SubPipe: A Submarine Pipeline Inspection Dataset for Segmentation and Visual-inertial Localization

• Published in: OCEANS 2024 - Singapore pp. 1 - 7
• Main Authors: Alvarez-Tunon, Olaya, Marnet, Luiza Ribeiro, Aubard, Martin, Antal, Laszlo, Costa, Maria, Brodskiy, Yury
• Format: Conference Proceeding
• Language: English
• Published: IEEE 15.04.2024
• Subjects: Image segmentation; Inertial navigation; Location awareness; Object detection; Oceans; pipeline; Pipelines; RGB and grayscale camera; segmentation; side-scan sonar; Simultaneous localization and mapping; SLAM; underwater dataset
• DOI: 10.1109/OCEANS51537.2024.10682150

This paper presents SubPipe, an underwater dataset for SLAM, object detection, and image segmentation. SubPipe has been recorded using a lightweight autonomous underwater vehicle (LAUV), operated by OceanScan MST, and carrying a sensor suite including two cameras, a side-scan sonar, and an inertial navigation system, among other sensors. The AUV has been deployed in a pipeline inspection environment with a submarine pipe partially covered by sand. The AUV's pose ground truth is estimated from the navigation sensors. The side-scan sonar and RGB images include object detection and segmentation annotations, respectively. State-of-the-art segmentation, object detection, and SLAM methods are benchmarked on SubPipe to demonstrate the dataset's challenges and opportunities for leveraging computer vision algorithms. To the authors' knowledge, this is the first anno-tated underwater dataset providing a real pipeline inspection scenario. The dataset and experiments are publicly avail-able online at https://github.com/remaro-network/SubPipe-dataset.