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

Molina, Daniela Espinoza; Gleich, Dušan; Datcu, Mihai

doi:10.1109/tgrs.2011.2169679

Cited by 28 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The notation β i ∼ β j means there is an edge between vertices β i and β j in G β . The graph can be interpreted by means of the Gauss-Markov random fields (see Gleich and Datcu [18], Anandkumar et al [19], Rombaut et al [20], Fang and Li [21], Vats and Moura [22], Molina et al [23], and Borri et al [24] for more details on this topic and applications), the pairwise Markov property implies ¬β i ∼ β j equivalent to β i conditional independence to β j in V \ {β i , β j }. This property leads to the following choice of matrix Ξ:…”

Section: Ontology Sparse Vector Learningmentioning

confidence: 99%

Graph Learning-Based Ontology Sparse Vector Computing

Wu¹,

Sangaiah

Gao

2020

Symmetry

View full text Add to dashboard Cite

The ontology sparse vector learning algorithm is essentially a dimensionality reduction trick, i.e., the key components in the p-dimensional vector are taken out, and the remaining components are set to zero, so as to obtain the key information in a certain ontology application background. In the early stage of ontology data processing, the goal of the algorithm is to find the location of key components through the learning of some ontology sample points, if the relevant concepts and structure information of each ontology vertex with p-dimensional vectors are expressed. The ontology sparse vector itself contains a certain structure, such as the symmetry between components and the binding relationship between certain components, and the algorithm can also be used to dig out the correlation and decisive components between the components. In this paper, the graph structure is used to express these components and their interrelationships, and the optimal solution is obtained by using spectral graph theory and graph optimization techniques. The essence of the proposed ontology learning algorithm is to find the decisive vertices in the graph Gβ. Finally, two experiments show that the given ontology learning algorithm is effective in similarity calculation and ontology mapping in some specific engineering fields.

show abstract

Section: Ontology Sparse Vector Learningmentioning

confidence: 99%

Graph Learning-Based Ontology Sparse Vector Computing

Wu¹,

Sangaiah

Gao

2020

Symmetry

View full text Add to dashboard Cite

show abstract

“…This process narrows down the probability density function of speckle and reduces the variance by a factor of L. However, it also reduces the ground resolution of the image with proportion of the number of looks. To overcome this problem, an alternative type of approaches has been proposed based on posterior speckle filtering techniques both in frequency domain and in spatial domain [14][15][16]. Some reviews of the connections and evolutions of the filtering algorithms has been made by [17].…”

Section: Related Workmentioning

confidence: 99%

Structure Preserving Sar Image Despeckling via L0-Minimization

Liu¹,

Yang²,

Xia³

et al. 2013

PIER

View full text Add to dashboard Cite

Abstract-In this paper, we propose a new method for synthetic aperture radar (SAR) image despeckling via L0-minimization strategy, which aims to smooth homogeneous areas while preserve significant structures in SAR images. We argue that the gradients of the despeckled images are sparse and can be pursued by L0-norm minimization. We then formularize the despeckling of SAR images as a global L0 optimization problem with difference of average operations. Namely, the number of pixels with difference of average that are unequal to one is controlled to approximate prominent structures in a sparsity-control manner. Finally, a numerical algorithm is employed to solve the L0 minimization problem. In contrast with existing SAR image despeckling approaches, this strategy is applied without necessity to consider the local features or structures. The performance of our method is tested on high-resolution X-band SAR images. The experimental results show that the proposed method achieves state-ofthe-art results in terms of the equivalent-number-of-looks measure and the edge-preserving index.

show abstract

“…The spatial-domain methods calculate the estimated pixels by sliding a window over the entire image [2], while the frequency-domain methods such as Wavelets [3] and contourlets [4,5] improve the performance of speckle reduction by representing the SAR image features more sparsely or accurately. By analyzing geometrical structures of SAR images in frequency domain [6,7], the latter kind optimizes the threshold determination strategy [8] to represent many detailed features with fewer high-magnitude transform coefficients.…”

Section: Introductionmentioning

confidence: 99%

Synthetic aperture radar image despeckling using convolutional neural networks in wavelet domain

Liu

2022

IET Image Processing

View full text Add to dashboard Cite

It is difficult for a convolutional neural network (CNN) to capture the detailed features of synthetic aperture radar (SAR) images when increasing the network depth. To capture sufficient information for reconstructing image details, the authors propose a multidirectional and multiscale convolutional neural network (MMCNN) in which the wavelet subband is input into each independent subnetwork to be trained. Each subnetwork has few convolution layers and a loss function. When the loss function reaches its optimal value, all subbands are integrated to produce the despeckled SAR image through the inverse Wavelet transform. The proposed MMCNN consisting of multiple subnetworks extracts the detailed features and suppresses speckle noise from different directions and scales; thus, its performance is improved by broadening the network width rather than increasing the depth. Experimental results on synthetic and real SAR images show that the proposed method shows superior performance over the state-of-the-art methods in terms of both quantitative assessments and subjective visual quality, especially for strong speckle noise.

show abstract

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

Cited by 28 publications

References 27 publications

Graph Learning-Based Ontology Sparse Vector Computing

Graph Learning-Based Ontology Sparse Vector Computing

Structure Preserving Sar Image Despeckling via L0-Minimization

Synthetic aperture radar image despeckling using convolutional neural networks in wavelet domain

Contact Info

Product

Resources

About