ShrimpWiz: More animal welfare in domestic shrimp farming through AI
Shrimps in German supermarkets come almost exclusively from farms outside the EU - without any proof of whether they have been kept in a species-appropriate manner. Under the leadership of the Alfred Wegener Institute, a consortium is working with the company Oceanloop on the "ShrimpWiz" project to investigate how land-based shrimp farming can be established in Germany that guarantees animal welfare and is economically viable for companies. To this end, they are using image recognition software to automatically examine and care for the animals.
Early stress detection for shrimp tails (red=stressed, green=not stressed)
Bert Wecker
Determination of the body length to calculate the individual weight (green frame / red segmentation mask = shrimp recognized / length not measured, green frame / green segmentation mask = length measured)
Bert Wecker
In modern land-based aquaculture, farm operators have to regularly fish, measure and weigh their shrimp in order to record the number of animals and their condition. However, this causes stress to the shrimp and reduces animal welfare. It is also practically impossible to detect symptoms of stress or even sick animals, even under optimal lighting conditions in the breeding facilities. This is precisely where the "ShrimpWiz" project comes in: Under the leadership of the Alfred Wegener Institute, Helmholtz Center for Polar and Marine Research (AWI), a team of researchers and engineers in collaboration with Oceanloop, a pioneer in European indoor shrimp farming, has developed a system that can count shrimp in photos using AI-assisted image recognition software. Under realistic breeding conditions and in real time, the system can also determine the length of the animals with an accuracy of 95 percent.
Raising awareness for sustainable and species-appropriate shrimp farming with AI
The first prototype was tested at Oceanloop's research and development farm in Kiel. A modern smartphone installed above the water surface automatically photographs the shrimp once a minute and transmits the live data to a local server. Here, Computer Vision's algorithms count each individual shrimp in each image and measure its length. By combining high-resolution image quality, state-of-the-art camera hardware, powerful computers and the latest generation of AI-based image processing models, the team was even able to detect visual signs of stress in the animals.
Oceanloop systems use clear water for breeding, unlike pond production. These systems are therefore ideal for AI-supported shrimp monitoring, as the consortium was able to demonstrate in the previous "MonitorShrimp" project. Due to the high turbidity of the water in traditional pond systems, optical detection of animal welfare, whether with the naked eye or automated image recognition, is virtually impossible. Dr. Stephan Ende, the coordinator of the project at the AWI, is convinced that clear water technology is therefore the key to animal welfare issues in intensive aquaculture facilities: "The use of image recognition software to measure the shrimp enables accurate and non-invasive monitoring of animal welfare and productivity in shrimp farming - 24 hours a day, 7 days a week. The clear water technology combined with our 'Early Welfare Alert' software can be the starting point for any welfare labeling in the future shrimp industry." The aim of "ShrimpWiz" is to develop a market-ready animal welfare software for land-based shrimp farming that enables all the necessary information to be recorded in a single shot, including biomass, stress and - at a later stage - possible diseases.
"The non-invasive, real-time monitoring of key production parameters such as growth, feed conversion, survival and stress will make a decisive contribution to a better understanding of shrimp farming. We can use this to develop an artificial neural network that takes into account all available farm data, which can easily add up to more than a hundred," says Dr. Bert Wecker, CTO of Oceanloop. Tomasz Kowalczyk, founder and CEO of NeuroSYS, which was involved in the development of the algorithm for the project, explains: "Technological advances can transform companies and entire industries. We are ready to be part of this change and are working to introduce the benefits of artificial intelligence and deep learning to the shrimp farming industry."
The consortium sees the development of AI-based software as an opportunity not only to improve animal welfare but also to increase production efficiency. The technology can help drive the digitalization of indoor shrimp farming, which is necessary to achieve today's retail price levels. "Demonstrating the technical feasibility of alternative solutions is crucial to meet the growing awareness of customers and stakeholders for more sustainable and species-appropriate shrimp farming," concludes Stephan Ende.
The project is funded by the Federal Ministry of Food and Agriculture (BMEL) on the basis of a decision by the German Bundestag via the Federal Agency for Agriculture and Food (BLE) as part of the innovation funding program.
Note: This article has been translated using a computer system without human intervention. LUMITOS offers these automatic translations to present a wider range of current news. Since this article has been translated with automatic translation, it is possible that it contains errors in vocabulary, syntax or grammar. The original article in German can be found here.
Other news from the department science
