AI 中文总结
针对深度学习手语识别成本高难部署边缘设备的问题，提出混合储备池计算模型，在WLASL100数据集上取得良好准确率且训练时间大幅缩短，具备边缘部署潜力。
AI 中文摘要
手语识别（SLR）可促进听力正常者与听障人士之间的交流。尽管深度学习（DL）在SLR领域已取得良好性能，但其高计算成本限制了在边缘设备上的部署。为应对这一挑战，本文提出一种基于储备池计算（RC）的轻量型SLR方法。该方法中，MediaPipe提取身体与手部关键点，以捕捉手势的时空动态；这些关键点随后由混合储备池计算（HRC）架构处理，该架构结合深度储备池计算（DRC）与双向储备池计算（BRC），将输入转换为高维动态表示；最后通过岭回归模型将HRC的最终状态映射到类别标签。在单词级美国手语100（WLASL100）视频数据集上，该基于HRC的SLR方法分别达到Top-1准确率61.12%、Top-5准确率86.05%、Top-10准确率92.56%，与基于深度学习的方法相比表现具有竞争力。此外，由于RC的轻量特性，其训练时间大幅缩短至仅数秒，相比基于深度学习的方法（如该方法），计算成本低，展现出在边缘设备部署的潜力。
英文摘要
Sign language recognition (SLR) enhances communication between hearing and hearing-impaired individuals. Although deep learning (DL) has achieved promising performance in SLR, its high computational cost limits deployment on edge devices. To address this challenge, we propose a lightweight reservoir computing (RC)-based approach for SLR. In the proposed method, MediaPipe extracts body and hand keypoints to capture the spatial and temporal dynamics of gestures. These keypoints are then processed by a hybrid reservoir computing (HRC) architecture that combines deep reservoir computing (DRC) and bidirectional reservoir computing (BRC), transforming the input into a high-dimensional dynamic representation. A ridge regression model maps the final HRC state to class labels. This HRC-based SLR method achieved Top-1, Top-5, and Top-10 accuracies of 61.12%, 86.05%, and 92.56%, respectively, on the Word-Level American Sign Language 100 (WLASL100) video dataset, demonstrating competitive performance compared to deep learning-based approaches. Additionally, due to the lightweight nature of RC, the training time was drastically reduced to only a few seconds compared with DL-based methods such as Bi-GRU.This method offers low computational cost, showing its potential for deployment on edge devices.
