利用极化距离变换实现极化SAR图像变化检测

Change Detection Algorithm of Polarimetric SAR Image with Polarimetric Distance Transformation

  • 摘要: 针对复杂场景下特定类型地物的变化给出了一种利用极化距离变换实现SAR图像变化检测的算法,首先利用改进的Wishart距离算法得到目标类地物与两时相图像的距离测度,然后对该测度进行比值对数变换,构造差异图像,最后利用双阈值分割法提取出变化区域,并区分出两种变化类型。利用2009年4月9日和2010年6月15日,Radarsat-2在苏州区域获取的雷达图像进行试验。实验结果表明,本文给出的算法能够较好的实现复杂场景下特定地物类型的变化检测,鲁棒性强。

     

    Abstract: In this paper, a new algorithm based on polarimetric distance transformation is proposed for the change of specific land cover type in complex scenes. Firstly, an improved Wishart distance algorithm was used to measure the distance between the target land cover type and two phase fully polarimetric images,Then, the ratio logarithm of the measurement was transformed to construct difference image. Finally,double threshold segmentation method was applied to extract the change areas and to distinguish two kinds of changes. Two Radarsat2 fully polarimetric images in Suzhou city, China, acquired on April 9, 2009 and June 15, 2010, were used for experiment. The results show that the proposed algorithm gives a good performance to achieve the change of the specific land cover type in complex scenes and has good robustness.

     

/

返回文章
返回