利用米级分辨率卫星影像实现国家级土地覆盖制图
Enabling Country-Scale Land Cover Mapping with Meter-Resolution Satellite Imagery
AI总结：
针对高分辨率影像大规模土地覆盖制图的挑战，提出了包含50亿标注像素的数据集Five-Billion-Pixels及基于Siamese网络的无监督域适应方法，实现了跨传感器与区域的米级国家级高质量制图。
摘要：
高分辨率卫星影像能够为土地覆盖分类提供丰富、详细的空间信息，这对于研究复杂的建成环境尤为重要。然而，由于复杂的土地覆盖模式、高昂的训练样本采集成本以及卫星影像严重的分布偏移，很少有研究将高分辨率影像应用于大规模的详细类别土地覆盖制图。为填补这一空白，我们提出了一个大规模土地覆盖数据集Five-Billion-Pixels。该数据集包含150幅高分二号（4 m）高分辨率卫星影像中超过50亿个标注像素，采用涵盖人工建造、农业和自然类别的24类分类体系进行标注。此外，我们提出了一种基于深度学习的无监督域适应方法，能够将在有标签数据集（称为源域）上训练的分类模型迁移到无标签数据（称为目标域）中，以进行大规模土地覆盖制图。具体而言，我们引入了一个端到端Siamese网络，采用动态伪标签分配和类别平衡策略来执行自适应域联合学习。为了验证我们的数据集和所提出方法在不同传感器和不同地理区域的泛化能力，我们分别使用PlanetScope（3 m）、高分一号（8 m）和Sentinel-2（10 m）卫星影像，对中国五个特大城市以及其他五个亚洲国家的六个城市进行了土地覆盖制图。在总计60000平方公里的研究区域内，实验显示出令人满意的结果，即使输入影像完全没有标签。所提出的方法结合Five-Billion-Pixels数据集训练，能够在中国全境及其他一些亚洲国家实现米级分辨率的高质量、详细的土地覆盖制图。
英文摘要：
High-resolution satellite images can provide abundant, detailed spatial information for land cover classification, which is particularly important for studying the complicated built environment. However, due to the complex land cover patterns, the costly training sample collections, and the severe distribution shifts of satellite imageries, few studies have applied high-resolution images to land cover mapping in detailed categories at large scale. To fill this gap, we present a large-scale land cover dataset, Five-Billion-Pixels. It contains more than 5 billion labeled pixels of 150 high-resolution Gaofen-2 (4 m) satellite images, annotated in a 24-category system covering artificial-constructed, agricultural, and natural classes. In addition, we propose a deep-learning-based unsupervised domain adaptation approach that can transfer classification models trained on labeled dataset (referred to as the source domain) to unlabeled data (referred to as the target domain) for large-scale land cover mapping. Specifically, we introduce an end-to-end Siamese network employing dynamic pseudo-label assignment and class balancing strategy to perform adaptive domain joint learning. To validate the generalizability of our dataset and the proposed approach across different sensors and different geographical regions, we carry out land cover mapping on five megacities in China and six cities in other five Asian countries severally using: PlanetScope (3 m), Gaofen-1 (8 m), and Sentinel-2 (10 m) satellite images. Over a total study area of 60,000 square kilometers, the experiments show promising results even though the input images are entirely unlabeled. The proposed approach, trained with the Five-Billion-Pixels dataset, enables high-quality and detailed land cover mapping across the whole country of China and some other Asian countries at meter-resolution.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
