MIMIR-UW: A Multipurpose Synthetic Dataset for Underwater Navigation and Inspection

TY - GEN

T1 - MIMIR-UW

T2 - 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

AU - Alvarez Tunon, Olaya

AU - Kanner, Hemanth

AU - Ribeiro Marnet, Luiza

AU - Pham, Xuan Huy

AU - Sejersen, Jonas le Fevre

AU - Brodskiy, Yury

AU - Kayacan, Erdal

PY - 2023/10

Y1 - 2023/10

N2 - This paper presents MIMIR-UW, a multipurpose underwater synthetic dataset for SLAM, depth estimation, and object segmentation to bridge the gap between theory and application in underwater environments. MIMIR-UW integrates three camera sensors, inertial measurements, and ground truth for robot pose, image depth, and object segmentation. The underwater robot is deployed within a pipe exploration scenario, carrying artificial lights that create uneven lighting, in addition to natural artefacts such as reflections from natural light and backscattering effects. Four environments totalling eleven tracks are provided, with various difficulties regarding light conditions or dynamic elements. Two metrics for dataset evaluation are proposed, allowing MIMIR-UW to be compared with other datasets. State-of-art methods on SLAM, segmentation and depth estimation are deployed and benchmarked on MIMIR-UW. Moreover, the dataset's potential for sim-to-real transfer is demonstrated by leveraging the segmentation and depth estimation models trained on MIMIR-UW in a real pipeline inspection scenario. To the best of the authors' knowledge, this is the first underwater dataset targeted for such a variety of methods. The dataset is publicly available online. https://github.com/remaro-network/MIMIR-UW/

AB - This paper presents MIMIR-UW, a multipurpose underwater synthetic dataset for SLAM, depth estimation, and object segmentation to bridge the gap between theory and application in underwater environments. MIMIR-UW integrates three camera sensors, inertial measurements, and ground truth for robot pose, image depth, and object segmentation. The underwater robot is deployed within a pipe exploration scenario, carrying artificial lights that create uneven lighting, in addition to natural artefacts such as reflections from natural light and backscattering effects. Four environments totalling eleven tracks are provided, with various difficulties regarding light conditions or dynamic elements. Two metrics for dataset evaluation are proposed, allowing MIMIR-UW to be compared with other datasets. State-of-art methods on SLAM, segmentation and depth estimation are deployed and benchmarked on MIMIR-UW. Moreover, the dataset's potential for sim-to-real transfer is demonstrated by leveraging the segmentation and depth estimation models trained on MIMIR-UW in a real pipeline inspection scenario. To the best of the authors' knowledge, this is the first underwater dataset targeted for such a variety of methods. The dataset is publicly available online. https://github.com/remaro-network/MIMIR-UW/

KW - Measurement

KW - Simultaneous localization and mapping

KW - robot vision systems

KW - pipelines

KW - estimation

KW - object segmentation

KW - inspection

UR - http://www.scopus.com/inward/record.url?scp=85174993207&partnerID=8YFLogxK

U2 - 10.1109/IROS55552.2023.10341436

DO - 10.1109/IROS55552.2023.10341436

M3 - Article in proceedings

SN - 978-1-6654-9191-4

T3 - IEEE International Conference on Intelligent Robots and Systems

SP - 6141

EP - 6148

BT - 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

PB - IEEE

Y2 - 1 October 2023

ER -