Benchmarking Online Object Trackers for Underwater Robot Position Locking Applications

TL;DR

This paper presents a comprehensive benchmarking of machine learning-based object trackers for underwater ROV position locking, addressing challenges like lighting, turbidity, and currents, and providing a new open dataset for future research.

Contribution

It introduces the first unified benchmark of multiple ML-based object tracking algorithms for underwater ROV position control and releases an open dataset to support further research.

Findings

Different trackers show varied strengths and weaknesses in underwater conditions.

The proposed system effectively uses tracking outputs to correct ROV position.

Open-source dataset aids future underwater robotics research.

Abstract

Autonomously controlling the position of Remotely Operated underwater Vehicles (ROVs) is of crucial importance for a wide range of underwater engineering applications, such as in the inspection and maintenance of underwater industrial structures. Consequently, studying vision-based underwater robot navigation and control has recently gained increasing attention to counter the numerous challenges faced in underwater conditions, such as lighting variability, turbidity, camera image distortions (due to bubbles), and ROV positional disturbances (due to underwater currents). In this paper, we propose (to the best of our knowledge) a first rigorous unified benchmarking of more than seven Machine Learning (ML)-based one-shot object tracking algorithms for vision-based position locking of ROV platforms. We propose a position-locking system that processes images of an object of interest in front of which the ROV must be kept stable. Then, our proposed system uses the output result of different object tracking algorithms to automatically correct the position of the ROV against external disturbances. We conducted numerous real-world experiments using a BlueROV2 platform within an indoor pool and provided clear demonstrations of the strengths and weaknesses of each tracking approach. Finally, to help alleviate the scarcity of underwater ROV data, we release our acquired data base as open-source with the hope of benefiting future research.