Transect-tape segmentation and dynamic ROI perception for robotic underwater surveys
Transect surveys are a standard sampling method in diver-led underwater environmental assessment, but, to our knowledge, no prior public dataset treats the transect tape as the primary target for autonomous robotic following. We present a 12,742-image multi-source underwater dataset with polygon annotations, spanning controlled pool recordings and multiple outdoor sources. A trained segmentation model is evaluated on unseen acquisition sources, alongside a separate benchmark of zero-shot methods. We also introduce a model-agnostic dynamic region-of-interest (ROI) method that uses previous detections to focus segmentation and expands the search after detection loss. The resulting tape position and orientation estimates support robotic following. Validation includes video replays, pool trials with motion capture, and open-water deployments. YOLOv8n-seg achieves mask mAP@50 of 0.8135 on a held-out video source, although performance varies across acquisition sources. In three open-water runs at a previously unseen site, the system provided tape position and orientation estimates for 87.8% of the combined run time. The dataset supports reproducible evaluation of transect perception, and the field trials provide evidence of generalisation to a new underwater environment.
Authors
- Waseem Akram (ORCID: https://orcid.org/0000-0002-7401-5120)
- Tarek Taha (ORCID: https://orcid.org/0000-0001-8267-1681)
- Mahmoud Elmezain (ORCID: https://orcid.org/0000-0001-8750-1366)
- Irfan Hussain (ORCID: https://orcid.org/0000-0002-9181-3407)
- Atif Sultan (ORCID: https://orcid.org/0009-0002-6110-5554)
Institutions
- Khalifa University of Science and Technology (AE)
- University of Zagreb (HR)
- Faculty of Electrical Engineering and Computing in Zagreb (HR)
Publication Details
- Journal
- Ocean Engineering
- Published
- 2026-11-18
- DOI
- https://doi.org/10.1016/j.oceaneng.2026.129357
- Primary Topic
- Advanced Neural Network Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Khalifa University of Science, Technology and Research