IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, VOL. 55, NO. 12, DECEMBER 2017 6893 Evaluation of the New Information in the H /α Feature Space Provided by ICA in PolSAR Data Analysis Leandro Pralon, Gabriel Vasile, Member, IEEE, Mauro Dalla Mura, Member, IEEE, and Jocelyn Chanussot, Fellow, IEEE Abstract— The Cloude and Pottier H/α feature space is one of the most employed methods for unsupervised polarimetric synthetic aperture radar (PolSAR) data classification based on incoherent target decomposition (ICTD). The method can be split in two stages: the retrieval of the canonical scattering mechanisms present in an image cell and their parameterization. The association of the coherence matrix eigenvectors to the most dominant scattering mechanisms in the analyzed pixel introduces unfeasible regions in the H/α plane. This constraint can compromise the performance of detection, classification, and geophysical parameter inversion algorithms that are based on the investigation of this feature space. The independent component analysis (ICA), recently proposed as an alternative to eigenvector decomposition, provides promising new information to better interpret non-Gaussian heterogeneous clutter (inherent to high- resolution SAR systems) in the frame of polarimetric ICTDs. Not constrained to any orthogonality between the estimated scattering mechanisms that compose the clutter under analysis, ICA does not introduce any unfeasible region in the H/α plane, increasing the range of possible natural phenomena depicted in the aforementioned feature space. This paper addresses the potential of the new information provided by the ICA as an ICTD method with respect to Cloude and Pottier H/α feature space. A PolSAR data set acquired in October 2006 by the E-SAR system over the upper part of the Tacul glacier from the Chamonix Mont Blanc test site, France, and a RAMSES X-band image acquired over Brétigny, France, are taken into consideration to investigate the characteristics of pixels that may fall outside the feasible regions in the H/α plane that arise when the eigenvector approach is employed. Index Terms— H/α feature space, independent component analysis (ICA), polarimetric incoherent target decomposi- tion (ICTD). I. I NTRODUCTION P OLARIMETRIC target decomposition is a polarimetric synthetic aperture radar (PolSAR) image interpretation technique that relies on the analysis of the interaction between Manuscript received March 16, 2016; revised January 19, 2017 and April 10, 2017; accepted July 13, 2017. Date of publication September 21, 2017; date of current version November 22, 2017. This work was supported by Brazilian Army. (Corresponding author: Leandro Pralon.) L. Pralon is with the Brazilian Army Technological Center, Rio de Janeiro 23020-470, Brazil, and also with the Grenoble Image Speech Signal Automatics Lab, CNRS/Grenoble INP, 38000 Grenoble, France (e-mail: pralon@ctex.eb.br). G. Vasile, M. Dalla Mura, and J. Chanussot are with the Grenoble Image Speech Signal Automatics Laboratory, CNRS/Grenoble INP, 38000 Grenoble, France. Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org. Digital Object Identifier 10.1109/TGRS.2017.2735992 the illuminated area and the transmitted waveform, considering each polarimetric state of the latter. Compared with the uni- variate analysis of single polarization systems, the multivariate nature of PolSAR data allows for a better prediction of the physical properties of the illuminated targets, leading to more effective classification, detection, and geophysical parameter inversion algorithms. More specifically, with respect to target decompositions, they enable the description of an image cell as a sum of canonical scattering mechanisms (also called as target vectors) making it more intuitive to understand the behavior of the clutter and therefore to analyze it [5]. Polarimetric target decompositions are mainly classified in coherent, if their interest lies on the scattering matrix analysis for each resolution cell, like the ones proposed in [1]– [3], or incoherent, if they are based on a statistical analysis of neighboring pixels. Incoherent target decomposition (ICTD) theory assumes that the scattering process in most natural media is a combination of coherent speckle noise and random vector scattering effects. Therefore, a stochastic approach is required and the concept of average or dominant scattering mechanisms is associated with each imaging cell [4]. Most methods described in the literature focus on the Hermitian semidefinite positive coherence or covariance matrix [4], [5]. Nevertheless, the investigation of higher order moments has recently sparked great interest of the SAR community, intro- ducing supplementary information to the clutter analysis and consequently leading to new ICTD approaches [8], [20]. ICTD algorithms can be split in two stages: the decom- position of an image cell into basic target vectors and the correct retrieval of quantitative information from them (parameterization). Concerning the latter, Cloude and Pottier’s parameters (entropy, alpha, and anisotropy) [6] and Touzi’s target scattering vector model [5] are the most employed ones, whose usefulness has already been demonstrated by several authors. Regarding the former, the association of the three most dominant scatters, or scattering mechanisms, in an image cell to the eigenvectors of the coherence/covariance matrix of the data (generally estimated considering a set of neighboring pixels) is so widespread in the PolSAR com- munity that it is often mistaken as the only alternative for that purpose. The eigenvector-based ICTD has an intrinsic property that the derived scatters, scattering mechanisms, are orthogonal and uncorrelated, which for Gaussian clutters also means independence. The drawback of this kind of method emerges when the clutter is not Gaussian or not composed by 0196-2892 © 2017 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.