Within the constraints of operational work supporting humanitarian organizations in their response to the Covid-19 pandemic, we conducted building extraction for Khartoum, Sudan. We extracted approximately 1.2 million dwellings and buildings, using a Mask R-CNN deep learning approach from a Pléiades very high-resolution satellite image with 0.5 m pixel resolution. Starting from an untrained network, we digitized a few hundred samples and iteratively increased the number of samples by validating initial classification results and adding them to the sample collection. We were able to strike a balance between the need for timely information and the accuracy of the result by combining the output from three different models, each aiming at distinctive types of buildings, in a post-processing workflow. We obtained a recall of 0.78, precision of 0.77 and F₁ score of 0.78, and were able to deliver first results in only 10 days after the initial request. The procedure shows the great potential of convolutional neural network frameworks in combination with GIS routines for dwelling extraction even in an operational setting.

中文翻译：

---

在人道主义行动中从 VHR 卫星数据中提取基于 Mask R-CNN 的建筑物：与苏丹喀土穆的 Covid-19 响应相关的示例

在支持人道主义组织应对 Covid-19 大流行的业务工作的限制下，我们为苏丹喀土穆进行了建筑物提取。我们使用来自Pléiades的 Mask R-CNN 深度学习方法提取了大约 120 万个住宅和建筑物具有 0.5 m 像素分辨率的高分辨率卫星图像。从未经训练的网络开始，我们将数百个样本数字化，并通过验证初始分类结果并将它们添加到样本集合中迭代地增加样本数量。通过在后处理工作流程中结合三个不同模型的输出，每个模型都针对不同类型的建筑物，我们能够在及时信息的需求和结果的准确性之间取得平衡。我们获得了 0.78 的召回率，0.77 的精度和F ₁得分为 0.78，并且能够在初始请求后仅 10 天内提供第一个结果。该过程显示了卷积神经网络框架与 GIS 例程相结合的巨大潜力，即使在操作环境中也可用于住宅提取。