Descriptor: Hydroacoustic and Optical Dataset for Oceanic Research (HODOR)

In this work, we introduce HODOR (<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">H</b>ydroacoustic and <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</b>ptical <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">D</b>ataset for <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</b>ceanic <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</b>esearch), a publicly accessible dataset developed for advanced analysis of marine life. It is one of the first datasets to provide synchronized sonar and optical stereo camera videos, comprising over 400 hours of continuous recordings per sensor. The purpose of HODOR is to support the development of machine learning and deep learning algorithms for marine applications, multimodal sensor fusion techniques, biomass quantification, and long-term ecological studies. The data was collected with a stationary underwater fish observatory (UFO) in the Kiel Fjord, an inlet of the Baltic Sea in northern Germany, and includes an 86-day subset of the recordings from 2021, which was selected based on automated detections using the YOLOv5 model.