Aquaculture Phenotyping Machine

Date

2021

Partner

Aquaticode

This project was developed in partnership with Aquaticode, a company bringing Machine Learning image recognition to the aquaculture industry. The goal for the machine is to generate robust datasets of images to help build the ML models. For this the machine needs to be able to capture several data inputs, components should be able to waistband a wet environment and processing time per fish should not exceed 5-7 seconds.

The project began with a quick 4 weeks research phase to evaluate a range of technical solutions and approaches. 

After successful field test, building 6 machine, and scanning thosands of fish in 3 countries, Aquaticode was able to secure the fundings to scale their operation.