ABSTRACT Building maps have a plethora of applications in government, industry and academia. In most cases, large scale maps can be retrieved from OpenStreetMap vector data. However, for certain rapidly changing built and semi-built environments, corresponding maps are not as accurate and contain label noise such as missing, incorrectly present, shifted labels, etc.; mainly because buildings in those regions are constantly being constructed, deconstructed, replaced and altered. One such case is extant in the Rohingya camps of southeastern border region of Bangladesh. Mass refugee influx in late 2017 and following population growth has necessitated the construction of buildings and expansion of camps. Consequently, reliable methods are necessary for detecting and documenting camp buildings. Ultra-high-resolution drone images of Rohingya camps are semantically segmented through fully convolutional U-Net deep learning systems for generating accurate building maps from noisy labels. A wide variety of noises are prevalent in the labels. Deep learning systems provide less noisy predictions compared to the classification tool in the most widely used Geographic Information System (GIS) software, ArcGIS. Data augmentation and regularization allows reliable learning, even in the presence of label noise. During testing, calculation of numeric performance metrics against noisy labels can grossly underestimate true skill and performance of the model. A subset of 22 million pixels of the testing data is relabelled by hand to obtain noise-free labels. Testing our generated maps against noisy and noise-free labels confirms that true performance is higher than otherwise indicated by freely available building maps. Empirical results reveal that utilized pipeline is able to learn from noisy data and produce labels which are more accurate and less noisy. Labels generated by our best performing system provide Intersection-over-Union (IoU) gain of 17.6% and Dice score gain of 13.6% over freely available labels from OpenStreetMap. Finally, spatio-temporal building maps are generated to portray the applicability of this research.

中文翻译：

---

学习从超高分辨率无人机图像和嘈杂标签中提取建筑物

摘要 建筑地图在政府、工业和学术界有大量应用。在大多数情况下，可以从 OpenStreetMap 矢量数据中检索大比例尺地图。然而，对于某些快速变化的建成和半建成环境，相应的地图并不那么准确，并且包含标签噪声，例如缺失、错误存在、移位标签等；主要是因为这些地区的建筑物不断被建造、解构、更换和改造。孟加拉国东南部边境地区的罗兴亚难民营中就存在这样的一个案例。2017 年底大量难民涌入以及随后的人口增长使得建造建筑物和扩建营地成为必要。因此，需要可靠的方法来检测和记录营地建筑。Rohingya 营地的超高分辨率无人机图像通过全卷积 U-Net 深度学习系统进行语义分割，以从嘈杂的标签中生成准确的建筑地图。标签中普遍存在各种各样的噪音。与使用最广泛的地理信息系统 (GIS) 软件 ArcGIS 中的分类工具相比，深度学习系统提供的预测噪声更少。即使在存在标签噪声的情况下，数据增强和正则化也可以实现可靠的学习。在测试期间，针对嘈杂标签的数字性能指标的计算可能会严重低估模型的真实技能和性能。手动重新标记测试数据的 2200 万像素子集以获得无噪声标签。针对噪声和无噪声标签测试我们生成的地图证实，真实性能高于免费提供的建筑地图所表明的其他情况。实证结果表明，所利用的管道能够从嘈杂的数据中学习并生成更准确且噪声更少的标签。与来自 OpenStreetMap 的免费可用标签相比，由我们性能最佳的系统生成的标签提供 17.6% 的 Intersection-over-Union (IoU) 增益和 13.6% 的 Dice 得分增益。最后，生成时空建筑图以描绘本研究的适用性。与 OpenStreetMap 中免费提供的标签相比，由我们性能最佳的系统生成的标签提供 17.6% 的交叉路口 (IoU) 增益和 13.6% 的 Dice 得分增益。最后，生成时空建筑图以描绘本研究的适用性。与 OpenStreetMap 中免费提供的标签相比，由我们性能最佳的系统生成的标签提供 17.6% 的交叉路口 (IoU) 增益和 13.6% 的 Dice 得分增益。最后，生成时空建筑图以描绘本研究的适用性。