选择利用Wishart和K统计描述的极化SAR图像分割

Segmentation of Polarimetric SAR Images Selectively Using Wishart and K Statistical Description

为得到极化SAR图像中不同异质程度区域的准确分割,本文提出一种选择利用Wishart和K统计描述的极化SAR图像分割方法。该方法采用分形网络演化算法思想,将简单线性迭代聚类算法生成的超像素作为初始对象;再根据区域异质度指标,选择利用Wishart分布或K分布描述对象的统计相似性;最终实现综合利用Wishart和K统计描述的极化SAR图像分形网络演化分割。通过模拟数据和真实极化数据进行实验并与其它方法相比较,结果表明,本文方法在整体上能准确分割不同异质程度的地物,在局部细节上分割结果边界更精细。

To obtain accurate segmentation of polarimetric SAR images in different heterogeneity areas, a new segmentation method is proposed in this paper which selectively uses Wishart and K statistical description based on the fractal network evolution algorithm （FNEA）. Specifically, initial objects are derived by using superpixels efficiently generated by simple linear iterative clustering （SLIC） algorithm. Similarity criterion between adjacent objects is defined by Wishart and K distribution depending on the regional heterogeneity index. Then the segmentation procedure for polarimetric data is realized, which makes full use of Wishart and K statistical description. Moreover, simulated data and real data are used to verify the effectiveness of the proposed method. The experiment result shows it can accurately segment different heterogeneity areas on the whole and get more precise boundary in the local details compared with other algorithms.