A New Classifier for Polarimetric Sar Images

Zhang, Yudong; Wu, Lenan; Wei, and Geng

doi:10.2528/pier09041905

Cited by 80 publications

(42 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A summarization including the mechanism of radar scattering and SAR imaging of the sea surface was concluded by Holt [1]. One of the most important applications of radar imaging of sea surface is ship detection and location by means of signal processing technology [2,3]. It has been generally accepted that the visibility of the sea surface wave in the SAR images is mainly due to their impact on the radar backscattered cross-section attributed to the tilt and hydrodynamic modulations.…”

Section: Introductionmentioning

confidence: 99%

Application of Facet Scattering Model in Sar Imaging of Sea Surface Waves With Kelvin Wake

Wang¹,

Min²,

Chen³

et al. 2016

PIER B

View full text Add to dashboard Cite

Abstract-The principal purpose of this work is the simulation of the ship wake in Synthetic Aperture Radar (SAR) imaging based on a facet scattering model. The hydrodynamic model of the surface waves mainly considers the Kelvin wake waves and the wind driven waves. For the prediction of radar returns from the composite surface, the semi-deterministic facet scattering model (SDFSM) is proposed, which is verified to have good performance through a comparison with the experiment by SASS-II. Then, the distributions of backscattering normalized radar cross section (NRCS) of facets are investigated for both V V and HH polarizations and characteristics of the wake pattern are shown with good visibility. On the basis of these, an application of velocity bunching (VB) imaging model is presented in detail for the simulation of SAR imaging of sea surface waves with Kelvin wake. Finally, several numerical results provide states of the effects of ship speed, wind speed and the ship sailing direction on the characteristics of Kelvin wake in SAR images. Thus, this simulation may enable us to provide a theoretical basis to the detection of ship wakes.

show abstract

Section: Introductionmentioning

confidence: 99%

Application of Facet Scattering Model in Sar Imaging of Sea Surface Waves With Kelvin Wake

Wang¹,

Min²,

Chen³

et al. 2016

PIER B

View full text Add to dashboard Cite

show abstract

“…with a more complex inner structure. In this study, the sub-area with size 600 × 600 is extracted and used for the purpose of comparing the classification results with the Wishart [3] and the NN-based [10] classifiers. The aerial photographs for this area which can be used as ground-truth are provided by the TerraServer Web site [20].…”

Section: Resultsmentioning

confidence: 99%

“…As suggested by the previous studies [14,10] appropriate texture measures for SAR imagery based on the gray level co-occurrence probabilities are included in the feature set to improve its discrimination power and classification accuracy. In this study, contrast, correlation, energy, and homogeneity features are extracted from normalized GLCMs which are calculated using interpixel distance of 2 and averaging over four possible orientation settings (θ = 0…”

Section: Feature Extractionmentioning

confidence: 99%

“…In [6], a new wavelet-based texture image segmentation algorithm is successfully applied to unsupervised SAR image segmentation problem. More recently, neural network based approaches [10,11] for classification of polarimetric synthetic aperture radar data have been shown to outperform other aforementioned well-known techniques. Compared with other approaches, neural network classifiers have the advantage of adaptability to the data without making a priori assumption of a particular probability model or distribution.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Polarimetric SAR Image Classification Using Radial Basis Function Neural Network

İnce¹

2010

PIERS Online

View full text Add to dashboard Cite

Abstract-This paper presents a robust radial basis function (RBF) network based classifier for polarimetric synthetic aperture radar (SAR) images. The proposed feature extraction process utilizes the covariance matrix, the gray level co-occurrence matrix (GLCM) based texture features, and the backscattering power (Span) combined with the H/α/A decomposition, which are projected onto a lower dimensional feature space using principal component analysis. For the classifier training two popular techniques are explored: conventional backpropagation (BP) and particle swarm optimization (PSO). By using both polarimetric covariance matrix and decomposition based pixel values and textural information (contrast, correlation, energy, and homogeneity) in the feature set, classification accuracy is improved. An experimental study is performed using the fully polarimetric San Francisco Bay and Flevoland data sets acquired by the NASA/Jet Propulsion Laboratory Airborne SAR (AIRSAR) at L-band to evaluate the performance of the proposed classifier. Classification results (in terms of confusion matrix, overall accuracy and classification map) compared with competing state of the art algorithms demonstrate the effectiveness of the proposed RBF network classifier.

show abstract

“…These applications include land use/land cover mapping [1][2][3][4][5][6][7][8][9], change detection, hazard monitoring and damage assessment, surface geophysical parameters retrieval [10], biomass and forest height estimation, etc. [11].…”

Section: Introductionmentioning

confidence: 99%

An Improved Sar Radiometric Terrain Correction Method and Its Application in Polarimetric Sar Terrain Effect Reduction

Chen¹

2013

PIER B

View full text Add to dashboard Cite

Abstract-A new SAR radiometric terrain correction method was proposed to reduce the terrain effects in sloped regions. Based on this method, a procedure for polarimetric SAR terrain effect reduction was proposed, including geometric correction, shadow detection, radiometric terrain correction, and polarization orientation angle shift compensation. Experiments using RADARSAT-2 polarimetric SAR data of the Three Gorges Area, China demonstrated the effectiveness of the proposed radiometric terrain correction method. Both visual and quantitative analyses showed that after the proposed radiometric terrain correction method was applied, the contrast between different slopes that caused by local incidence angle differences, foreshortening, and layover was significantly reduced. The difference of backscattering intensity on slopes facing the radar sensor and facing away from the sensor was reduced from 12.5 dB before radiometric correction to 1.3 dB. The overall accuracy of land use/land cover classification was improved by 11.2 percent using the terrain corrected polarimetric SAR data.

show abstract

A New Classifier for Polarimetric Sar Images

Cited by 80 publications

References 25 publications

Application of Facet Scattering Model in Sar Imaging of Sea Surface Waves With Kelvin Wake

Application of Facet Scattering Model in Sar Imaging of Sea Surface Waves With Kelvin Wake

Polarimetric SAR Image Classification Using Radial Basis Function Neural Network

An Improved Sar Radiometric Terrain Correction Method and Its Application in Polarimetric Sar Terrain Effect Reduction

Contact Info

Product

Resources

About