Feature-enhanced synthetic aperture radar image formation based on nonquadratic regularization

Çetin, Müjdat; Karl, W.C.

doi:10.1109/83.913596

Cited by 498 publications

(299 citation statements)

References 37 publications

(70 reference statements)

Supporting

Mentioning

284

Contrasting

Unclassified

Order By: Relevance

“…In order to avoid problems due to non-differentiability of the l 1 -norm [31], a smooth approximation to the l 1 -norm is used in (3):…”

Section: Scattering Centers Features Extraction With Sparse Constraintmentioning

confidence: 99%

See 1 more Smart Citation

Sar Target Classification Using Bayesian Compressive Sensing With Scattering Centers Features

Zhang¹,

Qin²,

Li³

2013

PIER

View full text Add to dashboard Cite

Abstract-The emerging field of compressed sensing provides sparse reconstruction, which has demonstrated promising results in the areas of signal processing and pattern recognition. In this paper, a new approach for synthetic aperture radar (SAR) target classification is proposed based on Bayesian compressive sensing (BCS) with scattering centers features. Scattering centers features is extracted as a l 1 -norm sparse problem on the basis of SAR observation physical model, which can improve discrimination ability compared with original SAR image. Using an overcomplete dictionary constructed by training samples, BCS is utilized to design targets classifier. For target classification performance evaluation, the proposed method is compared with several state-of-art methods through experiments on Moving and Stationary Target Acquisition and Recognition (MSTAR) public release database. Experiment results illustrate the effectiveness and robustness of the proposed approach.

show abstract

“…In order to avoid problems due to non-differentiability of the l 1 -norm [31], a smooth approximation to the l 1 -norm is used in (3):…”

Section: Scattering Centers Features Extraction With Sparse Constraintmentioning

confidence: 99%

“…To solve the problem of Equation (5), we adopt the quasi-Newton method in [31] which can account for the complex-valued nature of the SAR problem. The solution procedure is briefly described here.…”

Section: Scattering Centers Features Extraction With Sparse Constraintmentioning

confidence: 99%

Sar Target Classification Using Bayesian Compressive Sensing With Scattering Centers Features

Zhang¹,

Qin²,

Li³

2013

PIER

View full text Add to dashboard Cite

show abstract

“…Using an exhaustive search, the restoration, given in (2) with side constraint (5), is computed for all λ values within the interval [a, b]. At the end of each restoration, the kurtosis is used to determine the quality of the reconstructed image,f (λ).…”

Section: A Image Quality Measurementioning

confidence: 99%

“…Cetin and Karl [5] suggested that the side constraint function, ||f || p p with p ≤ 1, enhances point-based features and improves the resolvability of objects when there is a small number of dominant scatterers in the scene. In comparison, the function, ||∇f || p p with p ≈ 1, enhances region-based shape features that are useful for segmenting the object, shadow and background regions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic parameter selection for feature-enhanced radar image restoration

Seng

Bouzerdoum

Phung

et al. 2010

2010 IEEE Radar Conference

View full text Add to dashboard Cite

In this paper, we propose a new technique for optimum parameter selection in non-quadratic radar image restoration. Although both the regularization hyper-parameter and the norm value are influential factors in the characteristics of the formed restoration, most existing optimization methods either require memory intensive computation or prior knowledge of the noise. Here, we present a contrast measure-based method for automated hyper-parameter selection. The proposed method is then extended to optimize the norm value used in non-quadratic image formation and restoration. The proposed method is evaluated on the MSTAR public target database and compared to the GCV method. Experimental results show that the proposed method yields better image quality at a much reduced computational cost. Abstract-In this paper, we propose a new technique for optimum parameter selection in non-quadratic radar image restoration. Although both the regularization hyper-parameter and the norm value are influential factors in the characteristics of the formed restoration, most existing optimization methods either require memory intensive computation or prior knowledge of the noise. Here, we present a contrast measure-based method for automated hyper-parameter selection. The proposed method is then extended to optimize the norm value used in non-quadratic image formation and restoration. The proposed method is evaluated on the MSTAR public target database and compared to the GCV method. Experimental results show that the proposed method yields better image quality at a much reduced computational cost.

show abstract

Optimization and Learning‐Based Methods for Radar Imaging with Sparse and Limited Apertures

Saleem,

Güngör,

Alver

et al. 2023

Sparse Arrays for Radar, Sonar, and Communications

View full text Add to dashboard Cite

Feature-enhanced synthetic aperture radar image formation based on nonquadratic regularization

Cited by 498 publications

References 37 publications

Sar Target Classification Using Bayesian Compressive Sensing With Scattering Centers Features

Sar Target Classification Using Bayesian Compressive Sensing With Scattering Centers Features

Automatic parameter selection for feature-enhanced radar image restoration

Optimization and Learning‐Based Methods for Radar Imaging with Sparse and Limited Apertures

Contact Info

Product

Resources

About