Hierarchical PCA techniques for fusing spatial and spectral observations with application to MISR and monitoring dust storms

被引:8
作者
Agarwal, Abhishek [1 ]
El-Askary, Hesham Mohamed
El-Ghazawi, Tarek
Kafatos, Menas
Le-Moigne, Jacqueline
机构
[1] Univ Alexandria, Dept Environm Sci, Alexandria 21522, Moharam Bek, Egypt
[2] NARSS, Cairo, Egypt
[3] George Mason Univ, Ctr Earth Observing & Space Res, Fairfax, VA 22030 USA
[4] NASA, Goddard Space Flight Ctr, Greenbelt, MD 20771 USA
关键词
data fusion; dust storms; Multiangle Imaging SpectroRadiometer (MISR); principal component analysis (PCA);
D O I
10.1109/LGRS.2007.904467
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
In this letter, we propose hierarchical principal component analysis (HPCA) techniques for fusing spatial and spectral data, and compare them to direct principal component analysis (DPCA) over Multiangle Imaging SpectroRadiometer (MISR) data. It is shown that the proposed methods are significantly faster than DPCA. In case of DPCA, we merge the 20 different images resulting from the four spectral bands over the nadir and the four forward angles. In the hierarchical case, we first merge the information from the four spectral camera bands; then, we integrate the spatial information from the five cameras in the second step (or vice versa) by applying principal component analysis (PCA) twice. The classification results show that fused data using HPCA compare favorably to DPCA or to classification using the original data. This is because applying PCA to one particular data domain (e.g., spectral data followed by spatial data or vice versa) tends to better remove redundancies and enhance features within that domain. In addition, classification through hierarchical data fusion results in computational savings over the other methods.
引用
收藏
页码:678 / 682
页数:5
相关论文
共 13 条
[1]  
El-Askary H, 2005, INT GEOSCI REMOTE SE, P1424
[2]   Dust storms detection over the Indo-Gangetic basin using multi sensor data [J].
El-Askary, H. ;
Gautam, R. ;
Singh, R. P. ;
Kafatos, M. .
NATURAL HAZARDS AND OCEANOGRAPHIC PROCESSES FROM SATELLITE DATA, 2006, 37 (04) :728-733
[3]   A multisensor approach to dust storm monitoring over the Nile Delta [J].
El-Askary, HM ;
Sarkar, S ;
Kafatos, M ;
El-Ghazawi, TA .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2003, 41 (10) :2386-2391
[4]   Segmented principal components transformation for efficient hyperspectral remote-sensing image display and classification [J].
Jia, XP ;
Richards, JA .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1999, 37 (01) :538-542
[5]  
KAFATOS M, 2004, P INT S SAND DUST ST
[6]   An efficient k-means clustering algorithm:: Analysis and implementation [J].
Kanungo, T ;
Mount, DM ;
Netanyahu, NS ;
Piatko, CD ;
Silverman, R ;
Wu, AY .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (07) :881-892
[7]   RETRIEVAL OF SURFACE DIRECTIONAL REFLECTANCE PROPERTIES USING GROUND-LEVEL MULTIANGLE MEASUREMENTS [J].
MARTONCHIK, JV .
REMOTE SENSING OF ENVIRONMENT, 1994, 50 (03) :303-316
[8]   Fusion of 2D grayscale images using multiscale morphology [J].
Mukhopadhyay, S ;
Chanda, B .
PATTERN RECOGNITION, 2001, 34 (10) :1939-1949
[9]   Multisensor image fusion in remote sensing: concepts, methods and applications [J].
Pohl, C ;
van Genderen, JL .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1998, 19 (05) :823-854
[10]   A Markov random field model for classification of multisource satellite imagery [J].
Solberg, AHS ;
Taxt, T ;
Jain, AK .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1996, 34 (01) :100-113