Synthetic aperture radar (SAR) data obtained at multiple frequencies and polarizations offers valuable complementary information for classifying mixed classes that exhibit similar backscattering response. Although deep learning-based convolutional neural networks (CNNs) effectively extract features from multi-frequency SAR data, the arbitrary ordering of SAR features may hinder optimal convolution of the best feature sub-space for a specific class and underutilize available multi-frequency data. To address this, a novel CNN transforming SAR feature-space from 1-D to 2-D and employing varied dilation-rate convolutions is introduced. This transformation maximizes unique and localized feature combinations, efficiently utilizing the available feature sub-spaces and extracting discriminative features for accurate classifications, addressing the challenge of arbitrary band neighborhoods. Utilizing dual-polarization SAR data from ALOS-2 PALSAR-2 and Sentinel-1 sensors, the proposed CNN achieves an average f-score of 0.97 and a kappa coefficient of 0.97, an improvement of 11 %, 7 % and 3 % in OA compared to the 1-D, 2-D and 3-D CNN classifiers, without feature transformation. The classifier's generalization ability is evaluated using ground truth knowledge of various heterogeneous classes, and the proposed CNN classifier outperforms others in terms of accuracy metrics and generalization ability.

中文翻译：

---

使用 2D CNN 和多频 SAR 数据绘制混合类土地覆盖图

在多个频率和偏振下获得的合成孔径雷达 (SAR) 数据为对表现出类似反向散射响应的混合类别进行分类提供了宝贵的补充信息。尽管基于深度学习的卷积神经网络（CNN）可以有效地从多频 SAR 数据中提取特征，但 SAR 特征的任意排序可能会阻碍特定类别的最佳特征子空间的最佳卷积，并且无法充分利用可用的多频数据。为了解决这个问题，引入了一种新颖的 CNN，将 SAR 特征空间从一维转换为二维并采用不同的扩张率卷积。这种转换最大化了独特和局部的特征组合，有效地利用可用的特征子空间并提取判别特征以进行准确的分类，解决任意频带邻域的挑战。利用来自 ALOS-2 PALSAR-2 和 Sentinel-1 传感器的双偏振 SAR 数据，所提出的 CNN 实现了 0.97 的平均 f 分数和 0.97 的 kappa 系数，在 OA 方面分别提高了 11%、7% 和 3%与 1-D、2-D 和 3-D CNN 分类器相比，无需特征转换。使用各种异构类的真实知识来评估分类器的泛化能力，所提出的 CNN 分类器在准确性指标和泛化能力方面优于其他分类器。