Classification of multifrequency polarimetric SAR imagery using a dynamic learning neural network

Chen, K.S.; Huang, Wenqing; Tsay, David; Amar, F.

doi:10.1109/36.499786

Cited by 150 publications

(74 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One type relied on coefficients of radar backscatter [53][54][55][56][57] and the other type used decomposition maps, which are based on physical scattering mechanisms [23,27,[29][30][31]34,[46][47][48]. In this study, we compared classification results derived from PolSAR decomposition with those derived from optical satellite image data.…”

Section: Methodsmentioning

confidence: 99%

Evaluation of Polarimetric SAR Decomposition for Classifying Wetland Vegetation Types

et al. 2015

View full text Add to dashboard Cite

Abstract:The Florida Everglades is the largest subtropical wetland system in the United States and, as with subtropical and tropical wetlands elsewhere, has been threatened by severe environmental stresses. It is very important to monitor such wetlands to inform management on the status of these fragile ecosystems. This study aims to examine the applicability of TerraSAR-X quadruple polarimetric (quad-pol) synthetic aperture radar (PolSAR) data for classifying wetland vegetation in the Everglades. We processed quad-pol data using the Hong & Wdowinski four-component decomposition, which accounts for double bounce scattering in the cross-polarization signal. The calculated decomposition images consist of four scattering mechanisms (single, co-and cross-pol double, and volume scattering). We applied an object-oriented image analysis approach to classify vegetation types with the decomposition results. We also used a high-resolution multispectral optical RapidEye image to compare statistics and classification results with Synthetic Aperture Radar (SAR) observations. The calculated classification accuracy was higher than 85%, suggesting that the TerraSAR-X quad-pol SAR signal had a high potential for distinguishing different vegetation types. Scattering components from SAR acquisition were particularly advantageous for classifying mangroves along tidal channels. OPEN ACCESSRemote Sens. 2015, 7 8564We conclude that the typical scattering behaviors from model-based decomposition are useful for discriminating among different wetland vegetation types.

show abstract

Section: Methodsmentioning

confidence: 99%

Evaluation of Polarimetric SAR Decomposition for Classifying Wetland Vegetation Types

et al. 2015

View full text Add to dashboard Cite

show abstract

“…In order to improve the classification accuracy the backscattering values with combination of multi temporal and mutli polarization of RISAT -1 and EnviSat ASAR are used for primary level of classification. Maximum likelihood (Lee et al, 1994), Neural Network (Chen et al, 1996, Ito et al, 1998 and Support Vector Machine (Fukuda et al, 2002) The training sets (ROI) were chosen from the imagery with help of ground truth and optical imagery of Resourcesat 2 LISS IV data (09-Nov-2011) for supervised classification and applied for all the combination. The supervised classifiers namely ML, NN and SVM work carried out in Envi 4.8 image processing software.…”

Section: Methodsmentioning

confidence: 99%

Study of Discrimination Between Plantation and Dense Scrub Based on Backscattering Behavior of C Band SAR Data

Iyyappan

Ramakrishnan

Raju

2014

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:The study about on landuse and landcover classification using multi polarization and multi temporal C-band Synthetic Aperture Radar (SAR) data of recently launched multi-mode of RISAT-1 (Radar Imaging Satellite) by Indian Space Research Organization (ISRO) and European satellite, Envisat ASAR data. The backscattering coefficient were extracted for various land features from Cband SAR data. The training sample collecting from satellite optical imagery of study and field visit for verification. The training samples are used for the supervised classification technique of maximum Likelihood (ML) algorithms, Neural Network (NN) and Support Vector Machine (SVM) algorithms were applied for fourteen different polarizations combination of multi temporal and multiple polarizations. The previous study was carried only four band combination of RISAT 1 data, the continuation of work both SAR data were used in this study. The Classification results are verified with confusion matrix. The pixel based classification gives the good results in the dual polarization of CRS -HH and HV of RISAT -1 compared to dual polarization Envisat ASAR data. Meanwhile the quad Polarization combination of Envisat ASAR data got better classification accuracy. The SVM classifiers has given better classification results for all band combination followed by ML and NN. The Scrub are better identified in EnviSat

show abstract

“…During the past years, various methods were employed for classification of polarimetric SAR data, based on the maximum likelihood [1], artificial neural networks [2] [3], support vector machines [4], fuzzy methods [5] or other approaches [6] [7]. In this paper we develop a semiautomatic algorithm for SAR classification using solely the amplitude data and not the complex data as the approaches above.…”

Section: Introductionmentioning

confidence: 99%

High resolution SAR-image classification by Markov random fields and finite mixtures

2010

View full text Add to dashboard Cite

In this paper we develop a novel classification approach for high and very high resolution polarimetric synthetic aperture radar (SAR) amplitude images. This approach combines the Markov random field model to Bayesian image classification and a finite mixture technique for probability density function estimation. The finite mixture modeling is done via a recently proposed dictionary-based stochastic expectation maximization approach for SAR amplitude probability density function estimation. For modeling the joint distribution from marginals corresponding to single polarimetric channels we employ copulas. The accuracy of the developed semiautomatic supervised algorithm is validated in the application of wet soil classification on several high resolution SAR images acquired by TerraSAR-X and COSMO-SkyMed.

show abstract

Classification of multifrequency polarimetric SAR imagery using a dynamic learning neural network

Cited by 150 publications

References 10 publications

Evaluation of Polarimetric SAR Decomposition for Classifying Wetland Vegetation Types

Evaluation of Polarimetric SAR Decomposition for Classifying Wetland Vegetation Types

Study of Discrimination Between Plantation and Dense Scrub Based on Backscattering Behavior of C Band SAR Data

High resolution SAR-image classification by Markov random fields and finite mixtures

Contact Info

Product

Resources

About