A Visual Perception Algorithm for Human Motion by a Kinect
ZHU Tehao1, ZHAO Qunfei1, XIA Zeyang2
1. Department of Automation, Shanghai Jiaotong University, Shanghai 200240, China;
2. Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China
A visual perception algorithm of human motion for humanoid robot is proposed to improve the precision of the motion data captured from a Kinect. Firstly, the positions of the joints are transformed into the angles according to the inverse kinematics equations. Secondly, the long-time motion is segmented into episodes automatically based on the change of the angular velocity and acceleration, and then RVM (relevant vector machine) is utilized for estimating the angle trajectories with high accuracy. Finally, the spatial consistence, temporal consistence and smoothness of the angle trajectories are given to evaluate the algorithm, and a motion data series processed by the algorithm is implemented on a NAO robot platform. The experimental results indicate that the proposed algorithm effectively improves the spatial and temporal consistence of the motion perception and the smoothness of the trajectory, which provides a foundation for high-precision motion imitation.
[1] Microsoft. Develop for Kinect[EB/OL]. [2013-12-05]. http://www.microsoft.com/zh-cn/kinectforwindows/.[2] ASUSTeK Computer Inc. 多媒体产品——Xtion PRO[EB/OL]. [2013-10-24]. http://www.asus.com.cn/Multimedia/Xtion_PRO/.[3] Do M, Azad P, Asfour T, et al. Imitation of human motion on a humanoid robot using non-linear optimization[C]//2008 8th IEEE-RAS International Conference on Humanoid Robots. Piscataway, USA: IEEE, 2008: 545-552.[4] Wang F, Tang C, Ou Y S, et al. A real-time human imitation system[C]//2012 10th World Congress on Intelligent Control and Automation. Piscataway, USA: IEEE, 2012: 3692-3697.[5] Rosado J, Silva F, Santos V. A Kinect-based motion capture system for robotic gesture imitation[C]//ROBOT2013: First Iberian Robotics Conference. Berlin, Germany: Springer, 2014: 585-595.[6] Thobbi A, Sheng W H. Imitation learning of arm gestures in presence of missing data for humanoid robots[C]//2010 10th IEEE-RAS International Conference on Humanoid Robots. Piscataway, USA: IEEE, 2010: 92-97.[7] 李少波,赵毅夫,赵群飞,等.机器人的人体姿态动作识别与模仿算法[J].计算机工程,2013,39(8):181-186.Li S B, Zhao Y F, Zhao Q F, et al. Algorithm of human posture action recognition and imitation for robots[J]. Computer Engineering, 2013, 39(8): 181-186.[8] ALDEBARAN ROBOTICS. More about[EB/OL]. [2014-03-11]. http://www.aldebaran.com/en/more-about.[9] 赵姝颖,徐文杰,郑雪林,等.基于体感的机器人展示系统研究与开发[J].机器人技术与应用,2013(6):54-57.Zhao S Y, Xu W J, Zheng X L, et al. Research and development of display system of NAO humanoid robot based on posture perception[J]. Robot Techniques and Application, 2013(6): 54-57.[10] 张力格,黄强,杨洁,等.仿人机器人复杂动态动作设计及相似性研究[J].自动化学报,2007,33(5):522-528.Zhang L G, Huang Q, Yang J, et al. Design of humanoid complicated dynamic motion with similarity considered[J]. Acta Automatica Sinica, 2007, 33(5): 522-528.[11] Tipping M E. Sparse Bayesian learning and the relevance vector machine[J]. Journal of Machine Learning Research, 2001, 1(3): 211-244.[12] Bishop C M. Pattern recognition and machine learning[M]. New York, USA: Springer, 2006: 345-349.[13] Vicon Motion Systems Ltd. Vicon Systems T-Series[EB/OL]. [2013-11-15]. http://www.vicon.com/System/TSeries.