Benchmarking Classical and Learning-Based Multibeam Point Cloud Registration ...

• Main Authors: Ling, Li, Zhang, Jun, Bore, Nils, Folkesson, John, Wåhlin, Anna
• Format: Article in Journal/Newspaper
• Language: unknown
• Published: arXiv 2024
• Subjects: Computer Vision and Pattern Recognition cs.CV; Robotics cs.RO; FOS Computer and information sciences; West Antarctica; Antarc*; Antarctica
• Online Access: https://dx.doi.org/10.48550/arxiv.2405.06279; https://arxiv.org/abs/2405.06279

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 ... : Accepted at ICRA 2024 (IEEE International Conference on Robotics and Automation 2024) ...