Buildings represent pivotal entities in remote sensing imagery for various applications such as urban planning and land resource management. Predominantly, methods for building footprint extraction in the literature focus on optical imagery with visual attributes that faithfully mirror the physical world. Nevertheless, the acquisition of high-quality optical images presents formidable challenges due to the susceptibility to illumination conditions and scene visibility. In contrast, synthetic aperture radar (SAR) images can be acquired in all-weather and all-time situations, unburdened by the aforementioned constraints. However, the coherent imaging mechanism engenders intricate complexities for building footprint extraction SAR images. To address this issue, this article introduces the boundary information distillation network (BIDNet) to improve the prediction accuracy in SAR images by distilling knowledge from optical images. The proposed approach adopts a teacher–student framework, featuring two customized components: the explicit distillation module (EDM) and the latent distillation module (LDM). Different from the conventional practice of directly aligning feature maps, BIDNet focuses on leveraging the more conspicuous boundary information in optical images. The EDM operates by simultaneously yielding a boundary map to emphasize the boundary area and assimilating the explicit low-level features of two modalities. The LDM represents the structural attributes within the high-level latent feature space and aligns the representations of the two modalities. Within this module, intrinsic self-correlations among features originating from boundary regions are encoded, and so are the cross-correlations established between features from boundary regions and alternative areas. The two modules also serve as the conduit for knowledge distillation (KD) from the teacher network to the student network, enabling the utilization of optical imagery for enhancing the building footprint extraction in SAR imagery. Extensive experiments demonstrate that our BIDNet achieves state-of-the-art performance on the Multi-Sensor All Weather Mapping (MSAW) dataset, outperforming the strong baseline by 4.3–7.2 points in F1-score and 4.9–8.0 points in IoU. The source code and trained models will be publicly available at https://github.com/wangyx-chn/BIDNet .

中文翻译：

---

通过从光学图像中提取边界信息提取 SAR 图像中的建筑物足迹

建筑物代表了城市规划和土地资源管理等各种应用的遥感图像中的关键实体。文献中构建足迹提取的方法主要侧重于具有忠实反映物理世界的视觉属性的光学图像。然而，由于对照明条件和场景可见度的敏感性，高质量光学图像的获取面临着巨大的挑战。相比之下，合成孔径雷达（SAR）图像可以在全天候、全时的情况下获取，不受上述限制的影响。然而，相干成像机制给构建足迹提取 SAR 图像带来了复杂性。为了解决这个问题，本文引入了边界信息蒸馏网络（BIDNet），通过从光学图像中提取知识来提高 SAR 图像的预测精度。所提出的方法采用师生框架，具有两个定制组件：显式蒸馏模块（EDM）和潜在蒸馏模块（LDM）。与直接对齐特征图的传统做法不同，BIDNet 专注于利用光学图像中更明显的边界信息。 EDM 的工作方式是同时生成边界图以强调边界区域并同化两种模态的显式低级特征。 LDM 表示高级潜在特征空间内的结构属性，并对齐两种模态的表示。在该模块中，对源自边界区域的特征之间的内在自相关性进行编码，并且对来自边界区域和替代区域的特征之间建立的互相关性进行编码。这两个模块还充当从教师网络到学生网络的知识蒸馏 (KD) 管道，从而能够利用光学图像来增强 SAR 图像中的建筑物足迹提取。大量实验表明，我们的 BIDNet 在多传感器全天候测绘 (MSAW) 数据集上实现了最先进的性能，F1 分数比强基线高 4.3-7.2 点，IoU 比强基线高 4.9-8.0 点。源代码和经过训练的模型将在以下位置公开提供：https://github.com/wangyx-chn/BIDNet 。