Development of a non-invasive, acousto-optic underwater fish observatory (UFO)
Thünen Institute of Sea Fisheries
Prof. Dr. Joachim Gröger
The objective of the project is the development and construction of an underwater fish observatory (UFO) for the bentho-pelagic zone, which couples modern acoustic and optical techniques for monitoring fish stocks to their biotic environment. The UFO is to be coupled to the FINO3 platform, which allows reliable data transmission and coupling to COSYNA (Coastal Observation System for Northern and Arctic Seas). For this purpose, an order "Installation and Operation Offshore" was awarded to the FuE-Zentrum FH Kiel GmbH. Six partners from universities, institutes and companies work together in this project.
The subproject of the University of Applied Sciences Kiel deals with fish localization, tracking and classification in video sequences as well as acoustic pattern recognition.
University of Applied Sciences Kiel - Faculty of Computer Science and Electrical Engineering
Prof. Dr. Hauke Schramm and Prof. Dr.-Ing. Sabah Badri-Höher
In addition to the development and application of underwater technology, a central research goal of the three-year project is the development of novel methods for the automatic localization, measurement and classification of objects on underwater photographs (photos or video sequences). Already existing, developed at the University of Applied Sciences Kiel analysis methods from medical image processing will be used and adapted to the specific problem of the UFO. The proposed algorithms are based on a combination of the "Generalized Hough Transformation" with machine learning methods and have already proven their effectiveness in medical technology and video analysis in a wide variety of applications. Furthermore, the specific use of hydroacoustics in this project requires the development of special acoustic transducers as well as novel algorithms for acoustic pattern recognition.
The project "UFO" is part of the joint project "Adaptation and further development of innovative, non-invasive, monitoring systems and evaluation methods for fisheries research (AutoMAt)", which is funded under the program for innovation promotion of the Federal Ministry of Food and Agriculture (BMEL). The aim of the joint project is to develop various pre-prototypes that will revolutionize conventional data collection and analysis in fisheries biology and ecology in the form of automated acquisition and analysis systems. Modern electronics and sensor technology are used together with innovative software solutions.
Results are only available on the German website