Back to Search
Start Over
Late-Season Rural Land-Cover Estimation With Polarimetric-SAR Intensity Pixel Blocks and σ-Tree-Structured Near-Neighbor Classifiers.
- Source :
-
IEEE Transactions on Geoscience & Remote Sensing . Sep2006, Vol. 44 Issue 9, p2384-2392. 9p. 2 Black and White Photographs, 5 Diagrams, 4 Charts. - Publication Year :
- 2006
-
Abstract
- Synthetic aperture radar (SAR) image classification for late-season rural land-cover estimation is investigated. A novel tree-structured nearest neighbor-like classifier is applied to polarimetric SAR intensity image pixel blocks. The novel tree structure, called a or-tree, is generated by an ordered summation of unweighted template refinements. Computation and memory costs of a σ-tree classifier grow linearly. The reduced costs of or-tree classifiers are obtained with the tradeoff of a guarantee of nearest neighbor mappings. Causal-anticausal refinement-template design methods, combined with causal multiple-stage search engine structures, are shown to yield sequential search decisions that are acceptably near-neighbor mappings. The performance of a σ-tree classifier is demonstrated for rural land-cover estimation with detected polarimetric C-band AirSAR pixel data. Experiments are conducted on various polarization/pixel block size combinations to evaluate the relative utility of spatial-only, polarimetric-only, and combined spatial/polarimetric classifier inputs. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 01962892
- Volume :
- 44
- Issue :
- 9
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Geoscience & Remote Sensing
- Publication Type :
- Academic Journal
- Accession number :
- 22211398
- Full Text :
- https://doi.org/10.1109/TGRS.2006.875449