期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2022
卷号：V-1-2022
页码：41-48
DOI：10.5194/isprs-annals-V-1-2022-41-2022
语种：English
出版社：Copernicus Publications
摘要：Positioning accuracy is a key indicator that restricts the accuracy of satellite image mapping. Laser altimetry acquires surface height in decimeters or higher accuracy, providing high-accuracy topographic information for satellite photogrammetry. This study proposes a four-step high-accuracy positioning method called laser altimetry data-guided stereo images positioning (LGSP): photon outlier removal, digital surface model (DSM) generation by a variant of the tube-shape semi-global matching (tSGM), fast point cloud alignment, and DSM and rational function model (RFM) refining. First, outliers of the laser altimetry data are filtered out via confidence selection and open access DSM constraints. Second, the DSM around high-accuracy photons is generated via the variant of tSGM. Third, fast point cloud alignment is performed to align the DSM with laser altimetry data. Finally, we propose a high-resolution stereo model refinement method based on alignment parameters. Experiments on two satellite stereo datasets with different loads, resolutions, and topographies show that LGSP improved the planimetry accuracy of satellite stereo images after adding laser altimetry data. What’s more, LGSP significantly improved the height accuracy of satellite images. Specifically, LGSP reduced the height errors from the original 5.99 m to 1.00 m for the Ziyuan-3 stereo dataset and from the original 20.39 m to 0.83 m for the Gaofen-7 stereo dataset, and slightly outperformed bundle adjustment in which four ground control points were deployed around the four corners of the stereo images. RFM refining based on alignment parameters has been made publicly available at https://mega.nz/file/EFQASJ6A#BKjoupHVshylQR4wCxGd9BDtg08bhy-_aY-c_rHnl-0.
