Building-change detection underpins many important applications, especially in the military and crisis-management domains. Recent methods used for change detection have shifted towards deep learning, which depends on the quality of its training data. The assembly of large-scale annotated satellite imagery datasets is therefore essential for global building-change surveillance. Existing datasets almost exclusively offer near-nadir viewing angles. This limits the range of changes that can be detected. By offering larger observation ranges, the scroll imaging mode of optical satellites presents an opportunity to overcome this restriction. This paper therefore introduces S2Looking, a building-change-detection dataset that contains large-scale side-looking satellite images captured at various off-nadir angles. The dataset consists of 5000 bitemporal image pairs of rural areas and more than 65,920 annotated instances of changes throughout the world. The dataset can be used to train deep-learning-based change-detection algorithms. It expands upon existing datasets by providing (1) larger viewing angles; (2) large illumination variances; and (3) the added complexity of rural images. To facilitate {the} use of the dataset, a benchmark task has been established, and preliminary tests suggest that deep-learning algorithms find the dataset significantly more challenging than the closest-competing near-nadir dataset, LEVIR-CD+. S2Looking may therefore promote important advances in existing building-change-detection algorithms. The dataset is available at https://github.com/S2Looking/.
翻译:建筑变化探测是许多重要应用的基础,特别是在军事和危机管理领域。最近用于变化探测的方法已经转向深层次学习,这取决于其培训数据的质量。因此,大型附加说明的卫星图像数据集的组装对于全球建筑变化监测至关重要。现有的数据集几乎完全提供近视角度。这限制了可以检测到的变化范围。通过提供更大的观测范围,光学卫星滚动成像模式提供了一个克服这一限制的机会。因此,本文引入了S2S2查看,一个含有大型侧向式卫星图像的建筑变化探测数据集,该数据集包含在各种离线角度拍摄的大型侧向式卫星图像。该数据集由5000对农村地区进行咬刻式图像配对和超过65 920个附加说明的世界各地变化实例组成。该数据集可用于培训基于深学习的改变探测算法。它扩大了现有数据集的范围,提供了(1) 更大的浏览角度;(2) 严重不透明差异;以及(3) 增加农村图像的复杂性。因此,为了便利最有挑战性的现有数据排序,S-requestal-regal lax 使用最先进的数据测试,因此,S-refregregal-trading the daltrading daltrading be be betrading betrading a lax be lax betrading a lax be lax be lax be lax be lax be lagal be lax be lax be lagal be lax be lax be ex be be be latistedal be latistedaldaldal be latingd dregaldaltistedaldaldal be latingdaldaldaldaldaldaldalddaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldalddaldaldaldaldaldaldaldaldald lad ladddddddddal laddddaldaldaldaldaldddaldaldaldaldaldaldald ladaldaldal lad