Unsupervised classification of polarimetric synthetic aperture Radar images using fuzzy clustering and EM clustering

Kersten, P.R.; Lee, Jong-Sen; Ainsworth, T.L.

doi:10.1109/tgrs.2004.842108

Cited by 204 publications

(109 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The third pruning criterion relies on a Wishart similarity measure [19]. It is based on a statistical test that assumes that two matrices, Z 1 and Z 2 , follow a Wishart pdf and that one pdf is known.…”

Section: Bpt Pruning Optimizing a Global Criterionmentioning

confidence: 99%

Optimum Graph Cuts for Pruning Binary Partition Trees of Polarimetric SAR Images

Salembier

Foucher

2016

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Abstract-This paper investigates several optimum graph-cuts techniques for pruning Binary Partition Trees (BPTs) and their usefulness for low-level processing of Polarimetric SAR (PolSAR) images. BPTs group pixels to form homogeneous regions, which are hierarchically structured by inclusion in a binary tree. They provide multiple resolutions of description and easy access to subsets of regions. Once constructed, BPTs can be used for a large number of applications. Many of these applications consist in populating the tree with a specific feature and in applying a graph-cut called pruning to extract a partition of the space. In this paper, different pruning examples involving the optimization of a global criterion are discussed and analyzed in the context of PolSAR images for segmentation. Through objective evaluation of the resulting partitions by means of Precision and Recall for boundaries curves, the best pruning technique is identified and the influence of the tree construction on the performances is assessed.

show abstract

Section: Bpt Pruning Optimizing a Global Criterionmentioning

confidence: 99%

Optimum Graph Cuts for Pruning Binary Partition Trees of Polarimetric SAR Images

Salembier

Foucher

2016

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The EM algorithm is used for the tasks in remote sensing image classification [5][6][7][8][9][10][11]. In remote image classification a unimodal assumption for conditional distribution is incongruous for high spatial resolution remote sensed images.…”

Section: Related Workmentioning

confidence: 99%

A Comparative Study of Data Mining Algorithms for Image Classification

Thamilselvana¹,

Sathiaseelan²

2015

IJEME

View full text Add to dashboard Cite

Data mining is an important research area in computer science. It is a computational process of determining patterns in large data. Image mining is one of important techniques in data mining, which involved in multiple disciplines. Image Classification Refers the tagging the images into a number of predefined sets. It's also includes image preprocessing, feature extraction, object detection, object classification, object segmentation, object classification and many more techniques.

show abstract

“…The Manhattan, the Euclidean, the Bartlett and the revised Wishart distances between covariance matrices [4] were used in this comparison. If x and y are pxp different covariance matrices, then the four distances are defined as:…”

Section: Polarimetric Attributes Analysismentioning

confidence: 99%

Polarization plane rotation effects on SAR polarimetric attributes

Sant’Anna

Lacava

Fernandes

2009

2009 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

The polarization plane rotation effects on SAR polarimetric attributes are analyzed. This analysis is carried out by simulating a polarimetric SAR image containing four regions with different electric characteristic. The simulation process is based on an electromagnetic scattering model. Employing a rotation model is generated a image set having 361 images, where each image has it polarization plane rotated by a different angle. From all images of the set are computed the covariance matrix and six polarimetric attributes of each image region and compared with their correspondent parameter in the image without rotation. From this evaluation it could be seen that the rotation angle influences differently all polarimetric attributes. The effects of rotation angle can lead to a misunderstanding of the target scattering mechanism.

show abstract

Unsupervised classification of polarimetric synthetic aperture Radar images using fuzzy clustering and EM clustering

Cited by 204 publications

References 18 publications

Optimum Graph Cuts for Pruning Binary Partition Trees of Polarimetric SAR Images

Optimum Graph Cuts for Pruning Binary Partition Trees of Polarimetric SAR Images

A Comparative Study of Data Mining Algorithms for Image Classification

Polarization plane rotation effects on SAR polarimetric attributes

Contact Info

Product

Resources

About