Point Target Classification via Fast Lossless and Sufficient $\Omega$–$\Psi$–$\Phi$ Invariant Decomposition of High-Resolution and Fully Polarimetric SAR/ISAR Data

Paladini, R.; Famil, L. Ferro; Pottier, Éric; Berizzi, F.; Mese, E. Dalle

doi:10.1109/jproc.2012.2227894

Cited by 18 publications

(9 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As far as we know, it is the first time that the concept of finegrained recognition is introduced into ISAR ATR. For the above problems, how to make full use of the abundant shape and structural information contained in the ISAR image and design an effective robust feature extraction method and classification algorithm has received extensive attention in the ISAR ATR community [15], [16].…”

Section: A Problem Statementmentioning

confidence: 99%

A Deformation Robust ISAR Image Satellite Target Recognition Method Based on PT-CCNN

et al. 2021

View full text Add to dashboard Cite

To tackle the inherent unknown deformation (e.g., translation, rotation and scaling) of the inverse synthetic aperture radar (ISAR) images, a deep polar transformer-circular convolutional neural network, i.e., PT-CCNN, is proposed to achieve deformation robust ISAR image automatic target recognition (ATR) in this paper. Inspired by human visual system and canonical coordinate of Lie-groups, we adopt a polar transformer module to transform the deformation ISAR images to the log-polar representations, before which a conventional convolutional neural network (CNN) is utilized to predict the origin of log-polar transformation. The above techniques make the proposed network invariant to translation, and equivariant to rotation and scaling. On this basis, for the log-polar representations with wrap-around structure, a circular convolutional neural network (CCNN) is further applied to extract more effective and highly discriminative features and improve recognition accuracy. The proposed network is end-to-end trainable with a classification loss, and could extract deformation-robust and essential features automatically. For multiple practical ISAR image datasets of six satellites, the performance testing and comparison experiments demonstrate that the techniques utilized in PT-CCNN are effective, and our proposed network achieve higher recognition accuracy than those previous common methods based on deep learning. For instance, our proposed PT-CCNN beats traditional CNN on rotation, scaling and practical deformation datasets by 24.5-49.3%, 9.0-40.8% and 22.3-26.7%. And it also outperforms the polar CNN without using the above techniques on rotation, scaling and practical deformation datasets by 9.2-53.7%, 5.2-54.6% and 9.0-49.9%. Additionally, the presented visualization results show the abilities and advantages of our method in terms of handling image deformation and extracting effective features.INDEX TERMS Automatic target recognition (ATR), inverse synthetic aperture radar (ISAR), deep convolutional neural network (DCNN), image deformation, log-polar transformation.

show abstract

Section: A Problem Statementmentioning

confidence: 99%

A Deformation Robust ISAR Image Satellite Target Recognition Method Based on PT-CCNN

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In that case S(x, y) corresponds to a spatial pixel of an imaged area, that has consequences for all following polarimetric analysis regarding decomposition and classification methods that are performed in image domain. There exist a variety of different algorithms to give a physical interpretation to a measured scattering matrix [8]. Coherent techniques decompose S into orthogonal basis matrices that refer to different backscattering mechanisms.…”

Section: Microwave Polarimetrymentioning

confidence: 99%

Exploiting polarimetric radar cross section characteristics for clustering of ultrawideband radar signals

Roding

Thomä

2016

2016 10th European Conference on Antennas and Propagation (EuCAP)

View full text Add to dashboard Cite

The radar cross section (RCS) of an object is a reflectivity pattern that depends on geometrical features like incident and scattered angle, target features like shape or surface roughness and system parameters like frequency and polarization. Fully polarimetric ultrawideband (UWB) sensors exploit both last mentioned dimensions to understand the backscattering behavior of an object. The knowledge gained from RCS analysis can be used in applications related to multi target environment characterization. This publication introduces a procedure for discriminating polarimetric object RCS by investigating target features in time and image domain. For the purpose of a model based interpretation of an environment, polarimetric radar measurements are utilized for clustering specific polarimetric backscattering signatures. The clustering approach is embedded in an iterative algorithm that analyses the polarimetric radar data regarding dominant backscattering components.

show abstract

“…2) Polarisation basis invariance: The same dataset is used to demonstrate the invariance with respect to more complex unitary transform -the change of the polarization basis. The observed scattering matrices are projected on the circular polarization basis and the obtained components parametrized using Circular Polarization Scattering Vector (CPSV) [36], [37]:…”

Section: Data Set I: Urban Areamentioning

confidence: 99%

Polarimetric Incoherent Target Decomposition by Means of Independent Component Analysis

Bešič

Vasile

Chanussot

et al. 2015

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

International audienceThis paper presents an alternative approach for polarimetric incoherent target decomposition dedicated to the analysis of very-high resolution POLSAR images. Given the non-Gaussian nature of the heterogeneous POLSAR clutter due to the increase of spatial resolution, the conventional methods based on the eigenvector target decomposition can ensure uncorrelation of the derived backscattering components at most. By introducing the Independent Component Analysis (ICA) in lieu of the eigenvector decomposition, our method is rather deriving statistically independent components. The adopted algorithm - FastICA, uses the non-Gaussianity of the components as the criterion for their independence. Considering the eigenvector decomposition as being analogues to the Principal Component Analysis (PCA), we propose the generalization of the ICTD methods to the level of the Blind Source Separation (BSS) techniques (comprising both PCA and ICA). The proposed method preserves the invariance properties of the conventional ones, appearing to be robust both with respect to the rotation around the line of sight and to the change of the polarization basis. The efficiency of the method is demonstrated comparatively, using POLSAR Ramses X-band and ALOS L-band data sets. The main differences with respect to the conventional methods are mostly found in the behaviour of the second most dominant component, which is not necessarily orthogonal to the first one. The potential of retrieving non-orthogonal mechanisms is moreover demonstrated using synthetic data. On expense of a negligible entropy increase, the proposed method is capable of retrieving the edge diffraction of an elementary trihedral by recognizing dipole as the second component

show abstract

Point Target Classification via Fast Lossless and Sufficient $\Omega$–$\Psi$–$\Phi$ Invariant Decomposition of High-Resolution and Fully Polarimetric SAR/ISAR Data

Cited by 18 publications

References 51 publications

A Deformation Robust ISAR Image Satellite Target Recognition Method Based on PT-CCNN

A Deformation Robust ISAR Image Satellite Target Recognition Method Based on PT-CCNN

Exploiting polarimetric radar cross section characteristics for clustering of ultrawideband radar signals

Polarimetric Incoherent Target Decomposition by Means of Independent Component Analysis

Contact Info

Product

Resources

About