One-Shot Gesture Recognition for Underwater Diver-To-Robot Communication

2025-03-02

AI Summary

To address the poor adaptability of acoustic-based schemes and weak generalization of predefined models in underwater human-robot gesture communication, this paper proposes a one-shot adaptive gesture recognition method tailored for autonomous underwater vehicles (AUVs). The method introduces, for the first time in underwater settings, a lightweight shape feature extraction pipeline integrating Hu moments, Zernike moments, and Fourier descriptors, combined with temporal modeling and an embedded-friendly lightweight classifier. It enables recognition of unseen gestures from a single demonstration—without requiring a predefined lexicon or large-scale training data. Evaluated on real underwater video datasets, the approach achieves high recognition accuracy while incurring significantly lower computational overhead than deep learning baselines. It has been successfully deployed in real time on resource-constrained AUV platforms, thereby overcoming key technical bottlenecks in robustness, adaptability, and edge deployability for underwater gesture interaction.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Humans and AI: Interaction Techniques and Devices
• Intelligent Robots: Human-Robot Interaction

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Reliable human-robot communication is essential for underwater human-robot interaction (U-HRI), yet traditional methods such as acoustic signaling and predefined gesture-based models suffer from limitations in adaptability and robustness. In this work, we propose One-Shot Gesture Recognition (OSG), a novel method that enables real-time, pose-based, temporal gesture recognition underwater from a single demonstration, eliminating the need for extensive dataset collection or model retraining. OSG leverages shape-based classification techniques, including Hu moments, Zernike moments, and Fourier descriptors, to robustly recognize gestures in visually-challenging underwater environments. Our system achieves high accuracy on real-world underwater data and operates efficiently on embedded hardware commonly found on autonomous underwater vehicles (AUVs), demonstrating its feasibility for deployment on-board robots. Compared to deep learning approaches, OSG is lightweight, computationally efficient, and highly adaptable, making it ideal for diver-to-robot communication. We evaluate OSG's performance on an augmented gesture dataset and real-world underwater video data, comparing its accuracy against deep learning methods. Our results show OSG's potential to enhance U-HRI by enabling the immediate deployment of user-defined gestures without the constraints of predefined gesture languages.

Problem

• Enables real-time gesture recognition underwater from a single demonstration.
• Overcomes limitations of traditional methods in adaptability and robustness.
• Provides lightweight, efficient solution for diver-to-robot communication.

Innovation

• One-Shot Gesture Recognition for underwater communication
• Shape-based classification techniques for robust recognition
• Lightweight and efficient for embedded AUV hardware