SAR Image Classification Through Information-Theoretic Textural Features, MRF Segmentation, and Object-Oriented Learning Vector Quantization

D'Elia, C.; Ruscino, Simona; Abbate, Maurizio; Aiazzi, Bruno; Baronti, Stefano; Alparone, Luciano

doi:10.1109/jstars.2014.2304700

Cited by 44 publications

(22 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MRF is widely used in SAR images' interpretation; it captures the spatial interactions among neighborhoods as prior knowledge to guide classification. For instance, Elia [24] proposed a MRF model based on the regional and statistic texture; Voisin [25] put forward a multilayer MRF model based on texture information. However, with only local potential relationships considered in MRF, the connections among all observation data are ignored.…”

Section: Sar Images Classificationmentioning

confidence: 99%

Hierarchical Terrain Classification Based on Multilayer Bayesian Network and Conditional Random Field

Fan

Feng

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

This paper presents a hierarchical classification approach for Synthetic Aperture Radar (SAR) images. The Conditional Random Field (CRF) and Bayesian Network (BN) are employed to incorporate prior knowledge into this approach for facilitating SAR image classification.(1) A multilayer region pyramid is constructed based on multiscale oversegmentation, and then, CRF is used to model the spatial relationships among those extracted regions within each layer of the region pyramid; the boundary prior knowledge is exploited and integrated into the CRF model as a strengthened constraint to improve classification performance near the boundaries. (2) Multilayer BN is applied to establish the causal connections between adjacent layers of the constructed region pyramid, where the classification probabilities of those sub-regions in the lower layer, conditioned on their parents' regions in the upper layer, are used as adjacent links. More contextual information is taken into account in this framework, which is a benefit to the performance improvement. Several experiments are conducted on real ESAR and TerraSAR data, and the results show that the proposed method achieves better classification accuracy.

show abstract

Section: Sar Images Classificationmentioning

confidence: 99%

Hierarchical Terrain Classification Based on Multilayer Bayesian Network and Conditional Random Field

Fan

Feng

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The MRF was developed and used for the first time in the context of statistical physics to study the phase transition. Since an image could be considered as a graph with discrete labels, the MRF was adopted in image processing [43] such as classification [44], change detection [45], DEM reconstruction [37], and SAR image despeckling [46].…”

Section: Overview Of Mrfmentioning

confidence: 99%

A Joint Markov Random Field Approach for SAR Interferogram Filtering and Unwrapping

Abdallah

Abdelfattah

2016

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

This paper presents a new integrated interferometric synthetic aperture radar (InSAR) phase filtering and unwrapping method based on a Markov random field (MRF) model. This approach aims to estimate a noiseless unwrapped phase from the observed noisy interferogram. The phase image is modeled using a joint MRF with a corresponding energy function related simultaneously to noise filtering and phase unwrapping (PU). This function contains two parts: the first is for interferogram filtering process and the second aims to unwrap this filtered phase. The filtered unwrapped phase image is estimated by minimizing the proposed energy function using the genetic algorithm (GA). The proposed approach is tested and validated on simulated and real interferograms acquired with the Radarsat-2, ERS-2, and Envisat satellites acquired over two distinct regions in Tunisia (Mahdia and Ben Guerden) with different geographical characteristics. The obtained results show a significant improvement with respect to other simultaneously filtering and unwrapping algorithms.Index Terms-Genetic algorithm (GA), InSAR phase filtering, Markov random field (MRF), phase unwrapping (PU).

show abstract

“…Image segmentation is a critical prerequisite for use of SAR images; but these images cannot be segmented with conventional current methods because they can be affected by speckle noise, which can effect SAR image processing [1,2]. Speckle noise reduction is essential to the use of SAR images [1,3].…”

Section: Iintroductionmentioning

confidence: 99%

“…In SAR imaging, scattering mechanisms construct local statistical characteristics with different images and speckle noise can cause more diversity because of the invariability of SAR images [2]. A number of methods have been used to filter speckle noise.…”

Section: Iintroductionmentioning

confidence: 99%

Despeckling algorithm for remote sensing synthetic aperture radar images using multi-scale curvelet transform

Kooshesh

Akbarizadeh

2015

2015 the International Symposium on Artificial Intelligence and Signal Processing (AISP)

View full text Add to dashboard Cite

The goal of the present research is to despeckle SAR images, which is critical for segmentation and target recognition in satellite SAR images. When a despeckling algorithm is applied to a SAR image, important information such as the edges, corners, textures, and object parts will degrade. Curvelet transform is a recently proposed form of multi-scale analysis that achieves better performance of wavelet and Gabor transforms in edge and curve detection. This is a geometric transform that is useful for SAR image processing. For unsupervised texture images, segmentation is different and distinct from the textures, so the textures at the boundary noises will disappear. Curvelet transform has produced good results in the detection of curved edges with higher accuracy in finding the orientation than wavelet transforms. The present study uses fast discrete curvelet transform (FDCT) based on wresting and uses unsupervised adaptive threshold learning to develop a new despeckling algorithm for SAR images. In the proposed algorithm, each segment of the SAR image can be learned for selection of its adaptive threshold. Simulation results demonstrate that the proposed algorithm performs better than similar methods.

show abstract

SAR Image Classification Through Information-Theoretic Textural Features, MRF Segmentation, and Object-Oriented Learning Vector Quantization

Cited by 44 publications

References 32 publications

Hierarchical Terrain Classification Based on Multilayer Bayesian Network and Conditional Random Field

Hierarchical Terrain Classification Based on Multilayer Bayesian Network and Conditional Random Field

A Joint Markov Random Field Approach for SAR Interferogram Filtering and Unwrapping

Despeckling algorithm for remote sensing synthetic aperture radar images using multi-scale curvelet transform

Contact Info

Product

Resources

About