National-scale mapping of building height using Sentinel-1 and Sentinel-2 time series.
National-scale mapping of building height using Sentinel-1 and Sentinel-2 time series.
复制标题
DOI：
10.1016/j.rse.2020.112128
复制
发表时间：
2021-01
影响因子：
13.5
通讯作者：
Hostert P
中科院分区：
文献类型：
--
作者：
Frantz D;Schug F;Okujeni A;Navacchi C;Wagner W;van der Linden S;Hostert P
城市及其垂直特征对我们的环境有着多方面而深远的影响。然而，对于完整的国家或地区来说，公开获取的高空间分辨率信息仍然大量缺失。在这项研究中，我们结合了Sentinel-1A/B和Sentinel-2A/B时间序列，在10米网格上绘制了整个德国的建筑高度图，解决了农村和城市环境中的建筑结构。我们利用光谱/极化、时间和空间维度的信息，将波段方向的时间聚合统计与形态度量相结合。我们用来自几个3D建筑模型的高精度建筑高度信息训练机器学习回归模型。这种方法的新颖之处在于它的分辨率非常好，但它可以应用的空间范围很大，以及在光学图像中使用建筑阴影。结果表明，仅雷达和仅光学模型均可用于建筑物高度预测，但两种数据源的协同组合效果更佳。当针对独立数据集测试模型时，实现了非常一致的性能（频率加权RMSE为2.9 m至3.5 m），这表明对最频繁出现的建筑物的预测是稳健的。德国各地的平均建筑高度差异很大，德国东部和东南部的建筑较低，而德国西部高度城市化地区的建筑较高。我们强调这种方法在全国范围内的直接适用性。它主要依赖于免费提供的卫星图像和开源软件，这些软件可能允许频繁的更新周期和具有成本效益的制图，这可能与大量不同的应用相关，例如结构特征的物理分析或绘制社会资源使用情况。我们提出了一种在10米网格上预测整个德国建筑高度的方法。协同使用VV/VH Sentinel-1A/B和多光谱Sentinel-2A/B时间序列训练和高质量3D建筑模型的严格验证建筑物高度预测，频率加权RMSE为3.2 m至4.2 m。德国的平均建筑高度与人口密度相关。
Urban areas and their vertical characteristics have a manifold and far-reaching impact on our environment. However, openly accessible information at high spatial resolution is still missing at large for complete countries or regions. In this study, we combined Sentinel-1A/B and Sentinel-2A/B time series to map building heights for entire Germany on a 10 m grid resolving built-up structures in rural and urban contexts. We utilized information from the spectral/polarization, temporal and spatial dimensions by combining band-wise temporal aggregation statistics with morphological metrics. We trained machine learning regression models with highly accurate building height information from several 3D building models. The novelty of this method lies in the very fine resolution yet large spatial extent to which it can be applied, as well as in the use of building shadows in optical imagery. Results indicate that both radar-only and optical-only models can be used to predict building height, but the synergistic combination of both data sources leads to superior results. When testing the model against independent datasets, very consistent performance was achieved (frequency-weighted RMSE of 2.9 m to 3.5 m), which suggests that the prediction of the most frequently occurring buildings was robust. The average building height varies considerably across Germany with lower buildings in Eastern and South-Eastern Germany and taller ones along the highly urbanized areas in Western Germany. We emphasize the straightforward applicability of this approach on the national scale. It mostly relies on freely available satellite imagery and open source software, which potentially permit frequent update cycles and cost-effective mapping that may be relevant for a plethora of different applications, e.g. physical analysis of structural features or mapping society's resource usage. We present a method to predict building height on a 10 m grid for entire Germany. Synergistic use of VV/VH Sentinel-1A/B and multi-spectral Sentinel-2A/B time series Training and rigorous validation with high-quality 3D Building Models Building height predicted with a frequency-weighted RMSE of 3.2 m to 4.2 m. Mean building height in Germany is correlated with population density.
登录
查看更多内容
影响因子：
5
作者：
Doxani, Georgia;Vermote, Eric;Vanhellemont, Quinten
通讯作者：
Vanhellemont, Quinten
影响因子：
3.1
作者：
Borck, Rainald
通讯作者：
Borck, Rainald
影响因子：
4.8
作者：
Frantz, David;Roeder, Achim;Schmidt, Michael
通讯作者：
Schmidt, Michael
DOI：
10.1109/jstars.2017.2787650
发表时间：
2018-03-01
影响因子：
5.5
作者：
Ali, Iftikhar;Cao, Senmao;Wagner, Wolfgang
通讯作者：
Wagner, Wolfgang
影响因子：
4.4
作者：
Bauer-Marschallinger, Bernhard;Sabel, Daniel;Wagner, Wolfgang
通讯作者：
Wagner, Wolfgang