Optimal approach to SAR image segmentation and classification

Citation
D. Stewart et al., Optimal approach to SAR image segmentation and classification, IEE P-RAD S, 147(3), 2000, pp. 134-142
Citations number
15
Language
INGLESE
art.tipo
Article
Categorie Soggetti
Information Tecnology & Communication Systems
Journal title
IEE PROCEEDINGS-RADAR SONAR AND NAVIGATION
ISSN journal
1350-2395 → ACNP
Volume
147
Issue
3
Year of publication
2000
Pages
134 - 142
Database
ISI
SICI code
1350-2395(200006)147:3<134:OATSIS>2.0.ZU;2-Q
Abstract
Many algorithms have been proposed for the segmentation and classification of SAR imagery. Typically these are heuristic in basis, and more successful on some types of imagery than others. Methods based on global optimisation techniques can achieve the optimal solution of the posed problem; the algo rithm is then characterised by an objective function and the chosen optimis ation technique. The authors construct an appropriate objective function fo r SAR segmentation or classification, and show how to optimally quantify th e relationship between the competing terms within it. This removes the prev ious need for the introduction of heuristics. Also described is an implemen tation based on simulated annealing, in which considerable attention has be en paid to details, and examples are given of the resulting algorithm's per formance upon real data.