Bringing Computer Vision and AI to Aquaculture

The Problem

Every aquaculture farmer knows that feeding and health observation of fish stock is the greatest cost of production in Aquaculure. Ensuring each and every fish is optimally fed, healthy and environmentally safe is a massive cost to farmers. Rearing healthy salmon requires a delicate balance between overfeeding at the cost of feed loss, or underfeeding at the cost of sub-optimal fish growth.

Combining Computer vision and Artificial Intelligence

Our powerful machine learning algorithms extract real-time analytics of the behavior and movement of aquaculture stock. Observe combines the video stream data with existing sensory data platforms such as disolved oxygen, pH, salinity, temperature and other sensors to calculate optimal feeding portions. With this data, farmers can make data-driven decisions related to on-demand feeding, the health of the stock, and the environmental impact of the farm.


This demo is footage from an aquaculture farm rearing salmon. With Observe's technology fish are tracked and measured, as well as feeding pellet count loss. Computer vision technology provides real feedback on the fish themselves rather than simply give information on the environment of the cage. This is a first step to automatically providing farmers with metrics related to feed wastage, the growth and behavior of the stock.

Building on the computer vision system, we quantifying the feeding behavior, movement, and growth rate of the stock of fish. Combining this data with the oxygen, temperature, pH, salinity etc. data already available on farms, our system can provide real-time informed suggestions on optimal feed usage as well as flagging health issues within the stock.

We are actively working with many farms across the world. If our technology is of interest to you, please contact us.