面向人机交互的快速人体动作识别系统
|
摘要
针对在Kinect平台利用人体动作进行人机交互的时效性问题,提出了一种基于时间序列相似性的快速人体动作识别方法。通过Kinect获取人体全身20个关节点,提取关键点的空间三维坐标,转化成特征向量,该特征向量模型能很好地对全身动作进行表示;在动作识别方面提出了一种快速动态时间弯曲距离(Fast Dynamic TimeWarping,F-DTW)算法,解决了因动作速度不同导致的两时间序列在时间轴上不一致的问题,通过引入下界函数和提前终止技术对算法进行加速优化,解决动作识别的时延问题,从而能快速地控制机器人;定义20种动作进行识别,平均识别速度较传统算法大大提高,验证了方法的有效性,满足与机器人交互的要求。
Aiming at the problem of timeliness in human-computer interaction using human action based on Kinect, a rapid human action recognition method based on time series similarity is proposed. Three-dimensional coordinates of the key points extracted from 20 joints of human body obtained from the Kinect sensor are transformed into eigenvector and the eigenvector model is a superb action descriptor. A Fast Dynamic Time Warping(F-DTW)algorithm is proposed to solve the speed problem of action recognition. Lower bound function and early termination technique is used to solve the timelag problem so as to control the robot quickly. 20 kinds of actions are defined for recognition, the average recognition rate is greatly improved than traditional algorithm, verifying the validity of the method and meeting the requirements of the interaction with robot.
Aiming at the problem of timeliness in human-computer interaction using human action based on Kinect, a rapid human action recognition method based on time series similarity is proposed. Three-dimensional coordinates of the key points extracted from 20 joints of human body obtained from the Kinect sensor are transformed into eigenvector and the eigenvector model is a superb action descriptor. A Fast Dynamic Time Warping(F-DTW)algorithm is proposed to solve the speed problem of action recognition. Lower bound function and early termination technique is used to solve the timelag problem so as to control the robot quickly. 20 kinds of actions are defined for recognition, the average recognition rate is greatly improved than traditional algorithm, verifying the validity of the method and meeting the requirements of the interaction with robot.
引文
[1]董士海.人机交互的进展及面临的挑战[J].计算机辅助设计与图形学学报,2004,16(1):1-10.
[2]倪晨,邱鹏,王锋.Kinect体感技术在人机交互中的应用研究[J].信息技术与信息化,2013,1(1):87-90.
[3]吕蕾,张金玲,朱英杰.一种基于数据手套的静态手势识别方法[J].计算机辅助设计与图形学学报,2015,27(12):2412-2415.
[4]李文生,解梅,邓春健.基于机器视觉的动态多点手势识别方法[J].计算机工程与设计,2012,33(5):1988-1992.
[5]孙锦红,刘卫东,马亮.基于机器视觉的3D人体动作识别研究[J].计算机与现代化,2011,23(11):86-89.
[6]孟明,杨方波,佘青山.基于Kinect深度图像信息的人体运动检测[J].仪器仪表学报,2015,36(2):387-391.
[7]秦超龙,宋爱国.基于Unity3D与Kinect的康复训练机器人情景交互系统[J].仪器仪表学报,2017,38(3):530-536.
[8]Seddik B,Gazzah S,Amara N E B.Human-action recognition using a multi-layered fusion scheme of Kinect modalities[J].IEEE IET Computer Vision,2017,11(7):530-540.
[9]谢亮,廖宏建,杨玉宝.基于Kinect的姿势识别与应用研究[J].计算机技术与发展,2013,23(5):259-260.
[10]Raheja J L,Minhas M.Robust gesture recognition using Kinect:a comparison between DTW and HMM[J].OptikInternational Journal for Light and Electron Optics,2015,126(11/12):1098-1104.
[11]Yavsan E,Ucar A.Gesture imitation and recognition using Kinect sensor and extreme learning machines[J].Measurement,2016,94(9):852-861.
[12]余涛.Kinect应用开发实战[M].北京:机械工业出版社,2013:28-37.
[13]Troncoso A,Arias M.A multi-scale smoothing kernel for measuring time-series similarity[J].Neurocomputing,2015,167(11):8-17.
[14]Ibanez R,Alvaro S,Teyseyre A,et al.Easy gesture recognition for Kinect[J].Advances in Engineering Software,2014,76(10):171-180.
[15]Ding I J,Chang Y J.HMM with improved feature extractionbased feature parameters for identity recognition of gesture command operators by using a sensed Kinect-data stream[J].Neurocomputing,2017,262(11):108-119.
[2]倪晨,邱鹏,王锋.Kinect体感技术在人机交互中的应用研究[J].信息技术与信息化,2013,1(1):87-90.
[3]吕蕾,张金玲,朱英杰.一种基于数据手套的静态手势识别方法[J].计算机辅助设计与图形学学报,2015,27(12):2412-2415.
[4]李文生,解梅,邓春健.基于机器视觉的动态多点手势识别方法[J].计算机工程与设计,2012,33(5):1988-1992.
[5]孙锦红,刘卫东,马亮.基于机器视觉的3D人体动作识别研究[J].计算机与现代化,2011,23(11):86-89.
[6]孟明,杨方波,佘青山.基于Kinect深度图像信息的人体运动检测[J].仪器仪表学报,2015,36(2):387-391.
[7]秦超龙,宋爱国.基于Unity3D与Kinect的康复训练机器人情景交互系统[J].仪器仪表学报,2017,38(3):530-536.
[8]Seddik B,Gazzah S,Amara N E B.Human-action recognition using a multi-layered fusion scheme of Kinect modalities[J].IEEE IET Computer Vision,2017,11(7):530-540.
[9]谢亮,廖宏建,杨玉宝.基于Kinect的姿势识别与应用研究[J].计算机技术与发展,2013,23(5):259-260.
[10]Raheja J L,Minhas M.Robust gesture recognition using Kinect:a comparison between DTW and HMM[J].OptikInternational Journal for Light and Electron Optics,2015,126(11/12):1098-1104.
[11]Yavsan E,Ucar A.Gesture imitation and recognition using Kinect sensor and extreme learning machines[J].Measurement,2016,94(9):852-861.
[12]余涛.Kinect应用开发实战[M].北京:机械工业出版社,2013:28-37.
[13]Troncoso A,Arias M.A multi-scale smoothing kernel for measuring time-series similarity[J].Neurocomputing,2015,167(11):8-17.
[14]Ibanez R,Alvaro S,Teyseyre A,et al.Easy gesture recognition for Kinect[J].Advances in Engineering Software,2014,76(10):171-180.
[15]Ding I J,Chang Y J.HMM with improved feature extractionbased feature parameters for identity recognition of gesture command operators by using a sensed Kinect-data stream[J].Neurocomputing,2017,262(11):108-119.