Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.06279 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911872902496256 |
|---|---|
| author | Ling, Li Zhang, Jun Bore, Nils Folkesson, John Wåhlin, Anna |
| author_facet | Ling, Li Zhang, Jun Bore, Nils Folkesson, John Wåhlin, Anna |
| contents | Deep learning has shown promising results for multiple 3D point cloud registration datasets. However, in the underwater domain, most registration of multibeam echo-sounder (MBES) point cloud data are still performed using classical methods in the iterative closest point (ICP) family. In this work, we curate and release DotsonEast Dataset, a semi-synthetic MBES registration dataset constructed from an autonomous underwater vehicle in West Antarctica. Using this dataset, we systematically benchmark the performance of 2 classical and 4 learning-based methods. The experimental results show that the learning-based methods work well for coarse alignment, and are better at recovering rough transforms consistently at high overlap (20-50%). In comparison, GICP (a variant of ICP) performs well for fine alignment and is better across all metrics at extremely low overlap (10%). To the best of our knowledge, this is the first work to benchmark both learning-based and classical registration methods on an AUV-based MBES dataset. To facilitate future research, both the code and data are made available online. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_06279 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Benchmarking Classical and Learning-Based Multibeam Point Cloud Registration Ling, Li Zhang, Jun Bore, Nils Folkesson, John Wåhlin, Anna Computer Vision and Pattern Recognition Robotics Deep learning has shown promising results for multiple 3D point cloud registration datasets. However, in the underwater domain, most registration of multibeam echo-sounder (MBES) point cloud data are still performed using classical methods in the iterative closest point (ICP) family. In this work, we curate and release DotsonEast Dataset, a semi-synthetic MBES registration dataset constructed from an autonomous underwater vehicle in West Antarctica. Using this dataset, we systematically benchmark the performance of 2 classical and 4 learning-based methods. The experimental results show that the learning-based methods work well for coarse alignment, and are better at recovering rough transforms consistently at high overlap (20-50%). In comparison, GICP (a variant of ICP) performs well for fine alignment and is better across all metrics at extremely low overlap (10%). To the best of our knowledge, this is the first work to benchmark both learning-based and classical registration methods on an AUV-based MBES dataset. To facilitate future research, both the code and data are made available online. |
| title | Benchmarking Classical and Learning-Based Multibeam Point Cloud Registration |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2405.06279 |