组合Edgeworth逼近和交叉熵的SAR变化检测

 星载SAR具有比较固定的重访周期，适合对地物进行动态监视，而变化检测是监视的关键技术。该文采用Edgeworth展开方法来逼近各种场景下的SAR图像统计分布模型，并引入信息论中的交叉熵作为两种分布差异的衡量因子，从而计算两个时相SAR图像之间的变化差异程度，以分布差异图像进行分割实现变化区域的提取。此外通过引入积分图像的思想，大大提高了计算分布差异指数的效率。最后采用实际的星载SAR图像进行变化检测实验，说明了方法的可行性。

The Study of SAR Change Detection Based on Edgeworth Approach and Kullback-Leibler Divergence

Owing to its fixed revisit period, space-borne SAR is suitable for dynamic monitoring the ground information, and change detection is the key processing technology. In this paper Edgeworth approach is used to fit the statistical distribution model of SAR image in different kind of scenes and the Kullback-Leibler divergence is proposed as a measurement of the difference between two SAR images. The idea of integral image is used to improve the calculation efficiency. The difference image is segmented to extract the changed regions, this approach is demonstrated feasible according to the processing test using real satellite SAR image.