The developed technology targets the early detection of fish diseases in small tanks, pools or marine cages. It is built on a system of non-invasive, contactless monitoring of fish behaviour e.g. trajectories and image analysis of visible symptoms of fish diseases on their scales, such as Vibriosis.
The system design was patented in 2016. The operating principle of this system is based on the effect of strong absorption of near infrared (NIR) range light by water, thus allowing estimation of fish distance based on the corresponding fish object brightness on the camera image. The use of NIR illuminator as a part of the infra-red reflection (IREF) system allows fish behavior monitoring in the dark so as not to affect fish circadian rhythm.
The contactless approach uses 2D or 3D camera to capture both the trajectory of fish and the detailed appearance of the fish in 3D space illuminated by near infra-red (IR) light range. The camera measures reflected IR light from the fish and the light intensity to correlate the depth (distance) of the fish. Specific fish individual can be identified and modelled with detailed analysis of the fish appearance and unique patterns on its skin. Behavioural changes, such as patterns of the fish litter and visible symptoms on the fish litter can be detected and analysed.
The system has been tested in cooperation with the Norwegian Institute of Food, Fisheries and Aquaculture Research (NOFIMA).
The advantages of the IREF system over well-known stereo vision systems are lower hardware cost and less computationally intensive 3D coordinates estimation algorithm, while the disadvantage is lower accuracy that is nevertheless acceptable for most applications of aquaculture fish monitoring.
A system evaluation under aquaculture facility conditions with Atlantic salmon (Salmo salar) using flow-through water in tanks,showed the mean depth estimation error was equal to 5.3 ± 4.0 (SD) cm. The physiological variations among conspecific individual fish introduced the mean depth estimation error of 1.6 ± 1.3 (SD) cm.
The European Commission has defined (COM (2009) 162 final) the stagnation of fish production within the EU as opposed to the increase in imports mainly from Asia, which is growing annually by 70%. Animal production in third world countries is much more moderate than the EU, putting pressure on European fish farms in the area of highly efficient production. Highly efficient production or intensive aquaculture carries threats in the form of stress, disease and mortality of fish.
For this reason, fish farms are looking for new technologies to minimise such risks. The big challenge with commercial fish farms is the unpredictable occurrence of diseases that mostly decimate the entire farm (up to 200,000 fish). At present, some of the farms are equipped with underwater cameras that allow fish behavior monitoring. However, CCTV footage is evaluated by an operator who is not an expert in disease detection and does not have enough time to analyse the behaviour of individuals in the flock. This technology addresses the need for automatic and early detection of fish diseases through detection of visible disease symptoms and analysis of fish behaviour. Early detection of the disease minimises the spread of the disease within farming and thus minimises financial losses.