MoRSE: Deep Learning-based Arm Gesture Recognition for Search and Rescue Operations

TL;DR

This paper introduces a smartwatch-based deep learning system for recognizing arm gestures to enable Morse code communication in search and rescue, achieving over 95% accuracy and improving remote communication efficiency.

Contribution

The paper presents a novel deep learning model for arm gesture recognition using smartwatches, specifically designed for search and rescue operations, outperforming existing methods.

Findings

Gesture recognition accuracy exceeds 95%

Model outperforms existing DL and machine learning approaches

Effective for remote communication in disaster scenarios

Abstract

Efficient and quick remote communication in search and rescue operations can be life-saving for the first responders. However, while operating on the field means of communication based on text, image and audio are not suitable for several disaster scenarios. In this paper, we present a smartwatch-based application, which utilizes a Deep Learning (DL) model, to recognize a set of predefined arm gestures, maps them into Morse code via vibrations enabling remote communication amongst first responders. The model performance was evaluated by training it using 4,200 gestures performed by 7 subjects (cross-validation) wearing a smartwatch on their dominant arm. Our DL model relies on convolutional pooling and surpasses the performance of existing DL approaches and common machine learning classifiers, obtaining gesture recognition accuracy above 95%. We conclude by discussing the results and providing future directions.