摘要
为了使手势交互较少受到视角和光线的限制,提出利用可穿戴传感器作为输入设备和机器学习算法相结合进行手势识别的方法。通过采集加速度仪和地磁仪的数据,然后进行预处理、特征提取和特征选择,最终由隐马尔科夫模型进行手势分类和识别。为验证方法的有效性,设计实现了一个原型系统进行识别和对比实验。实验结果表明,该方法可以实时有效地对手势特别是复杂的手势进行识别。
Motion sensing techniques are less limited in space and lighting from the point of view of human computer interaction.On-body wearable sensors are used to study on how to effectively build gesture recognition system with machine learning methods.Acceleration and magnetic data collected by accelerometer and magnetometer are then used by the hidden Markov model.Data processing steps contain preprocessing,feature selection and extraction.A prototype system is developed to verify the effectiveness of the approach.The results show that the approach can effectively recognize some gestures,especially complicated ones in real time.
出处
《传感技术学报》
CAS
CSCD
北大核心
2011年第12期1723-1727,共5页
Chinese Journal of Sensors and Actuators
基金
国家自然科学基金项目(61070043)
浙江省自然科学基金项目(Y1100611)
关键词
运动传感器
人机交互
手势识别
隐马尔科夫模型
motion sensors
human computer interaction
gesture recognition
Hidden Markov Model（HMM）
