Sonar-to-RGB Image Translation for Diver Monitoring in Poor Visibility Environments

Context

This dataset is part of the paper "Sonar-to-RGB Image Translation for Diver Monitoring in Poor Visibility Environments" presented at Oceans 2022, Hampton Roads, DOI: 10.1109/OCEANS47191.2022.9977024

This dataset consists of paired camera and multi-beam sonar images of technical divers performing different underwater tasks in two locations: an indoor test basin and a lake. The general goal is to assist emergency operators that monitor the safety of divers operating in bad visibility conditions.

This data was used to train image-to-image translation models in order to generate realistic optical-like images given only sonar images as input or a combination of a sonar image and a dark or turbid optical image.

Content

This repository contains three .zip folders each containing data collected in a different lab or field trial.

• 'basin-dataset-1.zip' and 'basin-dataset-2.zip' contain data that were collected in an indoor testing facility at DFKI - Robotics Innovation Center, Bremen, Germany.
• 'lake-dataset-1.zip' and 'lake-dataset-2.zip' contains data collected at lake Kreidesee, Hemmoor, Germany.

Each .zip file contains two subfolders labelled as 'camera' and 'sonar', each containing the images in png format. Data files under these subfolders with matching names composes a pair of time-synchronized images. For example, 'camera/0001.png' corresponds to 'sonar/0001.png'. The acquisition timestamp represented in seconds since epoch for every data file is recorded in 'sample.csv' include in each .zip file.

For more details and meta-information on the collected data please refer to "data_description.json" included in this repository.

Additional tools for handling and preparing the data can be found under https://github.com/DeeperSense/oceans_2022

Acknowledgements

The data in this repository were collected as a joint effort between the German Center for Artificial Intelligence (DFKI), the German Federal Agency for technical Relief (THW), and Kraken Robotics GmbH. This work is part of the project DeeperSense that received funding from the European Commission. Program H2020-ICT-2020-2 ICT-47-2020 Project Number: 101016958.

The authors would like to thank the Federal Government and the Heads of Government of the Länder, as well as the Joint Science Conference (GWK), for their initiative within the framework of the NFDI4Ing consortium (German Research Foundation (DFG) - project number 442146713).