CaveSeg: Deep Semantic Segmentation and Scene Parsing for Autonomous Underwater Cave Exploration

TL;DR

CaveSeg introduces a novel deep learning pipeline with a new dataset for semantic segmentation of underwater caves, enabling autonomous AUV navigation with near real-time scene parsing and state-of-the-art accuracy.

Contribution

The paper presents the first visual learning pipeline and comprehensive dataset for underwater cave scene parsing, including a lightweight transformer model for real-time AUV navigation.

Findings

Robust deep models can be trained for underwater cave scene parsing.

The transformer-based model achieves near real-time performance.

Benchmark results demonstrate state-of-the-art accuracy.

Abstract

In this paper, we present CaveSeg - the first visual learning pipeline for semantic segmentation and scene parsing for AUV navigation inside underwater caves. We address the problem of scarce annotated training data by preparing a comprehensive dataset for semantic segmentation of underwater cave scenes. It contains pixel annotations for important navigation markers (e.g. caveline, arrows), obstacles (e.g. ground plane and overhead layers), scuba divers, and open areas for servoing. Through comprehensive benchmark analyses on cave systems in USA, Mexico, and Spain locations, we demonstrate that robust deep visual models can be developed based on CaveSeg for fast semantic scene parsing of underwater cave environments. In particular, we formulate a novel transformer-based model that is computationally light and offers near real-time execution in addition to achieving state-of-the-art performance. Finally, we explore the design choices and implications of semantic segmentation for visual servoing by AUVs inside underwater caves. The proposed model and benchmark dataset open up promising opportunities for future research in autonomous underwater cave exploration and mapping.