A high-resolution beach imagery dataset with COCO annotations for deep learning-based Sargassum monitoring in coastal environments
Javier Arellano-Verdejo, Hugo E. Lazcano-Hernandez, Arturo Trejo-Morales, Martin Santos Romero · 2026
Read A high-resolution beach imagery dataset with COCO annotations for deep learning-based Sargassum monitoring in coastal environments by Javier Arellano-Verdejo, Hugo E. Lazcano-Hernandez, Arturo Trejo-Morales, Martin Santos Romero (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13264090.txt.
Description
Javier Arellano-Verdejo and co-authors present a 2026 beach image dataset for tracking Sargassum seaweed along the coast of Quintana Roo, Mexico. Large Sargassum arrivals harm tourism, wildlife and local budgets, so automated measurement from photographs could guide cleanup. The collection holds high-resolution color images with pixel-level masks that label Sargassum, sand and other elements such as water, plants, sky and people.
Masks were converted into polygon annotations in the standard COCO format used by many vision models. Summary statistics describe how classes are distributed across scenes, which helps users judge difficulty. Teams can train and compare segmentation models such as U-Net or Mask R-CNN on a shared benchmark instead of building private test sets from scratch.
Catalog record
| CREATOR | Javier Arellano-Verdejo, Hugo E. Lazcano-Hernandez, Arturo Trejo-Morales, Martin Santos Romero |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 25 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |