Personalized gesture interactions for cyber-physical smart-home environments

AbstractA gesture-based interaction system for smart homes is a part of a complex cyber-physical environment, for which researchers and developers need to address major challenges in providing personalized gesture interactions. However, current research efforts have not tackled the problem of personalized gesture recognition that often involves user identification. To address this problem, we propose in this work a new event-driven service-oriented framework called gesture services for cyber-physical environments (GS-CPE) that extends the architecture of our previous work gesture profile for web services (GPWS). To provide user identification functionality, GS-CPE introduces a two-phase cascading gesture password recognition algorithm for gesture-based user identification using a two-phase cascading classifier with the hidden Markov model and the Golden Section Search, which achieves an accuracy rate of 96.2% with a small training dataset. To support personalized gesture interaction, an enhanced version of the Dynamic Time Warping algorithm with multiple gestural input sources and dynamic template adaptation support is implemented. Our experimental results demonstrate the performance of the algorithm can achieve an average accuracy rate of 98.5% in practical scenarios. Comparison results reveal that GS-CPE has faster response time and higher accuracy rate than other gesture interaction systems designed for smart-home environments.创新点1. 论文设计了一个支持智能家庭环境中个性化手势交互的集成框架GS-CPE,该框架同时集成了用户身份识别与个性化手势识别,通过服务的形式提供了一组简单易用的API。 2. 论文提出了一种可用于用户身份识别的手势识别算法。通过结合基于统计模型的HMM分类器及基于模板匹配的GSS分类器,该算法可在训练数据集有限的条件下较大幅度地提高手势密码的识别准确率。 3. 论文提出了一种融合多数据源的个性化手势识别算法,通过对比来自不同数据源的手势识别结果来消除对拒绝似然比的依赖,并针对实际环境设计了手势模板动态调节方法,从而提高了该算法的识别准确率。