Polarimetric Multipath Convolutional Neural Network for PolSAR Image Classification
Polarimetric Multipath Convolutional Neural Network for PolSAR Image Classification
复制标题
用于 PolSAR 图像分类的偏振多路径卷积神经网络
DOI：
10.1109/tgrs.2021.3071559
复制
发表时间：
2022
影响因子：
8.2
通讯作者：
Xiaoxue Qian
中科院分区：
文献类型：
--
作者：
Yuanhao Cui;Fang Liu;Licheng Jiao;Yuwei Guo;Xuefeng Liang;Lingling Li;Shuyuan Yang;Xiaoxue Qian
极化合成孔径雷达（PolSAR）图像中复杂地物的散射目标往往具有随机方向性，回波起伏较大，这给极化SAR图像分类带来了挑战。因此，许多现有的方法已经通过取向补偿来缓解这个问题。然而，仍然有两个障碍限制了分类精度的提高。一方面，这些方法通常处理具有固定极化旋转角的极化SAR图像，这是经验依赖性和灵活性。另一方面，对于不同的土地覆盖的极化SAR图像，现有的方法不考虑这些旋转角度分开。对于第一个障碍，我们设计了一组称为极化旋转核（PRK）的卷积核，并利用它们来构建极化卷积神经网络（CNN）（PolCNN）。PolCNN是我们最终模型的基础网络，它可以自适应地学习偏振旋转角度。对于第二个障碍，我们将PolCNN扩展为多径结构，最终模型极化多径CNN（PolMPCNN）。不同土地覆盖的极化旋转角与PolMPCNN中不同路径的网络直接相关。此外，为了使PolMPCNN能适应不同尺度的PolSAR目标，并能更好地处理难训练样本，本文还提出了双尺度采样和分阶段训练算法。对真实的PolSAR图像的实验表明，该模型在极低的采样率（0. 1%）下取得了最好的分类效果。
Scatter targets of complex land covers in polarimetric synthetic aperture radar (PolSAR) images are often randomly oriented and cause randomly fluctuating echoes, which brings a challenge to PolSAR image classification. Therefore, many existing methods have alleviated this problem through orientation compensation. However, there are still two obstacles that limit the improvement of classification accuracy. On the one hand, generally, these methods process PolSAR images with fixed polarization rotation angles, which is experience-dependent and inflexible. On the other hand, for the different land covers of a PolSAR image, the existing methods do not consider these rotation angles separately. For the first obstacle, we design a group of convolution kernels called polarization rotation kernels (PRKs) and utilize them to build the polarimetric convolutional neural network (CNN) (PolCNN). The PolCNN is the base network of our final model, and it can learn polarization rotation angles adaptively. For the second obstacle, we extend the PolCNN into a multipath structure, the final model polarimetric multipath CNN (PolMPCNN). The polarization rotation angles of different land covers are directly related to the networks of different paths within the PolMPCNN. Furthermore, we also put forward the two-scale sampling and the stagewise training algorithm in order that our PolMPCNN can fit different scales of PolSAR targets and pays more attention to difficult training samples. Experiments on real PolSAR images show that the proposed model achieves the best classification results with an extremely low sampling rate of 0.1%.