用可穿戴传感器实现实时动作识别，让机器与舞者协同演出。
Human-Machine Ritual: Synergic Performance through Real-Time Motion Recognition
- 通过可穿戴传感器和时间序列分类算法实时识别动作
- 动作识别延迟低于50毫秒，准确率高且可复现
- 适合舞蹈创作、教育及现场表演场景
我们提出一种轻量级、实时的动作识别系统，利用可穿戴惯性测量单元（IMU）传感器数据，结合MiniRocket时间序列分类方法与响应式多媒体控制，实现人机协同表演。通过将舞者特定动作与声音通过身体记忆和联想映射，构建了一种以人为本的人机协作新范式，在保留表演主体表达深度的同时，借助机器学习实现敏锐感知与响应。实验表明，该设计在低延迟（<50毫秒）下保持高精度分类，提供可复制的框架，支持将具备舞蹈理解能力的机器融入创意、教育及现场表演场景。
原文摘要 · Abstract (English)
We introduce a lightweight, real-time motion recognition system that enables synergic human-machine performance through wearable IMU sensor data, MiniRocket time-series classification, and responsive multimedia control. By mapping dancer-specific movement to sound through somatic memory and association, we propose an alternative approach to human-machine collaboration, one that preserves the expressive depth of the performing body while leveraging machine learning for attentive observation and responsiveness. We demonstrate that this human-centered design reliably supports high accuracy classification (<50 ms latency), offering a replicable framework to integrate dance-literate machines into creative, educational, and live performance contexts.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。