基于DBN模型与Kinect数据的高尔夫挥杆重建

doi:10.7523/j.issn.2095-6134.2016.02.009

中国科学院大学学报 ›› 2016, Vol. 33 ›› Issue (2): 204-212.DOI: 10.7523/j.issn.2095-6134.2016.02.009

基于DBN模型与Kinect数据的高尔夫挥杆重建

吕东岳¹, 黄志蓓², 陶冠宏², 俞能海¹, 吴健康²

1. 中国科学院电子学研究所, 北京 100190;
2. 中国科学院大学, 北京 100049

收稿日期:2014-11-20 修回日期:2015-06-12 发布日期:2016-03-15
通讯作者: 黄志蓓
基金资助:
Supported by National Natural Science Foundation of China (61431017)

DBN model-based golf swing reconstruction using Kinect data

LV Dongyue¹, HUANG Zhipei², TAO Guanhong², YU Nenghai¹, WU Jiankang²

1. Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2014-11-20 Revised:2015-06-12 Published:2016-03-15
Supported by:
Supported by National Natural Science Foundation of China (61431017)

摘要/Abstract

摘要：

人们对高尔夫运动的兴趣在过去的10年间爆发式增长,同时高尔夫球员的数量也显著增加.因此,如何训练一个球员做出适当和准确的挥杆动作已经引起研究者的广泛关注.在此类研究中最重要的步骤是挥杆动作的捕获与重建.至今为止,以Kinect为代表的深度成像设备受其基础条件的限制,其捕获的挥杆运动可能会由于运动中肢体之间的互相遮挡与肢体识别时产生的混乱丧失足够的精确度.为了从肢体互相遮挡并且分辨率较低的深度图像信息中恢复比较精确的运动信息,该文提出一个用于描述人体关节点之间空间关系与关节点动态特性的动态贝叶斯网络(DBN)模型,并基于该模型实现了高尔夫挥杆动作的重建.实验结果表明,该算法能够实现重建精度媲美商用的光学运动捕获系统(OMocap),并且比现有的深度信息修改算法具有更好的性能.

关键词: 高尔夫挥杆重建, 动态贝叶斯网络模型, Kinect

Abstract:

The last decade has witnessed an explosion of interest in golf, and the number of golf players has increased significantly. Therefore, how to train a golfer to make a proper and accurate golf swing has attracted extensive research attentions. Among these researches the most important step is swing capture and reconstruction. Thus far, restricted to the development of present depth imaging devices, of which the most famous one is Kinect, the initial captured swing movement may not be acceptable enough due to occlusions and mixing up of body parts. To restore motion information from self-occlusion and reconstruct 3D golf swing from low resolution depth data, a dynamic Bayesian network (DBN) model based golf swing reconstruction algorithm is proposed to increase the capture accuracy which integrates the spatial relationship among joints and their movement dynamics. Experimental results have proved that the proposed algorithm can achieve comparable reconstruction accuracy to the commercial optical motion caption (OMocap) system and better performance than state of art modification algorithms using depth information.

Key words: golf swing reconstruction, dynamic Bayesian network model, Kinect

中图分类号:

TP391

吕东岳, 黄志蓓, 陶冠宏, 俞能海, 吴健康. 基于DBN模型与Kinect数据的高尔夫挥杆重建[J]. 中国科学院大学学报, 2016, 33(2): 204-212.

LV Dongyue, HUANG Zhipei, TAO Guanhong, YU Nenghai, WU Jiankang. DBN model-based golf swing reconstruction using Kinect data[J]. , 2016, 33(2): 204-212.

