five

<b>Leveraging Chinese GaoFen-7 imagery for high-resolution building height estimation in multiple cities</b>

收藏
DataCite Commons2024-02-13 更新2024-08-18 收录
下载链接:
https://figshare.com/articles/dataset/_b_Leveraging_Chinese_GaoFen-7_imagery_for_high-resolution_building_height_estimation_in_multiple_cities_b_/24305428
下载链接
链接失效反馈
官方服务:
资源简介:
This is a building height dataset estimated from Chinese Gaofen-7 imagery. The estimated building heights in the different cities (Tianjin, Lanzhou, Chongqing, Ningbo, Guangzhou, and Shenzhen) are highly consistent with the reference building height data obtained from field-measured building height data, building floor data, and airborne light detection and ranging (LiDAR) data. The R<sup>2</sup> varies from 0.75 to 0.90, while the root mean square error (RMSE) ranges from 4.06 m to 8.06 m. The validation of the estimated building heights over 106,366 buildings using airborne LiDAR height data yielded R<sup>2</sup> and RMSE of 0.90 and 6.72 m for Shenzhen and 0.89 and 4.06 m for Hong Kong, respectively. Note that the Viewing angles for the GF-7Backward image are -5°, so there is a small offset between the building roof derived from GF-7 image and the building roof derived from other images. Reference: https://doi.org/10.1016/j.rse.2023.113802.

本数据集为基于中国高分七号(Gaofen-7)遥感影像估算得到的建筑高度数据集。针对天津、兰州、重庆、宁波、广州及深圳等多个城市的估算建筑高度,与通过实地实测建筑高度数据、建筑楼层数据以及机载激光雷达(LiDAR)数据获取的参考建筑高度数据具有极高一致性。其中决定系数(R²)介于0.75至0.90之间,均方根误差(RMSE)则处于4.06米至8.06米的区间内。针对106366栋建筑的估算建筑高度,通过机载LiDAR高度数据开展验证的结果显示:深圳的决定系数与均方根误差分别为0.90和6.72米,香港则分别为0.89和4.06米。需注意的是,GF-7后向影像的观测角为-5°,因此通过GF-7影像提取的建筑屋顶与其他影像提取的建筑屋顶之间存在微小偏移。参考文献:https://doi.org/10.1016/j.rse.2023.113802.
提供机构:
figshare
创建时间:
2023-10-13
二维码
社区交流群
二维码
科研交流群
商业服务