Watershed identification of polygonal patterns in noisy SAR images

Moreels, Pierre; Smrekar, S. E.

doi:10.1109/tip.2003.814254

Cited by 19 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The watershed algorithm [12] is used frequently for oversegmenting images. For comparison, classification maps using the proposed method, a Gaussian MRF (GMRF)-based method [3], a watershed-based method, and a pixel-based ML [10] are Fig.…”

Section: A Classification Of Fully Polarimetric Sar Datamentioning

confidence: 99%

Region-Based Classification of Polarimetric SAR Images Using Wishart MRF

Wang

et al. 2008

IEEE Geosci. Remote Sensing Lett.

150

View full text Add to dashboard Cite

The scattering measurements of individual pixels in polarimetric SAR images are affected by speckle; hence, the performance of classification approaches, taking individual pixels as elements, would be damaged. By introducing the spatial relation between adjacent pixels, a novel classification method, taking regions as elements, is proposed using a Markov random field (MRF). In this method, an image is oversegmented into a large amount of rectangular regions first. Then, to use fully the statistical a priori knowledge of the data and the spatial relation of neighboring pixels, a Wishart MRF model, combining the Wishart distribution with the MRF, is proposed, and an iterative conditional mode algorithm is adopted to adjust oversegmentation results so that the shapes of all regions match the ground truth better. Finally, a Wishart-based maximum likelihood, based on regions, is used to obtain a classification map. Real polarimetric images are used in experiments. Compared with the other three frequently used methods, higher accuracy is observed, and classification maps are in better agreement with the initial ground maps, using the proposed method.

show abstract

Section: A Classification Of Fully Polarimetric Sar Datamentioning

confidence: 99%

Region-Based Classification of Polarimetric SAR Images Using Wishart MRF

Wang

et al. 2008

IEEE Geosci. Remote Sensing Lett.

150

View full text Add to dashboard Cite

show abstract

“…Its applications can be found in speech processing [10], fault diagnosis [11], fingerprint matching [12], DNA classification [13], and satellite image processing [14], to name a few. The basic idea of a correlationbased pattern recognition scheme is to correlate the signal being analyzed with a known template [15], [16] and make decisions based on the magnitude of the correlation coefficients.…”

Section: Correlation-based Pattern Recognition In Time-frequency mentioning

confidence: 99%

Selective Regional Correlation for Pattern Recognition

Sejdić

Jiang

2007

IEEE Trans. Syst., Man, Cybern. A

View full text Add to dashboard Cite

In this paper, a novel correlation-based pattern classifier that relies on the analysis of time-frequency decomposition of a template and signals is proposed. Significant improvements in resolution and accuracy are obtained using this new classifier when compared to a conventional correlation-based one. The short-time Fourier transform, continuous wavelet transform, and S-transform are considered in the time-frequency decomposition process. To evaluate the performance of the proposed scheme, numerical studies are performed on a set of synthetic test signals, and excellent results have been obtained. This paper also presents an illustrative example where two types of heart sounds are classified. The classification error percentage for the heart sounds using the new classifier is only 6.670% as compared to 56.67% when a general correlation-based classifier is used.

show abstract

“…The use of conventional edge detection filter techniques of lineament recognition has recently been criticized (Moreels and Smrekar 2003). In this study the application of these filters on the SAR images made the lineament pattern distribution very complex, by introducing many linear features that do not correspond to any to geological element; this increased the difficulty of lineament patterns interpretation.…”

Section: Image Processing and Enhancementmentioning

confidence: 99%

Comparison between remote sensed lineaments and geological structures in intensively cultivated hills (Monferrato and Langhe domains, NW Italy)

Morelli¹,

Piana

2006

International Journal of Remote Sensing

View full text Add to dashboard Cite

Stereo and panchromatic Spot HRV and GTC ERS-2 SAR images were used to study the correspondence between the lineament systems and geological structures of hills composed of marly-arenaceous sediments with rich vegetation and extensive human activities, namely the Monferrato and Langhe domains (north-west Italy). In this context, a large number of lineaments are usually found and their correspondence with geological structures is mainly non-direct. Since the lineaments belonged to homogeneous, well-represented geometrical families, 'geometrical filters' were used to reduce the complexity of the lineament patterns. The lineaments were statistically analysed and four systems were individuated for each domain. Comparison between the lineaments and the geological structures revealed distinct geometrical and distribution similarities. The geological meaning of the lineaments has been thus investigated. In the highly deformed Monferrato domain it was determined by comparison with the detailed geological model, whereas in the poorly and uniformly deformed Langhe comparison was made with mesostructural analysis and the geometry of its drainage network. The good correspondences in both domains are probably due to a structural control during their geomorphological evolution that is, driven by recent relevant uplifting. The use of lineaments as discontinuities to simulate fracture networks at different scales is allowed in the study case, in view of their geometrical similarities with geological structures.

show abstract

Watershed identification of polygonal patterns in noisy SAR images

Cited by 19 publications

References 23 publications

Region-Based Classification of Polarimetric SAR Images Using Wishart MRF

Region-Based Classification of Polarimetric SAR Images Using Wishart MRF

Selective Regional Correlation for Pattern Recognition

Comparison between remote sensed lineaments and geological structures in intensively cultivated hills (Monferrato and Langhe domains, NW Italy)

Contact Info

Product

Resources

About