EREBUS: End-to-end Robust Event Based Underwater Simulation

TL;DR

This paper introduces EREBUS, a pipeline for generating realistic synthetic event-based camera data in underwater environments to improve vision model training under challenging conditions.

Contribution

The paper presents a novel end-to-end pipeline for creating synthetic event-based underwater data, aiding robust vision model development for AUVs.

Findings

Effective rock detection in poor visibility conditions

Synthetic data improves model robustness in underwater scenarios

Pipeline generalizes to various underwater tasks

Abstract

The underwater domain presents a vast array of challenges for roboticists and computer vision researchers alike, such as poor lighting conditions and high dynamic range scenes. In these adverse conditions, traditional vision techniques struggle to adapt and lead to suboptimal performance. Event-based cameras present an attractive solution to this problem, mitigating the issues of traditional cameras by tracking changes in the footage on a frame-by-frame basis. In this paper, we introduce a pipeline which can be used to generate realistic synthetic data of an event-based camera mounted to an AUV (Autonomous Underwater Vehicle) in an underwater environment for training vision models. We demonstrate the effectiveness of our pipeline using the task of rock detection with poor visibility and suspended particulate matter, but the approach can be generalized to other underwater tasks.