Title :
SAR mosaic segmentation of tropical forest region
Author :
Raucoules, Daniel ; Thomson, Keith
Author_Institution :
Centre de Recherches en Geomatique, Laval Univ., Que., Canada
Abstract :
The authors discuss SAR image segmentation/classification. This type of segmentation is made difficult by the signal characteristics and is especially problematic if the objects to be segmented depend on textural features. The software used is the Hierarchical Stepwise Optimization Segmentation Algorithm (developed by J.M. Beaulieu). The authors have modified its merging criterion by introducing textural feature and edge information. The procedure is applied to the CAMP mosaic in order to segment tropical forest regions
Keywords :
forestry; geophysical signal processing; geophysical techniques; image classification; image segmentation; radar imaging; remote sensing by radar; synthetic aperture radar; vegetation mapping; CAMP mosaic; Hierarchical Stepwise Optimization Segmentation Algorithm; SAR; edge; geophysical measurement technique; image classification; image segmentation; merging criterion; mosaic segmentation; radar imaging; radar remote sensing; software; synthetic aperture radar; textural feature; tropical forest; vegetation mapping; Costs; Degradation; Image edge detection; Image segmentation; Information filtering; Information filters; Iterative algorithms; Low pass filters; Merging; Partitioning algorithms;
Conference_Titel :
Geoscience and Remote Sensing Symposium Proceedings, 1998. IGARSS '98. 1998 IEEE International
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-4403-0
DOI :
10.1109/IGARSS.1998.702336
