Real-time Seafloor Segmentation and Mapping

2025-04-14

AI Summary

To address the global degradation of *Posidonia oceanica* seagrass meadows, this study proposes a real-time, AUV-centric framework for joint segmentation and georeferenced mapping of rocky–seagrass boundaries on the seafloor. To overcome challenges posed by underwater illumination non-uniformity and optical attenuation—leading to low semantic segmentation accuracy and unreliable autonomous inspection—we introduce, for the first time, rock-specific category enhancement into Mask R-CNN, coupled with adaptive underwater image preprocessing, AUV pose-integrated geospatial mapping, and boundary-following navigation strategies, thereby closing the segmentation–localization–annotation loop. The method achieves 78.3% mAP@0.5 on real underwater imagery; simulation validation confirms fully autonomous boundary tracking and georeferenced annotation capability. This work enables high-precision ecological assessment and evidence-based conservation decision-making for seagrass ecosystems.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Distributed Search

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Posidonia oceanica meadows are a species of seagrass highly dependent on rocks for their survival and conservation. In recent years, there has been a concerning global decline in this species, emphasizing the critical need for efficient monitoring and assessment tools. While deep learning-based semantic segmentation and visual automated monitoring systems have shown promise in a variety of applications, their performance in underwater environments remains challenging due to complex water conditions and limited datasets. This paper introduces a framework that combines machine learning and computer vision techniques to enable an autonomous underwater vehicle (AUV) to inspect the boundaries of Posidonia oceanica meadows autonomously. The framework incorporates an image segmentation module using an existing Mask R-CNN model and a strategy for Posidonia oceanica meadow boundary tracking. Furthermore, a new class dedicated to rocks is introduced to enhance the existing model, aiming to contribute to a comprehensive monitoring approach and provide a deeper understanding of the intricate interactions between the meadow and its surrounding environment. The image segmentation model is validated using real underwater images, while the overall inspection framework is evaluated in a realistic simulation environment, replicating actual monitoring scenarios with real underwater images. The results demonstrate that the proposed framework enables the AUV to autonomously accomplish the main tasks of underwater inspection and segmentation of rocks. Consequently, this work holds significant potential for the conservation and protection of marine environments, providing valuable insights into the status of Posidonia oceanica meadows and supporting targeted preservation efforts

Problem

• Autonomous monitoring of Posidonia oceanica meadows using AUVs
• Improving underwater image segmentation for complex marine conditions
• Enhancing conservation efforts by analyzing meadow-rock interactions

Innovation

• Uses Mask R-CNN for underwater image segmentation
• Introduces rock class to improve model accuracy
• Autonomous AUV framework for meadow boundary tracking