2010 IEEE International Geoscience and Remote Sensing Symposium 2010
DOI: 10.1109/igarss.2010.5653466
|View full text |Cite
|
Sign up to set email alerts
|

Filtering and segmentation of polarimetric SAR images with Binary Partition Trees

Abstract: A new multi-scale PolSAR data filtering technique, based on a Binary Partition Tree (BPT) representation of the data, is proposed. Different alternatives for the construction and the exploitation of the BPT for filtering and segmentation are presented. Results with simulated and experimental PolSAR data are presented to shown the capabilities of the BPT-filtering strategy to maintain both spatial details and the polarimetric information.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
14
0

Year Published

2011
2011
2014
2014

Publication Types

Select...
3
3
2

Relationship

2
6

Authors

Journals

citations
Cited by 16 publications
(16 citation statements)
references
References 3 publications
0
14
0
Order By: Relevance
“…Furthermore, the mentioned applications are based on similarity measures or distances over the covariance matrix space, as in the case of the proposed technique, making it a natural preprocessing stage as it is based on parallel concepts. For Binary Partition Tree (BPT) [31] based PolSAR speckle filtering and segmentation [15,32] an initial 3 × 3 multilook filter is applied for this purpose. However, this initial step implies a small spatial resolution loss, as seen previously.…”
Section: Resultsmentioning
confidence: 99%
“…Furthermore, the mentioned applications are based on similarity measures or distances over the covariance matrix space, as in the case of the proposed technique, making it a natural preprocessing stage as it is based on parallel concepts. For Binary Partition Tree (BPT) [31] based PolSAR speckle filtering and segmentation [15,32] an initial 3 × 3 multilook filter is applied for this purpose. However, this initial step implies a small spatial resolution loss, as seen previously.…”
Section: Resultsmentioning
confidence: 99%
“…The BPT representation can be employed to process PolSAR images, as described in [14]- [16]. In these publications, the traditional 8-connectivity was employed, and the polarimetric covariance matrix (2) was used as a region model.…”
Section: Polsar Time Series Bptmentioning
confidence: 99%
“…This constraint justify the use of i ' and i 2 norms in the standard one dimensional case, the bests well-known algorithms using costs functions associated with these norms being respectively some variants of the Wiener-like ( [1], [2], [3], [4], among others) and median-based ( [5], [6], [7], among others) filtering strategies.…”
Section: Introductionmentioning
confidence: 99%
“…Standard methods for filtering remote sensing data are mainly based on the minimization of i 2 and i ' error norm cost functions, see [1], [2], [3], [4], [5], [6], [7], among others.…”
Section: Introductionmentioning
confidence: 99%