MUM (Merge Using Moments) segmentation for SAR images

Cook, R. D.; McConnell, Ian; Oliver, C.J.; Welbourne, E.

doi:10.1117/12.197529

Cited by 50 publications

(32 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our RAG scheme was inspired by [14] that considered the size and the length of the common frontier along the regions created by the region growing process. Differently from the aforementioned work we use the ratio of the averages of border pixels combined with size and length features.…”

Section: The Proposed Cost Functionmentioning

confidence: 99%

See 1 more Smart Citation

SAR imagery segmentation by statistical region growing and hierarchical merging

Carvalho

Ushizima

Medeiros

et al. 2010

Digital Signal Processing

View full text Add to dashboard Cite

This paper presents an approach to accomplish synthetic aperture radar (SAR) image segmentation, which are corrupted by speckle noise. Some ordinary segmentation techniques may require speckle filtering previously. Our approach performs radar image segmentation using the original noisy pixels as input data, eliminating preprocessing steps, an advantage over most of the current methods. The algorithm comprises a statistical region growing procedure combined with hierarchical region merging to extract regions of interest from SAR images. The region growing step oversegments the input image to enable region aggregation by employing a combination of the KolmogorovSmirnov (KS) test with a hierarchical stepwise optimization (HSWO) algorithm for the process coordination. We have tested and assessed the proposed technique on artificially speckled image and real SAR data containing different types of targets 1 .

show abstract

Section: The Proposed Cost Functionmentioning

confidence: 99%

“…The strategy used in this paper is to aggregate statistically homogeneous regions to create new segments. We use an initial set of regions to carry out automatic segmentation by merging using moments (MUM) [14].…”

Section: Introductionmentioning

confidence: 99%

SAR imagery segmentation by statistical region growing and hierarchical merging

Carvalho

Ushizima

Medeiros

et al. 2010

Digital Signal Processing

View full text Add to dashboard Cite

show abstract

“…Using (3) The second term in (6) for the entire image is consequently equal to p. Hence, only the fourth term in (6) …”

Section: B Polarimetric Sarmentioning

confidence: 99%

“…Another approach is to perform segment merging in an initially over-segmented image using an appropriate test statistic. This approach has for instance been used for single channel SAR images in the MUM (Merging Using Moments) segmentation algorithm described in [5] [6].…”

Section: Introductionmentioning

confidence: 99%

Evaluation of the Wishart test statistics for polarimetric SAR data

Skriver

Nielsen

Conradsen

IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477)

View full text Add to dashboard Cite

Abstract-A test statistic for equality of two covariance matrices following the complex Wishart distribution has previously been used in new algorithms for change detection, edge detection and segmentation in polarimetric SAR images. Previously, the results for change detection and edge detection have been quantitatively evaluated. This paper deals with the evaluation of segmentation. A segmentation performance measure originally developed for single-channel SAR images has been extended to polarimetric SAR images, and used to evaluate segmentation for a mergeusing-moment algorithm for polarimetric SAR data.

show abstract

“…The segmentations algorithms evaluated in this paper are: the MUM [2] and the RWSEG [8]. They both produce segmentations based on gray-levels, modeled by the square root of Gamma distribution only, and they also assume that the pixel values in an image are uncorrelated.…”

Section: Segmentation Algorithmsmentioning

confidence: 99%

SAR segmentation algorithms: a quantitative assessment

Frery¹,

Lucca

Freitas

et al.

IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293)

View full text Add to dashboard Cite

~ This paper compareethe performance of two segmentation tttgaithms, the MUM (Merge Usinghrloments) and RWSEG, using simulatea3yn+h& Aperture Radar (SAR) data. This amparison is performed from b t h the qualitative and quantitative-pohrs o€ *and carried out using synthetic contain regions WTth different homogeneity applications. The process for onsists of creating an idealized which summarizes thhe-mi%n -m e t r i c and topologic charac€er&ks Q€ Amazonian targets.observations from each dmis expesiaceis performed.Then a stati%tkz& pmgosed, and a M

show abstract

MUM (Merge Using Moments) segmentation for SAR images

Cited by 50 publications

References 0 publications

SAR imagery segmentation by statistical region growing and hierarchical merging

SAR imagery segmentation by statistical region growing and hierarchical merging

Evaluation of the Wishart test statistics for polarimetric SAR data

SAR segmentation algorithms: a quantitative assessment

Contact Info

Product

Resources

About