DocumentCode :
2936920
Title :
Improving the accuracy of linear pixel unmixing via appropriate endmember dimensionality reduction
Author :
Li, Jiang ; Bruce, Lori Mann
Author_Institution :
Electr. & Comput. Eng. Dept, Mississippi State Univ., Starkville, MS, USA
fYear :
2003
fDate :
27-28 Oct. 2003
Firstpage :
157
Lastpage :
162
Abstract :
Spectral unmixing is a quantitative analysis procedure used to recognize constituent ground cover materials (or endmembers) and obtain their mixing proportions (or abundances) from a mixed pixel. The endmember abundances may be estimated using the least squares estimation (LSE) method based on the linear mixture model. This paper investigates the use of spectral dimensionality reduction as a preprocessing tool for hyperspectral linear unmixing. Four dimensionality reduction methods are investigated and compared; these include methods based on the discrete wavelet transform (DWT), discrete cosine transform, principal component transform, and linear discriminant transform (LDT). Three sets of experiments are designed and implemented for evaluating the effects of the dimensionality reduction techniques on the LSE of endmember abundances. Experimental results show that the use of the DWT and LDT-based features extracted from the original hyperspectral signals can greatly improve the abundance estimation of endmembers. On average with these methods, the root-mean-square of the abundance estimation error is reduced by 20%.
Keywords :
discrete cosine transforms; discrete wavelet transforms; image classification; least mean squares methods; principal component analysis; spectral analysis; abundance estimation error; discrete cosine transform; discrete wavelet transform; endmember dimensionality reduction; hyperspectral linear unmixing; hyperspectral signals; least squares estimation; linear discriminant transform; linear mixture model; linear pixel unmixing; principal component transform; root mean square method; spectral dimensionality reduction; spectral unmixing; Crops; Design methodology; Discrete cosine transforms; Discrete wavelet transforms; Feature extraction; Hyperspectral imaging; Hyperspectral sensors; Least squares approximation; Object detection; Soil;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Advances in Techniques for Analysis of Remotely Sensed Data, 2003 IEEE Workshop on
Print_ISBN :
0-7803-8350-8
Type :
conf
DOI :
10.1109/WARSD.2003.1295187
Filename :
1295187
Link To Document :
بازگشت