High-Resolution Bathymetry by Deep-Learning Based Point Cloud Upsampling
Gridded bathymetric data are often used to understand seafloor topography; however, high-resolution data are rare. To obtain high-resolution gridded bathymetric data, the observations from which the data are derived must be densely measured. However, this process is time consuming and expensive. In...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10379585/ |
| _version_ | 1797357086163599360 |
|---|---|
| author | Naoya Irisawa Masaaki Iiyama |
| author_facet | Naoya Irisawa Masaaki Iiyama |
| author_sort | Naoya Irisawa |
| collection | DOAJ |
| description | Gridded bathymetric data are often used to understand seafloor topography; however, high-resolution data are rare. To obtain high-resolution gridded bathymetric data, the observations from which the data are derived must be densely measured. However, this process is time consuming and expensive. In this study, we propose a method to obtain dense bathymetric data from sparse observations by treating the observed data as a 3D point cloud and applying a deep-learning-based point cloud upsampling technique. The upsampled cloud points were converted into gridded form. The effectiveness of our method was verified through both quantitative and qualitative analyses. |
| first_indexed | 2024-03-08T14:39:23Z |
| format | Article |
| id | doaj.art-6abc94530f264079aa0c5fc8b4f5d8b0 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T14:39:23Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-6abc94530f264079aa0c5fc8b4f5d8b02024-01-12T00:01:54ZengIEEEIEEE Access2169-35362024-01-01124387439810.1109/ACCESS.2023.334914910379585High-Resolution Bathymetry by Deep-Learning Based Point Cloud UpsamplingNaoya Irisawa0https://orcid.org/0009-0003-3941-1667Masaaki Iiyama1https://orcid.org/0000-0002-7715-3078Graduate School of Data Science, Shiga University, Hikone, Shiga, JapanGraduate School of Data Science, Shiga University, Hikone, Shiga, JapanGridded bathymetric data are often used to understand seafloor topography; however, high-resolution data are rare. To obtain high-resolution gridded bathymetric data, the observations from which the data are derived must be densely measured. However, this process is time consuming and expensive. In this study, we propose a method to obtain dense bathymetric data from sparse observations by treating the observed data as a 3D point cloud and applying a deep-learning-based point cloud upsampling technique. The upsampled cloud points were converted into gridded form. The effectiveness of our method was verified through both quantitative and qualitative analyses.https://ieeexplore.ieee.org/document/10379585/Bathymetrydeep learningpoint cloudssuper-resolution |
| spellingShingle | Naoya Irisawa Masaaki Iiyama High-Resolution Bathymetry by Deep-Learning Based Point Cloud Upsampling IEEE Access Bathymetry deep learning point clouds super-resolution |
| title | High-Resolution Bathymetry by Deep-Learning Based Point Cloud Upsampling |
| title_full | High-Resolution Bathymetry by Deep-Learning Based Point Cloud Upsampling |
| title_fullStr | High-Resolution Bathymetry by Deep-Learning Based Point Cloud Upsampling |
| title_full_unstemmed | High-Resolution Bathymetry by Deep-Learning Based Point Cloud Upsampling |
| title_short | High-Resolution Bathymetry by Deep-Learning Based Point Cloud Upsampling |
| title_sort | high resolution bathymetry by deep learning based point cloud upsampling |
| topic | Bathymetry deep learning point clouds super-resolution |
| url | https://ieeexplore.ieee.org/document/10379585/ |
| work_keys_str_mv | AT naoyairisawa highresolutionbathymetrybydeeplearningbasedpointcloudupsampling AT masaakiiiyama highresolutionbathymetrybydeeplearningbasedpointcloudupsampling |