Advancements in information technology have increased demand for natural human-computer interaction in areas such as gaming, smart homes, and vehicles. However, conventional approaches like physical buttons or cameras are often limited by contact requirements, privacy concerns, and high costs.Motivated by the observation that these EM signals are not only strong and measurable but also rich in gesture-related information, we propose EMGesture, a novel contactless interaction technique that leverages the electromagnetic (EM) signals from Qi wireless chargers for gesture recognition. EMGesture analyzes the distinctive EM features and employs a robust classification model. The end-to-end framework enables it capable of accurately interpreting user intent. Experiments involving 30 participants, 10 mobile devices, and 5 chargers showed that EMGesture achieves over 97% recognition accuracy. Corresponding user studies also confirmed higher usability and convenience, which demonstrating that EMGesture is a practical, privacy-conscious, and cost-effective solution for pervasive interaction.

翻译：信息技术的进步增加了游戏、智能家居和车辆等领域对自然人机交互的需求。然而，传统方法如物理按钮或摄像头通常受限于接触要求、隐私问题和高成本。受电磁信号不仅强度高、可测量且富含手势相关信息的启发，我们提出了EMGesture，一种新颖的非接触式交互技术，利用Qi无线充电器的电磁信号进行手势识别。EMGesture通过分析独特的电磁特征并采用鲁棒的分类模型，其端到端框架能够准确解读用户意图。涉及30名参与者、10台移动设备和5个充电器的实验表明，EMGesture实现了超过97%的识别准确率。相应的用户研究也证实了更高的可用性和便利性，这表明EMGesture是一种实用、注重隐私且经济高效的普适交互解决方案。