Enterprise Europe Network

Biomass estimation system in aquaculture based on 3D images

Country of origin:
External Id: 
Last update
Expiration date


Partner keyword: 
Fish / Fisheries / Fishing Technology
Food Technology
Optical Technology related to measurements
Industrial measurement and sensing equipment
Machine vision software and systems
Agriculture, Forestry, Fishing, Animal Husbandry & Related Products


A Spanish university has developed a system for estimating the biomass necessary for feeding in aquaculture. The estimation is made through the reconstruction of 3D images to establish the optimum amount of biomass for feeding fish in intensive aquaculture facilities with the smallest possible margin of error. In addition, it is useful to perform fish counting, growth tracking and for monitoring their behaviour. Aquaculture companies are sought to develop applications under license agreements.



In aquaculture, the food costs represent approximately 45% of the operating costs in a fish farm. Thus, the reduction of food costs is essential to achieve the sustainability of such industry, existing great potential both in the reduction of food costs per unit and through the adoption of appropriate food management strategies. The present invention solves typical technical problems in this area (variable fish speed, low resolution or measurement errors in the calculation of the weight and height of the fish) through the reconstruction of 3D images.

Researchers from a Spanish university working in electronic engineering provide a system for estimating biomass in aquaculture based on reconstructions of images in three dimensions. The system comprises a frame that defines a cube whose interior is divided into two different zones: the first one is a passage for the fish and a second one is configured to prevent the access of fish to its interior and where several sensors for oxygen, pH, conductivity and turbidity are provided, as well as an RFID reader device connected with an RFID antenna arranged in a frame at the entrance of the fish passage zone. Unlike current systems, this technology works out the biomass in real time based on the volume of the fish and its density. It also uses a discretization and tracking algorithm and, with the use of all the obtained variables from the sensors and the use of neural networks, predictions of the state and behavior of the fish can be performed.

The researchers would like to reach license agreements with companies operating in the aquaculture field with the aim to develop applications of the described technology.

Advantages & innovations

Cooperation plus value: 
- Accuracy. Current systems base the calculation of biomass on models that characterize the relationship between the length of the fish and their mass. This system makes the estimation based on the volume of the fish and its density by 3D image reconstruction with two cameras and stereographic technology. - Low cost equipment. New low-cost stereo cameras allow to calculate depth and enable devices to see, understand, interact with, and learn from their environment — powering intuitive, natural interaction and immersion. The onboard processor performs all the depth calculations on the camera, allowing for low power, platform agnostic devices. - Unlike other systems, in which the selection of the fish is done manually by a technician, this technology uses a fish discretization and tracking algorithm, which can also help to follow the fish even when they overlap each other. - Real time biomass estimation. The system has an antenna that, together with a reader, constitutes a radio frequency (RFID) system that allows real-time identification of the fish. This novelty, not present in current commercial equipment, provides a substantial improvement in the estimation of biomass as it allows the individual fish biomass to be monitored and compared with the global calculation. - Record the physical variables of the farm. The system has a set of sensors that check the state of the medium at all times (oxygen, pH, conductivity and turbidity). Being a system that works continuously, with the use of all those inputs and the use of neural networks, predictions of the state and behaviour of the fish can be obtained.

Stage of development

Cooperation stage dev stage: 
Under development/lab tested

Partner sought

Cooperation area: 
Type of partner sought: Industry. Specific area of activity of the partner: Companies that operate in the aquaculture field. Task to be performed: Development of applications of the described invention.

Type and size

Cooperation task: 
SME 11-50,SME <10,>500 MNE,251-500,SME 51-250,>500