Polarimetric SAR image object segmentation via level set with stationary global minimum
EURASIP Journal on Advances in Signal Processing - Special issue on advances in multidimensional synthetic aperture radar signal processing
| Hi-index | 0.00 |
In this paper a new approach to polarimetric Synthetic Aperture Radar (SAR) image region boundary detection is presented. It is based on a new model for polarimetric SAR data and the use of B-Spline active contours for image segmentation. In order to detect the boundary for a region, an initial B-Spline curve is specified and the proposed algorithm uses a deformable contours technique to find the boundary. In doing this, the statistical parameters of the polarimetric G^H model for the data are estimated, in order to find the transition points between the region being segmented and the surrounding area. This algorithm can be regarded as a local one, in the sense that it works on the region to be segmented instead of on the whole image