Loading...
Loading...

Go to the content (press return)

Optimum graph cuts for pruning binary partition trees of polarimetric SAR images

Author
Salembier, P.; Foucher, S.
Type of activity
Journal article
Journal
IEEE transactions on geoscience and remote sensing
Date of publication
2016-09-01
Volume
54
Number
9
First page
5493
Last page
5502
DOI
https://doi.org/10.1109/TGRS.2016.2566581 Open in new window
Repository
http://hdl.handle.net/2117/99189 Open in new window
URL
http://ieeexplore.ieee.org/document/7480960/ Open in new window
Abstract
This paper investigates several optimum graph-cut techniques for pruning binary partition trees (BPTs) and their usefulness for the low-level processing of polarimetric synthetic aperture radar (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 ap...
Citation
Salembier, P., Foucher, S. Optimum graph cuts for pruning binary partition trees of polarimetric SAR images. "IEEE transactions on geoscience and remote sensing", 1 Setembre 2016, vol. 54, núm. 9, p. 5493-5502.
Keywords
Binary partition tree (BPT), Graph cut, Polarimetric synthetic aperture radar (SAR) (PolSAR) image processing, Precision and recall for boundaries, Segmentation, Speckle noise, Tree pruning
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants

Attachments