Towards Non-invasive Fish Monitoring in Hard-to-Access Habitats Using Autonomous Underwater Vehicles and Machine Learning

Scientific monitoring is one of the key elements in the sustainable management of exploited fish populations. Traditional fisheries monitoring predominantly relies on international coordinated scientific large-scale bottom trawl surveys. Survey catches are used to obtain information on the target fish stocks’ structure (e.g., age and size distribution), recruitment strengths, and spatio-temporal distribution patterns. However, these bottom trawl surveys often have limited spatial coverage, considering hard-to-access areas.

This talk explores the use of autonomous underwater vehicles in combination with artificial intelligence to enable automatic habitat mapping and fish detection using sonar and camera data. The monitoring approach will help to fill important knowledge gaps on target fish spatio-temporal distribution in hard-to-access areas, give valuable insight into target fish behaviour, and help to identify the species’ essential habitats, which is relevant for the design of marine protected areas in fish management and conservation.

In der Regel sind die Vorträge Teil von Lehrveranstaltungsreihen der Universität Bremen und nicht frei zugänglich. Bei Interesse wird um Rücksprache mit dem Sekretariat unter sek-ric(at)dfki.de gebeten.

zuletzt geändert am 30.07.2019
nach oben