddy field, dry land, water and building was selected through field survey. Then supervised classification and non-supervised classification were used upon original image and four fusion images (HIS, PCA, high-pass filtering (HPF) and Brovery) respectively. Land change area, change rate and classification accuracy were calculated. Finally suitable SPOT5 fusion method for every land types was presented. The result showed: (1) In all four fusing methods PCA held the highest land change rate, being average 49.0% for non-supervised classification and average 18.9% for supervised classification. So visual interpretation was a better way for PCA fusion image. (2) HIS produced some distortion to the original spectrum and made flaky features into pieces. This method was suitable to extract small features in complicated urban areas because of its high spatial resolution. In the research, building change rate in HIS fusing image under supervised classification was lowest, only 3.32%. (3) For HPF land change rate was low for no matter non-supervised classification or supervised classification, being average 16.3% and 11.2% respectively. This fusion method held low distortion and more high-frequency spectrum. It was suitable to be used as the basic image data for both supervised classification and non-supervised classification. In our research image classification accuracy of urban areas in HPF fusion image was 93.1%.

Paper Details

Date Published: 15 October 2009
PDF: 7 pages
Proc. SPIE 7492, International Symposium on Spatial Analysis, Spatial-Temporal Data Modeling, and Data Mining, 74922C (15 October 2009); doi: 10.1117/12.838450
Show Author Affiliations
Guifang Liu, Henan Univ. (China)
Heli Lu, Henan Univ. (China)

Published in SPIE Proceedings Vol. 7492:
International Symposium on Spatial Analysis, Spatial-Temporal Data Modeling, and Data Mining
Yaolin Liu; Xinming Tang, Editor(s)

© SPIE. Terms of Use
Back to Top