Texture preserving despeckling of SAR images using GMRFs

Walessa, M.

doi:10.1109/igarss.1999.772016

Cited by 8 publications

(7 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In (11), the first expression can be solved analytically. However, the second expression, which represents the autobinomial model, is solved by subtracting log p((x i + 1)|θ i ) − log p(x i |θ i ), numerically.…”

Section: Maximum a Posteriori Information Extraction Using Auto-bimentioning

confidence: 99%

“…However, the resulting images are subject to the degradation of spatial and radiometric resolution, which can result in a loss of image information [23]. Therefore, despeckling techniques should put emphasis on speckle removal (radiometric enhancement) with texture and structure preservation to conserve spatial resolution [11].…”

Section: A Quality Of the Despecklingmentioning

confidence: 99%

“…The modeled parameters capture the essential qualities of the texture. Therefore, the textural and structural features contained in the images must be modeled to enable an accurate reconstruction in the despeckled image [11]. Many authors have proposed a MAP estimate using different models as prior, which enables information extraction through parameter estimation, and the despeckling process.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Evaluation of Bayesian Despeckling and Texture Extraction Methods Based on Gauss–Markov and Auto-Binomial Gibbs Random Fields: Application to TerraSAR-X Data

Molina

Gleich

Datcu

2012

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Speckle hinders information in synthetic aperture radar (SAR) images and makes automatic information extraction very difficult. The Bayesian approach allows us to perform the despeckling of an image while preserving its texture and structures. This model-based approach relies on a prior model of the scene. This paper presents an evaluation of two despeckling and texture extraction model-based methods using the two levels of Bayesian inference. The first method uses a Gauss-Markov random field as prior, and the second is based on an auto-binomial model (ABM). Both methods calculate a maximum a posteriori and determine the best model using an evidence maximization algorithm. Our evaluation approach assesses the quality of the image by means of the despeckling and texture extraction qualities. The proposed objective measures are used to quantify the despeckling performances of these methods. The accuracy of modeling and characterization of texture were determined using both supervised and unsupervised classifications, and confusion matrices. Real and simulated SAR data were used during the validation procedure. The results show that both methods enhance the image during the despeckling process. The ABM is superior regarding texture extraction and despeckling for real SAR images.Index Terms-Auto-binomial model (ABM), Bayesian inference, Gauss-Markov random fields (GMRF), parameter estimation, speckle reduction, synthetic aperture radar (SAR), TerraSAR-X, texture extraction.

show abstract

Section: Maximum a Posteriori Information Extraction Using Auto-bimentioning

confidence: 99%

Section: A Quality Of the Despecklingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of Bayesian Despeckling and Texture Extraction Methods Based on Gauss–Markov and Auto-Binomial Gibbs Random Fields: Application to TerraSAR-X Data

Molina

Gleich

Datcu

2012

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Therefore, the user should continue the training process of "mountains" on one of these images. In this example, we have defined "mountains" using the signal class indices derived from the estimated parameters of "model based despeckling" [26] at scales of 50 m and 100 m.…”

Section: B Calculation Of Posterior Probability and Separabilitymentioning

confidence: 99%

“…As also mentioned in the main text, the posterior distribution of after training is a Dirichlet distribution Dir (25) with the hyperparameters . Therefore, we can obtain the likelihood via integration over all as (26) where the integration extends over the allowed parameter space of as given by the normalization constraint of the likelihood. Furthermore, we obtain the variance of the likelihood as Var (27) Note, that for a strict notation, we always have to specify the state of knowledge on the right side of the conditioned probability.…”

Section: A Mean and Variance Of A Single Likelihoodmentioning

confidence: 99%

Interactive learning and probabilistic retrieval in remote sensing image archives

Schröder

Rehrauer

Seidel

et al. 2000

IEEE Trans. Geosci. Remote Sensing

107

View full text Add to dashboard Cite

We present a concept of interactive learning and probabilistic retrieval of user-specific cover types in a content-based remote sensing image archive. A cover type is incrementally defined via user-provided positive and negative examples. From these examples, we infer probabilities of the Bayesian network that link the user interests to a pre-extracted content index. Due to the stochastic nature of the cover type definitions, the database system not only retrieves images according to the estimated coverage but also according to the accuracy of that estimation given the current state of learning. For the latter, we introduce the concept of separability. We expand on the steps of Bayesian inference to compute the application-free content index using a family of data models, and on the description of the stochastic link using hyperparameters. In particular, we focus on the interactive nature of our approach, which provides instantaneous feedback to the user in the form of an immediate update of the posterior map, and a very fast, approximate search in the archive. A java-based demonstrator using the presented concept of content-based access to a test archive of Landsat TM, X-SAR, and aerial images are available over the Internet [http://www.vision.ee.ethz.ch/~rsia/ClickBayes].

show abstract