Sultan Qaboos University researchers create new underwater fish weight system
Researchers from Sultan Qaboos University published a new method for estimating fish weight in real time without full depth maps on October 23, 2026.
System uses paired cameras and AI
The new technology relies on two synchronized cameras working together to identify fish. Artificial intelligence identifies the animals in paired images before calculating their depth from geometric relationships between bounding boxes.
Machine learning predicts accurate biomass
Detected length and width measurements feed into an XGBoost model to predict weight. This approach avoids the need for substantial computing power required by conventional imaging methods.
Testing covered tilapia over time
Scientists evaluated the system using tilapia monitored across four growth stages over a period of 15 months. Manual measurements provided reference values for length, width and weight during the testing phase.
Reported by one outlet
Only one outlet has published this. Nothing here has been checked against a second report, so read it as that outlet's account and follow the link below for the original.
Reported by
1 independent outlet. Headline as published. Links open the original report.