Annotate the ocean,
box by box.

Start Annotating → See the pipeline ⌘ Built for marine research workflows
4
pipeline stages
5
role-based views
DINOv3
AI classification
JSON
research export
// The Pipeline

Four stages, one production line.

Each image moves through a dedicated stage. Specialists pick up where the previous role left off — no context-switching, no email chains.

STAGE 01
Bounding
Annotator

Draw, drag, and resize bounding boxes over regions of interest. Keyboard shortcuts (V / D / E) keep your hands on the canvas.

STAGE 02
Classifying
Classifier

DINOv3 suggests a top-K taxonomy in real time. Accept the AI label or pick from the taxonomy panel — batch-classify a whole image in one click.

STAGE 03
Specifying
Researcher

Drill down to species level. Add identification notes, confidence flags, and finalise observations one box at a time.

STAGE 04
Complete
Export

Finalised images export to clean JSON — ready to feed downstream models, papers, or shared with collaborators.

// What's inside

Built for the way marine teams actually work.

DINOv3 in the loop

Top-K AI suggestions per box, batch-classify entire images, toggle auto-suggest off when you want pure manual control.

Precision boxing

Draw, drag, resize from any handle. Per-box opacity slider keeps the underlying imagery legible while you work.

Role-based queues

Annotators, classifiers, researchers, viewers, and admins each see only the work that needs them — with per-role queue counts.

Drag-and-drop upload

Drop images directly onto the gallery page to upload. Files go straight to cloud storage — no extra steps, no page reload.

Cluster & category filters

Slice the gallery by cluster, taxonomy category, or pipeline stage. Find the next image to work on in seconds.

Research-ready JSON

Researchers and admins export finalised annotations as clean JSON — directly consumable by downstream ML pipelines.

Keyboard-first

V to select, D to draw, E to erase, Esc to deselect, Delete to remove. The canvas stays under your cursor.

Routing summary

A live per-image breakdown of category counts and finalisation status, so researchers always know what is left.

// Roles

Five roles. Zero overlap.

Permissions are enforced end-to-end. Each user sees only the controls that belong to their role, keeping the pipeline focused and the data clean.

Annotator
  • Upload images
  • Draw bounding boxes
  • Submit to Classify
Classifier
  • DINOv3 AI suggestions
  • Apply taxonomy labels
  • Batch classify
Researcher
  • Specify species
  • Add field notes
  • Finalise & Export JSON
Admin
  • Full pipeline access
  • User management
  • Dashboard & export
Viewer
  • Read-only gallery
  • Inspect annotations
  • No edits
// Taxonomy

A taxonomy tuned for the reef.

Five top-level categories, color-coded across every panel and overlay, extensible from the admin dashboard.

Coral
Acropora · Porites · Montipora
Fish
Pomacentridae · Labridae · Chaetodontidae
Invertebrate
Echinoderms · Crustaceans · Molluscs
Algae
Halimeda · Sargassum · Turbinaria
Other
Substrate · Sand · Unknown
⬡ Ready when you are

Turn raw underwater imagery into research-ready data.

Sign in with your lab account to start uploading. Your team's pipeline, queues, and taxonomy are pre-configured.