Publication
An Acoustic and Optical Dataset for the Perception of Underwater Unexploded Ordnance (UXO)
Nikolas Dahn; Miguel Bande Firvida; Proneet Kumar Sharma; Leif Christensen; Oliver Geisler; Jochen Mohrmann; Torsten Frey; Prithvi Sanghamreddy; Frank Kirchner
In: OCEANS. OCEANS MTS/IEEE Conference (OCEANS-2024), September 23-26, Halifax, Kanada, Canada, IEEE, 9/2024.
Abstract
During the 20st century, millions of tons of munition were dumped into the oceans worldwide. After decades of decay, the problems these unexploded ordnance (UXO) are causing are starting to become apparent. In order to facilitate more efficient salvage efforts through e.g. autonomous underwater vehicles, access to representative data is paramount. However, so far such data is not publicly available. In this paper we present a dataset of multimodal synchronized data for acoustic and optical sensing of UXO underwater. Using an ARIS 3000 imaging sonar, a GoPro Hero 8 and a custom design gantry crane, we recorded close to 100 trajectories and over 74,000 frames of 3 distinct types of UXO in a controlled environment. Included in this dataset are raw and polar transformed sonar frames, annotated camera frames, sonar and target poses, textured 3D models, calibration matrices, and more. The dataset is publicly available at urlhttps://zenodo.org/records/11068046. The code for processing the raw data is available at urlhttps://github.com/dfki-ric/uxo-dataset2024.