Independent component analysis within polarimetric incoherent target decomposition

Nikola Besic (1, 2) , Gabriel Vasile (2) , Jocelyn Chanussot (2) , Srdjan Stankovic (1) , Didier Boldo (3) , Guy d'Urso (4)

1 Department of Electrical Engineering
2 GIPSA-SIGMAPHY - GIPSA - Signal Images Physique
3 EDF R&D - EDF R&D
4 EDF - EDF

This paper represents a part of our efforts to generalize polarimetric incoherent target decomposition to the level of BSS techniques by introducing the ICA method instead of the conventional eigenvector decomposition. We compare, in the frame of polarimetric incoherent target decomposition, several criteria for the estimation of complex independent components. This is done by parametrising the obtained dominant and mutually independent target vectors using the TSVM and representing them on the corresponding Poincare sphere. We demonstrate notably good performances of the proposed method applied on the RAMSES POLSAR X-band image, by precisely identifying the class of trihedral reflectors present in the scene. Logarithm and square root nonlinearities - two of the three proposed criteria for complex IC derivation prove to be very efficient. The best discrimination between the a priori defined classes appears to be achieved with the principal kurtosis criterion. Finally, the algorithm using the former two functions leads to very interesting entropy estimation.

Mots clés: Polarimetric ICTD; Complex Fast-ICA; TVSM; Poincare sphere; non-gaussianity

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]; Applications [stat.AP]

Nikola Besic, Gabriel Vasile, Jocelyn Chanussot, Srdjan Stankovic, Didier Boldo, et al.. Independent component analysis within polarimetric incoherent target decomposition. IGARSS 2013 - IEEE International Geoscience and Remote Sensing Symposium, Jul 2013, Melbourne, Australia. pp.4158-4161. ⟨hal-00852109⟩