使用测地线活动轮廓模型的合成孔径雷达图像分割方法

为解决经典的测地线活动轮廓(geodesic active contour, GAC)模型在合成孔径雷达(synthetic aperture radar,SAR)图像上不适用的问题,在原GAC模型的基础上提出一种新的分割方法。首先在ROEWA算子进行边缘检测的同时使用Frost滤波器对图像进行负指数加权,形成边滤波边检测的模式,提高了算子的边缘检测与定位能力;然后使用经验阈值对ROEWA强度进行二值化,提高了曲线演化的速度与精确度;最终使用二值化的改进后ROEWA算子替代原GAC模型中的全局梯度项作为边缘指示函数引导图像分割。实验结果表明,针对仿真SAR图像及真实河流SAR图像,分割效果与参数指标都有明显提升。

SAR Image Segmentation Method using Geodesic Active Contour Model

In order to solve the problem that the classic geodesic active contour (GAC) model is not suitable for SAR image, a new segmentation method is proposed based on the original GAC model. First of all, when ROEWA operator is used for edge detection, Frost filter is used for negative exponential weighting of image to form a mode of to detect the edge while filtering, which improves the edge detection and positioning ability of operator; then, experience threshold is used to binarize ROEWA intensity, which improves the speed and accuracy of curve evolution. Finally, the improved ROEWA operator after binarization is used to replace the global gradient term in the original GAC model as the edge indicator function to guide image segmentation. The experimental results show that the segmentation effect and parameters of the simulated SAR images and the real river SAR images are significantly improved.