期刊
REMOTE SENSING OF ENVIRONMENT
卷 264, 期 -, 页码 -出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/j.rse.2021.112590
关键词
Building height; High-resolution; Multi-view; ZY-3; Multi-task; Deep learning
资金
- National Natural Science Foundation of China [41771360, 41971295]
The study focuses on using high-resolution multi-view satellite images for building height estimation, proposing the M(3)Net deep network model that can accurately estimate building height at a spatial resolution of 2.5 meters. Testing on 42 Chinese cities showed that M(3)Net outperformed the RF method with a lower root mean square error (RMSE), and the inclusion of ZY-3 multi-view images significantly reduced the uncertainty of building height prediction.
Knowledge of building height is critical for understanding the urban development process. High-resolution optical satellite images can provide fine spatial details within urban areas, while they have not been applied to building height estimation over multiple cities and the feasibility of mapping building height at a fine scale (< 5 m) remains understudied. Multi-view satellite images can describe vertical information of buildings, due to the inconsistent response of buildings (e.g., spectral and structural variations) to different viewing angles, but they have not been employed to deep learning-based building height estimation. In this context, we introduce high-resolution ZY-3 multi-view images to estimate building height at a spatial resolution of 2.5 m. We propose a multi-spectral, multi-view, and multi-task deep network (called M(3)Net) for building height estimation, where ZY-3 multi-spectral and multi-view images are fused in a multi-task learning framework. A random forest (RF) method using multi-source features is also carried out for comparison. We select 42 Chinese cities with diverse building types to test the proposed method. Results show that the M(3)Net obtains a lower root mean square error (RMSE) than the RF, and the inclusion of ZY-3 multi-view images can significantly lower the uncertainty of building height prediction. Comparison with two existing state-of-the-art studies further confirms the superiority of our method, especially the efficacy of the M(3)Net in alleviating the saturation effect of high-rise building height estimation. Compared to the vanilla single/multi-task models, the M(3)Net also achieves a lower RMSE. Moreover, the spatial-temporal transferability test indicates the robustness of the M(3)Net to imaging conditions and building styles. The test of our method on a relatively large area (covering about 14,120 km(2)) further validates the scalability of our method from the perspectives of both efficacy and quality. The source code will be made available at https://github.com/lauraset/BuildingHeightModel.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据