Interactive segmentation of high resolution synthetic aperture radar data by tree-structured MRF

Author

Gaetano, R. ; Amitrano, D. ; Masi, G. ; Poggi, G. ; Ruello, G. ; Verdoliva, L. ; Scarpa, G.

Author_Institution

DIETI, Univ. Federico II of Naples, Naples, Italy

fYear

2014

fDate

13-18 July 2014

Firstpage

3734

Lastpage

3737

Abstract

Reliable segmentation of SAR images requires some forms of user supervision: we resort here to the interactive version of the Tree-Structured Markov Random Field (TS-MRF) segmentation suite. The TS-MRF model, and the associated segmentation tool, provide a flexible and spatially adaptive description of the data. In the interactive version, the user can drive the process based on the inspection of the current result, deciding step-by-step which direction to take, and switching from one segmentation modality to another. Experiments with the segmentation and classification of multitemporal SAR images prove the potential of the interactive approach and of the TS-MRF tool.

Keywords

Markov processes; image classification; image resolution; image segmentation; radar imaging; random processes; synthetic aperture radar; SAR image segmentation; TS-MRF model; high resolution synthetic aperture radar data; interactive segmentation; multitemporal SAR image classification; tree-structured Markov random field model; Adaptation models; Data models; Image resolution; Image segmentation; Inspection; Remote sensing; Synthetic aperture radar; MRF; SAR; classification; interactive; segmentation; supervised;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium (IGARSS), 2014 IEEE International

Conference_Location

Quebec City, QC

Type

conf

DOI

10.1109/IGARSS.2014.6947295

Filename

6947295