【摘要】 针对传统基于像素的变化检测方法受speckle噪声影响严重的问题,在区域分割的基础上,提出似然比检测的方法,获得了良好的检测结果.该方法先针对多时相SAR图像数据样本的统计模型提出未知和变化两种假设,然后采用似然比检验方法对两种假设进行检验,从而获得区域的变化检测结果.实验表明,该方法很大程度上降低了SAR图像乘性噪声在变化检测过程中带来的误检和漏检效应,将检测的精确度提高了22%,从而比较准确地反映了SAR图像区域的变化,具有很好的应用前景.更多还原

【Abstract】 Based on region segmentation, this paper adapt a new change detection technique that make use of region likelihood ratio. The experimental results on SAR images show that the new technique decrease the false detection which are created by speckle noise, and the detect precision is increased by 22 percent . This technique has a bright future to be used in different areas.更多还原