Results

**1 - 9**of**9**### THE LOW BACKSCATTERING TARGETS CLASSIFICATION IN URBAN AREAS

"... The Polarimetric and Interferometric Synthetic Aperture Radar (POLINSAR) is widely used in urban area nowadays. Because of the physical and geometric sensitivity, the POLINSAR is suitable for the city classification, power-lines detection, building extraction, etc. As the new X-band POLINSAR radar, ..."

Abstract
- Add to MetaCart

The Polarimetric and Interferometric Synthetic Aperture Radar (POLINSAR) is widely used in urban area nowadays. Because of the physical and geometric sensitivity, the POLINSAR is suitable for the city classification, power-lines detection, building extraction, etc. As the new X-band POLINSAR radar, the china prototype airborne system, XSAR works with high spatial resolution in azimuth (0.1m) and slant range (0.4m). In land applications, SAR image classification is a useful tool to distinguish the interesting area and obtain the target information. The bare soil, the cement road, the water and the building shadow are common scenes in the urban area. As it always exists low backscattering sign objects (LBO) with the similar scattering mechanism (all odd bounce except for shadow) in the XSAR images, classes are usually confused in Wishart-H-Alpha and Freeman-Durden methods. It is very hard to distinguish those targets only using the general information. To overcome the shortage, this paper explores an improved algorithm for LBO refined classification based on the Pre-Classification in urban areas. Firstly, the Pre-Classification is applied in the polarimetric datum and the mixture class is marked which contains LBO. Then, the polarimetric covariance matrix C3 is re-estimated on the Pre-Classification results to get more reliable results. Finally, the occurrence space which combining the entropy and the phase-diff standard deviation between HH and VV channel is used to refine the Pre-Classification results. The XSAR airborne experiments show the improved method is potential to distinguish the mixture classes in the low backscattering objects. 1.

### POLSAR CLASSIFICATION BASED ON THE SIRV MODEL WITH A REGION GROWING INITIALIZATION

"... Polarimetry has been studied for many years in SAR. Due to the enormous quantity of SAR images acquired by satellites or airborne systems, there is an evident need for efficient automatic analysis tools. Classification algorithms are one of the main applications for PoLSAR data. Nowadays, fully pola ..."

Abstract
- Add to MetaCart

(Show Context)
Polarimetry has been studied for many years in SAR. Due to the enormous quantity of SAR images acquired by satellites or airborne systems, there is an evident need for efficient automatic analysis tools. Classification algorithms are one of the main applications for PoLSAR data. Nowadays, fully polarimetric high resolution sensors can commonly reach up to decimeter resolutions. This yields a higher heterogeneity in the clutter, especially in urban areas, where the clutter can no longer be modeled as a Gaussian process. Recent advances in the field of SIRV (Spherically Invariant Random Vectors) allow the modeling of non-Gaussian clutter as a compound Gaussian process. In this paper, we propose to apply a region growing process as an initialization to a SIRV based classification technique. As the region growing process is shape constrained, spatial features are better delineated and the samples used for the estimation of the coherency matrices are more adapted. Then a statistical clustering technique adapted to the SIRV model is applied to retrieve similarities between regions in the whole image.

### Author manuscript, published in "6th International Workshop on Science and Applications of SAR Polarimetry and Polarimetric Interferometry, Frascati: Italy (2013)" POINCARÉ SPHERE REPRESENTATION OF INDEPENDENT SCATTERING SOURCES: APPLICATION ON DISTRIBUTE

, 2013

"... This paper introduces Independent Component Analysis (ICA) to the Incoherent Target Decomposition theory (ICDT) through the particular application- snow cover analysis. Given that the equivalence of the currently used eigenvalue decomposition and Principal Component Analysis (PCA) can be stated unde ..."

Abstract
- Add to MetaCart

(Show Context)
This paper introduces Independent Component Analysis (ICA) to the Incoherent Target Decomposition theory (ICDT) through the particular application- snow cover analysis. Given that the equivalence of the currently used eigenvalue decomposition and Principal Component Analysis (PCA) can be stated under certain constraints, the goal is to generalise ICDT in the context of Blind Source Separation (family of techniques comprising both PCA and ICA). This generalisation allows independent non-orthogonal backscattering mechanisms retrieval in case of non-Gaussian polarimetric clutter. The obtained independent target vectors are parametrized using the Target Scattering Vector Model (TSVM) [1]. The algorithm is applied on a distributed target- snow cover, and the obtained parameters are illustrated and appropriately interpreted using the Poincaré sphere. Key words: target decomposition, independent component analysis, Poincaré sphere, snow cover. 1.

