British Sign Language Detection Using Ultra-Wideband Radar Sensing and Residual Neural Network
British Sign Language Detection Using Ultra-Wideband Radar Sensing and Residual Neural Network
复制标题
DOI：
10.1109/jsen.2024.3364389
复制
发表时间：
2024-04-01
影响因子：
4.3
通讯作者：
Abbasi，Qammer H.
中科院分区：
文献类型：
--
作者：
Saeed，Umer;Shah，Syed Aziz;Abbasi，Qammer H.
这项研究代表了手语检测（SLD）方面的重大进步，手语检测是加强听力障碍社区沟通和促进包容性的重要工具。它创新地将雷达技术与深度学习技术相结合，开发出复杂的非侵入性 SLD 系统。传统的 SLD 方法通常依赖于笨重的可穿戴设备，或者面临环境不一致的问题。相比之下，该系统利用雷达的独特能力在各种照明条件下有效运行。这项研究的核心在于其在英国手语（BSL）检测中的应用，使用先进的神经网络架构进行实时解释。一个关键亮点是使用残差神经网络 (ResNet) 模型在 BSL 识别中实现了令人印象深刻的 92% 准确率。这一成功归功于全面的数据集以及 ResNet 用于处理雷达数据的战略调整。在这种背景下，雷达技术与深度学习的融合不仅标志着该领域的一种新颖方法，而且使这项研究成为对 SLD 领域的基础性贡献。它的影响超越了技术成就，为听力障碍者提供了一种更方便、更具包容性的沟通替代方案。
This study represents a significant advancement in sign language detection (SLD), a crucial tool for enhancing communication and fostering inclusivity among the hearing-impaired community. It innovatively combines radar technology with deep learning techniques to develop a sophisticated, noninvasive SLD system. Traditional SLD methods often rely on cumbersome wearable devices or struggle with environmental inconsistencies. In contrast, this system uses the distinctive ability of radar to function effectively across various lighting conditions. The core of this research lies in its application to British Sign Language (BSL) detection, using advanced neural network architectures for real-time interpretation. A key highlight is the impressive 92% accuracy rate achieved in BSL recognition, using the residual neural network (ResNet) model. This success is attributed to a comprehensive dataset and the strategic adaptation of ResNet for processing radar data. The fusion of radar technology with deep learning in this context not only marks a novel approach in the field but also establishes this research as a foundational contribution to the realm of SLD. Its implications extend beyond technical achievement, offering a more accessible and inclusive communication alternative for the hearing-impaired.