Loading demo…
← Labs Abyssal Vision
CV + HITL · deep-sea imagery

Seafloor Imagery Intelligence

One deep-sea dive line, end to end: a Google-Maps-style seafloor mosaic with automated polymetallic-nodule detection and real-world sizing, a megafauna expert-review queue, and the analytics that fall out of it — every number computed from the sample imagery, de-duplicated across the 70% frame overlap and sized from the georeferencing. Explore the map, then scroll for the dashboard.

Layers


Unique nodules
Density
Mean size
Coverage
Ground res
Click a nodule to measure it. Scroll to zoom — only tiles in view load, Google-Maps style.
Results Dashboard

Nodule & megafauna analytics

Every number below is computed from the sample imagery by the pipeline — de-duplicated across the 70% frame overlap, sized in real-world units from the georeferencing.

Nodule size distribution

Equivalent circular diameter (cm), unique nodules only.

Overlap de-duplication

Raw detections vs unique nodules after geometric dedup — the "70% overlap" answer, quantified.

Regional breakdown

Survey line split into 6 segments — nodule density (per m²) along track.

Per-frame detections

Raw (all frames) vs owned (counted once). Consistency = stable capture.

Megafauna review queue

Low-confidence candidates are never auto-labelled — they route to a marine biologist. This nodule-pavement line yields few candidates, all in review.

#Candidate taxonConf.Status

Anomalies flagged

Frames with density >1.8σ from mean, plus every fauna candidate — the "flag for expert review" surface.

ItemDetailValue

Export for scientific analysis

Machine-readable outputs — drop straight into QGIS / ArcGIS / pandas.

Sample exports from this pilot line. The full pipeline also emits a UTM GeoJSON / GeoPackage of every sized nodule for direct GIS ingest.