Sharing Aquaculture

  • Bluetalks
  • Podcasts
  • Speakers
  • About
  • Log in
  • Log out
  • Log in
Loading...
Log in to watch video

Solving underwater fish segmentation with realistic labeled data generation and test-time augmentation

October 7, 2025

Andrei Jelea


See next

Image for Overvåkbar og fremtidsrettet infrastruktur for åpne merdanlegg
Offshore Aquaculture

Overvåkbar og fremtidsrettet infrastruktur for åpne merdanlegg

09. april 2026

Image for Hvilke leverandører trenger vi for havbruk til havs?
Offshore Aquaculture

Hvilke leverandører trenger vi for havbruk til havs?

09. april 2026

Image for Blár: Veien videre etter utviklingstillatelsene
Offshore Aquaculture

Blár: Veien videre etter utviklingstillatelsene

08. april 2026

Image for Sammensatt lydbilde som kontrollstrategi mot lakselus
salmon lice

Sammensatt lydbilde som kontrollstrategi mot lakselus

31. mars 2026

Image for Alotta’s Journey into Chile – Floating Solar Systems for Aquaculture
Exports

Alotta’s Journey into Chile – Floating Solar Systems for Aquaculture

20. mars 2026

In this video, Andrei Jelea from NORCE shows how AI can solve one of aquaculture's big challenges: segmenting fish in underwater videos. By generating realistic synthetic training data and using test-time augmentation, the method reduces the need for manual labeling and improves monitoring of fish health and behavior.

Categories

  • Offshore Aquaculture
  • Technology

Bluetalk

  • > About Bluetalk

Get access to the entire library?

  • > Become a member of Stiim

Follow us

  • > LinkedIn
  • > Instagram
  • > Facebook

Partners

  • > Blue Planet Academy
  • > Stiim Aqua Cluster
  • > Blue Planet
  • >Aquanext
  • Norsk
  • Español
  • 中文 (简体)