Unsupervised classification of multifrequency and fully polarimetric SAR images based on the H/A/Alpha-Wishart classifier

Ferro-Famil, Laurent; Pottier, Éric; Lee, Jong-Sen

doi:10.1109/36.964969

Cited by 316 publications

(123 citation statements)

References 18 publications

Supporting

Mentioning

120

Contrasting

Unclassified

Order By: Relevance

“…Single-date multi-polarization SAR data also has the potential to identify crops based on the variation in their scattering signatures in different polarizations. Various authors have reported of achieving significant classification accuracies for crops and other landuse classes using dual and quad polarimetric data from airborne as well as spaceborne SARs [1,6,7,23,24,26]. Although there is a consensus that full-polarimetric imaging modes provide higher classification accuracies than dual polarimetric modes, opinions vary regarding the classification accuracies obtained by different modes of dual polarimetric SARs, including hybrid-dual polarimetric imaging modes.…”

Section: Introductionmentioning

confidence: 99%

“…2(b)). The details of these classification algorithms can be found in literature [6,[10][11][12][13][14][15]18]. We have however discussed the algorithm and methodology of the present classification in brief.…”

Section: Supervised Classification Of Multi-polarization Sar Datamentioning

confidence: 99%

“…The backscatter intensities (in logarithmic scale) of the data were computed as: σ 0 (dB) = 10 * log 10 (Intensity) + CF − 32.0 (6) where 'CF ' is the calibration factor (here −83 dB) provided by JAXA for ALOS-PALSAR level 1.1 (SLC) products. Conversion of DN values to backscatter intensity after performing multilooking operation from the SLC data is shown in the above equation and n = 4.…”

Section: Supervised Classification Of Multi-date Single Polarization mentioning

confidence: 99%

See 2 more Smart Citations

Assessment of L-Band Sar Data at Different Polarization Combinations for Crop and Other Landuse Classification

Haldar¹,

Das²,

Mohan³

et al. 2012

PIER B

View full text Add to dashboard Cite

Abstract-In the present study evaluation of L-band SAR data at different polarization combinations in linear, circular as well as hybrid polarimetric imaging modes for crop and other landuse classifications has been carried out. Full-polarimetric radar data contains all the scattering information for any arbitrary polarization state, hence data of any combination of transmit and receive polarizations can be synthesized, mathematically from full-polarimetric data. Circular and various modes of hybrid polarimetric data (where the transmitter polarization is either circular or orientated at 45 • , called π/4 and the receivers are at horizontal and vertical polarizations with respect to the radar line of sight) were synthesized (simulated) from ALOS-PALSAR fullpolarimetric data of 14th December 2008 over central state farm central latitude and longitude 29 • 15 N/75 • 43 E and bounds for northwest corner is 29 • 24 N/75 • 37 E and southeast corner is 29 • 07 N/75 • 48 E in Hisar, Haryana (India) Supervised classification was conducted for crops and few other landuse classes based on ground truth measurements using maximum-likelihood distance measures derived from the complex Wishart distribution of SAR data at various polarization combinations. It has been observed that linear fullpolarimetric data showed maximum classification accuracy (92%) followed by circular-full (89%) and circular-dual polarimetric data (87%), which was followed by hybrid polarimetric data (73-75%) and then linear dual polarimetric data (63-71%). Among the linear dual polarimetric data, co-polarization complex data showed better classification accuracy than the cross-polarization data. Also multidate single polarization SAR data over central state farm during rabi (winter) season was analyzed and it was observed that single date fullpolarimetric SAR data produced equally good classification result as the multi-date single polarization SAR data.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Supervised Classification Of Multi-polarization Sar Datamentioning

confidence: 99%

Section: Supervised Classification Of Multi-date Single Polarization mentioning

confidence: 99%

See 1 more Smart Citation

Assessment of L-Band Sar Data at Different Polarization Combinations for Crop and Other Landuse Classification

Haldar¹,

Das²,

Mohan³

et al. 2012

PIER B

View full text Add to dashboard Cite

show abstract

“…Moreover, as the sample covariance matrix of A 22 follows a complex Wishart density function with n degrees of freedom W C (n, Σ 22 ), the conditional probability density of A 12 given A 22 is a complex normal function [18] …”

