Skip to content

Long-term monitoring

Underwater Relocalisation and Mapping

Monitoring a reef means returning to exactly the same place and comparing what changed.

Why it matters

Underwater scenes change constantly: corals grow, bleach and recover, and visibility varies from day to day. We re-localise images of dynamic underwater environments, align them for change detection, reconstruct sites across many sessions, and correct for refraction through flat camera ports.

Team

Members of my group at the QUT Centre for Robotics and close collaborators.

Tobias Fischer
Lead

Beverley Gorry

Beverley Gorry
PhD student

Chelim Lim

Chelim Lim
PhD student

Alejandro Fontan

Alejandro Fontan
Collaborator

Emilio Olivastri

Emilio Olivastri
Former postdoc

Publications

Selected papers from this line of work. See all publications.

arXiv 2026

Image-Space Refraction Correction for Underwater 3D Reconstruction: Warping Flat-Port Views into Pinhole Perspective

Chelim Lim, Tobias Fischer, Emilio Olivastri, Beverley Gorry, Michael Milford, and Alejandro Fontan

arXiv 2610.07788

PDF Code BibTeX

arXiv 2026

Long-Term Multi-Session 3D Reconstruction Under Substantial Appearance Change

Beverley Gorry, Tobias Fischer, Michael Milford, and Alejandro Fontan

arXiv 2602.20584

IROS 2025

Image-Based Relocalization and Alignment for Long-Term Monitoring of Dynamic Underwater Environments

Beverley Gorry, Tobias Fischer, Michael Milford, and Alejandro Fontan

IEEE/RSJ International Conference on Intelligent Robots and Systems 2025

PDF Publisher Code Poster Video BibTeX

More projects

Reef Restoration and Adaptation Program (T2D) · Faculty Lead

Reef Guidance System

AI that decides in real time where coral seeding devices should be dispensed on the Great Barrier Reef.

Label-efficient learning

Reef Scene Understanding

Segmenting corals, seagrass and marine species from just a handful of labels per image.