### Australia (2013)" INDEPENDENT COMPONENT ANALYSIS WITHIN POLARIMETRIC INCOHERENT TARGET DECOMPOSITION

, 2013

"... 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 ..."

Abstract
- Add to MetaCart

(Show Context)
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 [1, 2]. This is done by parametrising the obtained dominant and mutually independent target vectors using the TSVM [3] and representing them on the corresponding Poincaré sphere. We demonstrate notably good performances of the proposed method applied on the RAM-SES 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.

### 1An Automatic U-distribution and Markov Random Field Segmentation Algorithm for PolSAR Images.

"... Abstract—We recently presented a novel unsupervised, non-Gaussian and contextual clustering algorithm for segmentation of polarimetric SAR images [1]. This represents one of the most advanced PolSAR unsupervised statistical segmentation algo-rithms and uses the doubly flexible, two parameter, U-dist ..."

Abstract
- Add to MetaCart

(Show Context)
Abstract—We recently presented a novel unsupervised, non-Gaussian and contextual clustering algorithm for segmentation of polarimetric SAR images [1]. This represents one of the most advanced PolSAR unsupervised statistical segmentation algo-rithms and uses the doubly flexible, two parameter, U-distribution model for the PolSAR statistics and includes a Markov Random Field approach for contextual smoothing. A goodness-of-fit testing stage adds a statistically rigorous approach to determine the significant number of classes. The fully automatic, algorithm was demonstrated with good results for both simulated and real data-sets. This paper discusses a re-thinking of the overall strategy and leads to some simplifications. The primary issue was that the Markov random field optimisation depends on the number of classes and did not behave well under the split-and-merge environment. We explain the reasons behind a separation of the cluster evaluation from the contextual smoothing as well as a modified rationale for the adaptive number of classes. Both aspects have simplified the overall algorithm whilst maintaining good visual results.

### Article Improved POLSAR Image Classification by the Use of Multi-Feature Combination

"... remote sensing ..."

### CFAR HIERARCHICAL CLUSTERING OF POLARIMETRIC SAR DATA

"... Recently, a general approach for high-resolution polarimetric SAR (POLSAR) data classification in heterogeneous clutter was presented, based on a statistical test of equality of co-variance matrices. Here, we extend that approach by taking advantage of the Constant False Alarm Ratio (CFAR) prop-erty ..."

Abstract
- Add to MetaCart

(Show Context)
Recently, a general approach for high-resolution polarimetric SAR (POLSAR) data classification in heterogeneous clutter was presented, based on a statistical test of equality of co-variance matrices. Here, we extend that approach by taking advantage of the Constant False Alarm Ratio (CFAR) prop-erty of the statistical test in order to improve the clustering process. We show that the CFAR property can be used in the hierarchical segmentation of the POLSAR data images to automatically detect the number of clusters. We test the pro-posed method on a high-resolution polarimetric data set ac-quired by the ONERA RAMSES system and compare them to previous results on the same dataset. 1.

### Hartigan’s method for k-MLE: Mixture modeling with Wishart distributions

"... and its application to motion retrieval ..."

(Show Context)
### ON THE USE OF THE HOTELLING’S T 2 STATISTIC FOR THE HIERARCHICAL CLUSTERING OF HYPERSPECTRAL DATA

"... In this work we propose a hierarchical clustering methodol-ogy for hyperspectral data based on the Hotelling’s T 2 statis-tic. For each hypespectral sample data, the statistical sam-ple mean is calculated using a window-based neighborhood. Then, the pairwise similarities between any two hyperspec-tr ..."

Abstract
- Add to MetaCart

(Show Context)
In this work we propose a hierarchical clustering methodol-ogy for hyperspectral data based on the Hotelling’s T 2 statis-tic. For each hypespectral sample data, the statistical sam-ple mean is calculated using a window-based neighborhood. Then, the pairwise similarities between any two hyperspec-tral samples are computed based on the Hotelling’s T 2 statis-tic. This statistic assumes a Gaussian distribution of the data while hyperspectral data have been observed to be long tailed distributed. In order to improve the statistic robustness we use the Fixed Point estimates, and compare them to the clas-sical sample mean estimator. The similarities are then used to hierarchically cluster the hyperspectral data. We give some preliminary qualitative results of the proposed approach over the Indian Pines hyperspectral scene. Results show that the use of the Fixed Point estimator does not significantly affect the clustering results. Further work will be focused on the use of the robust Hotelling statistic. Index Terms — hypespectral imaging, hierarchical clus-tering, Fixed Point estimates 1.