A Fast Segmentation Scheme Based on Level Set for SAR Images

摘要：

In this paper, we propose a modified segmentation algorithm based on level set for synthetic aperture radar (SAR) images. The segmentation of SAR images is a difficult problem due to the presence of speckle which can be modeled as strong, multiplicative noise. One main drawback of previous the SAR image segmentation algorithm based on active contour model and level set is the computational expense inherent to solving the proposed nonlinear parabolic partial differential equation. The proposed algorithm is faster than the previous SAR image segmentation via standard curve evolution model. Experimental results are shown on both synthetic and real SAR images.

关键词： Image segmentation active contours level sets partial differential equation synthetic aperture radar.

作者: Yongmin Shuai Hong Sun Ge Xu

作者单位: Signal Processing Laboratory,Wuhan University,Wuhan 430079,China

会议类型: 国际会议

会议名称: 首届亚太合成孔径雷达会议(1st Asian and Pacific Conference on Synthetic Aperture Radar Proceedings)

会议地点: 安徽黄山

会议语种:英文

在线出版日期: 2007-11-05（万方平台首次上网日期，不代表论文的发表时间）