文中提出了一种基于AdaBoost算法的全极化SAR(Synthetic Aperture Radar)图像分类方法。该方法将AdaBoost算法与HH、HV和VV三个极化通道数据结合起来,对全极化SAR图像进行分类,充分利用了极化信息和AdaBoost算法的快速收敛性。将该方法的仿真结果与彤垡分类方法仿真结果进行比较,发现该方法分类模糊程度较低,在细节上分类更为准确,且在相同的情况下,该算法速度更快。
In this paper, a new method for fully polarimetric SAR(Synthetic Aperture Radar) images classification based on AdaBoost algorithm is proposed. Fully using the polarimetric information and the fast convergence of AdaBoost algorithm, this method is combined with the data of channel HH,channel HV and channel VV to classify the fully polarimetric SAR images. Compared the simulation result with the result of H/α classification method, this method has much lower blur and is more precise in detail and faster in the same situation.