Section: B Joint Density Function Of Temporal Polarimetric Covariancmentioning

confidence: 99%

A New Coherent Similarity Measure for Temporal Multichannel Scene Characterization

Erten¹,

Reigber

Ferro-Famil

et al. 2012

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Abstract-This paper proposes a new method for a measure of coherent similarity between temporal multichannel synthetic aperture radar (SAR) images and its implementation to change detection application. The method is based on mutual information (MI) from information theory. The MI measures the amount of information in common between coherent temporal multichannel SAR acquisitions. In order to develop an algorithm for all kinds of SAR images, such as interferometric SAR, polarimetric-interferometric SAR (PolInSAR), and partial PolIn-SAR, first, the joint density function of temporal multichannel images based on their second-order statistics has been derived. Then, the derived joint density function is used to calculate an analytical expression for the MI between temporal images, which is assumed to be maximal if the temporal images are identical. Although, in this paper, a new coherent similarity measure has analytically been derived for temporal polarimetric SAR images based on complex Wishart process in time, since the mathematical formulation is general, it can equally well be implemented into any kind of multivariate remote sensing data, such as multispectral optical and interferometric images after small continuation. This derived quantity has been implemented for change detection application whose aim is to characterize the temporal behavior of the acquisitions. A comparison between the proposed and the other well-known change detection methods by means of scene characterization is shown, describing the advantages due to the fact that the proposed change detector involves almost every facet of applied change detection.

show abstract

“…Polarimetric parameters such as copolarization phase differences ( hhvv ), entropy (H), anisotropy (A), and polarization scattering angle (a), from the eigenvalue and eigenvector decomposition [Cloude and Pottier, 1996;Pottier and Cloude, 1997], are the basis for the development of new classification methods [Lee et al, 1999;Ferro-Famil et al, 2001;Touzi et al, 2004;Lee and Pottier, 2009]. These polarimetric parameters use statistical properties of the polarimetric data, including eigencharacters of the coherency matrix; all elements of the coherency matrix are analyzed including NRCS, correlation, and phase differences among different polarimetric channels.…”

Section: Introductionmentioning

confidence: 99%

On polarimetric characteristics in SAR images of mesoscale cellular convection in the marine atmospheric boundary layer

Perrie

Guo

et al. 2011

J. Geophys. Res.

View full text Add to dashboard Cite

Convection is an important phenomenon in the marine atmospheric boundary layer (MABL). Previous spaceborne radar studies of such have been limited to single polarization data, and therefore their focus was on the variation in intensity of the radar return, which was constrained by the existence of a single polarization image pattern, representing different atmospheric and oceanic phenomena. In this paper, we study the polarimetric characteristics of mesoscale cellular convection (MCC) in the MABL using high‐resolution data from fully polarimetric (HH, VV, HV, and VH) RADARSAT‐2 (RS‐2) synthetic aperture radar (SAR) images, in conjunction with closely collocated mesoscale atmospheric model simulations, to identify the MCC signatures. To compare the polarimetric characteristics of MCC with those of the ocean surface, our analysis also includes 641 open ocean surface quad‐polarization RS‐2 SAR images collocated with 52 National Data Buoy Center buoys. The open ocean surface SAR images exhibit different polarimetric characteristics from those of MCC. Thus, we differentiate MCC from other open ocean phenomena, based on identifiable polarimetric SAR characteristics.

show abstract

Unsupervised classification of multifrequency and fully polarimetric SAR images based on the H/A/Alpha-Wishart classifier

Abstract: International audienceno abstrac

Cited by 316 publications

References 18 publications

Assessment of L-Band Sar Data at Different Polarization Combinations for Crop and Other Landuse Classification

Assessment of L-Band Sar Data at Different Polarization Combinations for Crop and Other Landuse Classification

A New Coherent Similarity Measure for Temporal Multichannel Scene Characterization

On polarimetric characteristics in SAR images of mesoscale cellular convection in the marine atmospheric boundary layer

Contact Info

Product

Resources

About