Historical land cover (LC) maps are significant geospatial data sources used to understand past land characteristics and accurately determine the long-term land changes that provide valuable insights into the interactions between human activities and the environment over time. This article introduces a novel open LC benchmark dataset generated from very high spatial resolution historical Hexagon (KH-9) reconnaissance satellite images to be used in deep learning (DL)-based image segmentation tasks. This new benchmark dataset, which includes very high-resolution (VHR) mono-band Hexagon images of several Turkish and Bulgarian territories from the 1970s and 1980s, covers a large geographic area. Our dataset includes eight LC classes inspired by the European Space Agency (ESA) WorldCover project except for the tree class, which we divided into subclasses, namely agricultural fruit trees and other trees. We implemented widely used U-Net++ and DeepLabv3+ segmentation architectures with appropriate hyperparameters and backbone structures to demonstrate the versatility and impact of our HexaLCSeg dataset and to compare the performance of these models for accurate and fast LC mapping of past terrain conditions. We achieved the highest accuracy using U-Net++ with an SE-ResNeXt50 backbone and obtained an F1-score of 0.8804. The findings of this study can be applied to different geographical regions with similar Hexagon images, providing valuable contributions to the field of remote sensing and LC mapping. Our dataset, related source codes, and pretrained models are available at https://github.com/RSandAI/HexaLCSeg and https://doi.org/10.5281/zenodo.11005344 .

中文翻译：

---

HexaLCSeg：来自 Hexagon 卫星图像的用于土地覆盖分割的历史基准数据集 [软件和数据集]


历史土地覆盖 (LC) 地图是重要的地理空间数据源，用于了解过去的土地特征并准确确定长期土地变化，为了解人类活动与环境之间随时间的相互作用提供有价值的见解。本文介绍了一种新颖的开放 LC 基准数据集，该数据集由极高空间分辨率的历史 Hexagon (KH-9) 侦察卫星图像生成，用于基于深度学习 (DL) 的图像分割任务。这个新的基准数据集包括 20 世纪 70 年代和 1980 年代几个土耳其和保加利亚领土的超高分辨率 (VHR) 单波段六边形图像，覆盖了很大的地理区域。我们的数据集包括受欧洲航天局 (ESA) WorldCover 项目启发的八个 LC 类，除了树木类，我们将其分为子类，即农业果树和其他树木。我们实现了广泛使用的 U-Net++ 和 DeepLabv3+ 分割架构，并具有适当的超参数和骨干结构，以展示 HexaLCSeg 数据集的多功能性和影响，并比较这些模型的性能，以准确、快速地对过去的地形条件进行 LC 映射。我们使用 U-Net++ 和 SE-ResNeXt50 主干网络实现了最高的准确率，并获得了 0.8804 的 F1 分数。这项研究的结果可以应用于具有相似Hexagon图像的不同地理区域，为遥感和LC制图领域提供了宝贵的贡献。我们的数据集、相关源代码和预训练模型可在 https://github.com/RSandAI/HexaLCSeg 和 https://doi.org/10.5281/zenodo.11005344 获取。