CAJ | 학술논문

由于合成孔径雷达( SAR )图像易受相干斑噪声的影响，光学图像的分割方法并不适用于SAR 图像，更不能获得精确的分割结果对比，因此，首先基于 G 0A统计模型定义能量映射函数以代替像素值进行后续处理，减小相干斑的影响；其次，使用水平集算法对处理后的图像进行分割处理，选用了一种形式更为简单的水平集函数，并可以较容易地推广到多区域 SAR 图像分割情况。实验结果表明，该方法可以减少相干斑噪声对 SAR 图像分割过程的不良影响，具有较好的准确性。
유우합성공경뢰체( SAR )도상역수상간반조성적영향，광학도상적분할방법병불괄용우SAR 도상，경불능획득정학적분할결과대비，인차，수선기우 G 0A통계모형정의능량영사함수이대체상소치진행후속처리，감소상간반적영향；기차，사용수평집산법대처리후적도상진행분할처리，선용료일충형식경위간단적수평집함수，병가이교용역지추엄도다구역 SAR 도상분할정황。실험결과표명，해방법가이감소상간반조성대 SAR 도상분할과정적불량영향，구유교호적준학성。
To solve the problem that optical image′ segmentation method is not suitable for SAR image and cannot obtain the accurate segmentation results , which is affected by synthetic aperture radar image′ speckle noise , a SAR image segmentation method based on G 0A statistical model and level set is presented in this paper . Firstly , a energy mapping function based on G 0A statistical model is defined to instead of pixel values for subsequent image processing , which can reduce the speckle noise′ influence . Sec-ondly , using level set method to finish images′ segmentation , this article uses a more simple energy function which is easy to be used to deal with multiregion SAR images′ segmentation . Experimental results show that this method can reduce speckle noise′ in-fluence in SAR image segmentation process , and has better accuracy and adaptive .