DocumentCode :
2942860
Title :
Terrain classification in polarimetric SAR using wavelet packets
Author :
Keshava, Nirmal ; Moura, José
Author_Institution :
Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
Volume :
1
fYear :
1997
fDate :
21-24 Apr 1997
Firstpage :
555
Abstract :
POL-SAR data acquired from the two 1994 flights of the SIR-C/X-SAR platform has illustrated the variability of measurements due to seasonal, spectral, and angular changes. Consequently statistical techniques for terrain classification make robust, unsupervised classification problematic. We present an algorithm for classifying terrain that accounts for variability in terrain signatures by deriving a single representative process for each terrain from a family of stochastic scattering models. A best-basis search through a wavelet packet tree, using the Bhattacharyya coefficient as a cost measure, determines the optimal unitary basis of eigenvectors for the representative process and offers a scale-based interpretation of the scattering phenomena. The associated eigenvalues and means are determined through iterative algorithms. The technique is illustrated with a simple example
Keywords :
eigenvalues and eigenfunctions; image classification; iterative methods; radar applications; radar cross-sections; radar imaging; radar polarimetry; statistical analysis; stochastic processes; synthetic aperture radar; wavelet transforms; Bhattacharyya coefficient; SIR-C/X-SAR platform; angular changes; best-basis search; cost measure; eigenvalues; eigenvectors; iterative algorithms; measurements variability; optimal unitary basis; polarimetric SAR; radar images; scale-based interpretation; seasonal changes; spectral changes; statistical techniques; stochastic scattering models; terrain classification; terrain signatures; unsupervised classification; wavelet packet tree; Covariance matrix; Electric variables measurement; Phase change materials; Radar scattering; Robustness; Statistical analysis; Statistics; Stochastic processes; Testing; Wavelet packets;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on
Conference_Location :
Munich
ISSN :
1520-6149
Print_ISBN :
0-8186-7919-0
Type :
conf
DOI :
10.1109/ICASSP.1997.599698
Filename :
599698
Link To Document :
بازگشت