参考文献

[1] Mann R, Griffin F, Yocom G. Swing like a pro: the breakthrough scientific method of perfecting your golf swing[M].Random House Digital, Inc.,1998:
[2] Urtasun R, Fleet D J, Fua P. Monocular 3D tracking of the golf swing[C]//Computer Vision and Pattern Recognition 2005. IEEE Computer Society Conference on. IEEE,2005:932-938.
[3] Karliga I, Hwang J N. Analyzing human body 3-d motion of golf swing from single-camera video sequences[C]//Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on:Toulouse IEEE,2006:V-V.
[4] MacKenzie S J. Club position relative to the golfer's swing plane meaningfully affects swing dynamics[J]. Sports Biomechanics, 2012, 11(2):149-164.
[5] Coleman S, Anderson D. An examination of the planar nature of golf club motion in the swings of experienced players[J].Journal of Sports Sciences,2007,25(7):739-748.
[6] Kwon Y H. Kinematic analysis of sports movements: golf swing plane analysis[C]//ISBS-Conference Proceedings Archive: Limerick: 2009: 31-34.
[7] Nesbit S M, McGinnis R. Kinematic analyses of the golf swing hub path and its role in golfer/club kinetic transfers[J]. Journal of Sports Science and Medicine, 2009, 8(2): 235-246.
[8] Kenny I, Madden D, Downey J, et al. Biomechanical characterisation of leg movement during the golf swing following knee surgery[C]//2012 British Association of Sport and Exercise Sciences Biomechanics Interest Group Conference.2012.
[9] Chun S, Kang D, Choi H-R, et al. A sensor-aided self coaching model for uncocking improvement in golf swing[J]. Multimedia Tools and Applications, 2014, 72(1): 253-279.
[10] Suzuki S, Haake S, Heller B. Skill analysis of the wrist release in golf swing to utilize shaft elasticity[C]//Proceedings of APCST2005-Asia-Pacific congress on sports technology. 2005: 188-193.
[11] Zhou H, Hu H. Human motion tracking for rehabilitation: A survey[J].Biomedical Signal Processing and Control, 2008, 3(1): 1-18.
[12] Holte M B, Chakraborty B, Gonzalez J, et al. A local 3-D motion descriptor for multi-view human action recognition from 4-D spatio-temporal interest points[J]. Selected Topics in Signal Processing, IEEE Journal of, 2012, 6(5): 553-565.
[13] MacKenzie S J, Sprigings E J. A three-dimensional forward dynamics model of the golf swing[J]. Sports Engineering, 2009, 11(4): 165-175.
[14] Wu Q, Boulanger P. Real-time estimation of missing markers for reconstruction of human motion[C]//Virtual Reality (SVR), 2011 XIII Symposium on. Uberlandia: IEEE, 2011:161-168.
[15] Nesbit S M. A three dimensional kinematic and kinetic study of the golf swing[J]. Journal of Sports Science and Medicine, 2005, 4(4): 499-519.
[16] Watanabe K, Hokari M. Kinematical analysis and measurement of sports form[J]. Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on, 2006, 36(3): 549-557.
[17] Arvind D, Bates A. The speckled golfer[C]//Proceedings of the ICST 3rd international conference on Body area networks: Tempe, Arizona, USA. 2008: 1-7.
[18] Liu H, Wei X, Chai J, et al. Realtime human motion control with a small number of inertial sensors[C]//Symposium on Interactive 3D Graphics and Games: ACM. 2011: 133-140.
[19] Seaman A, McPhee J. Comparison of optical and inertial tracking of full golf swings[J]. Procedia Engineering, 2012, 34: 461-466.
[20] Evans K, Horan S A, Neal R J, et al. Repeatability of three-dimensional thorax and pelvis kinematics in the golf swing measured using a field-based motion capture system[J]. Sports Biomechanics, 2012, 11(2): 262-272.
[21] Smisek J, Jancosek M, Pajdla T. 3D with Kinect[C]//Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on Barcelona IEEE.2011: 1 154-1 160.
[22] Shum H P, Ho E S, Jiang Y, et al. Real-time posture reconstruction for Microsoft Kinect[J]. Cybernetics, IEEE Transactions on, 2013, 43(5): 1 357-1 369.
[23] Zhang L, Hsieh J-C, Ting T-T, et al. A Kinect based golf swing score and grade system using GMM and SVM[C]//Image and Signal Processing (CISP), 2012 5th International Congress on. Chongqing: IEEE, 2012: 711-715.
[24] Zhang L, Hsieh J C, Wang J. A Kinect-based golf swing classification system using HMM and Neuro-Fuzzy //Computer Science and Information Processing (CSIP), 2012 International Conference on. Xi'an: IEEE, 2012: 1 163-1 166.
[25] Lin Y-H, Huang S-Y, Hsiao K-F, et al. A Kinect-based system for golf beginners' training[M]. Springer, 2013: 121-129.
[26] Shen W, Deng K, Bai X, et al. Exemplar-based human action pose correction and tagging[C]//Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. Providence, USA: IEEE, 2012: 1784-1791.
[27] MAT-T Website[DB/OL].[2014-11-23]. http://tmpl.taylormadegolf.com/mat-t-system.
[28] Introducing OpenNI[M/OL]. (2013-12-12).[2014-10-30] http://www.openni.org/images/stories/pdf/OpenNI_UserGuide.pdf.
[29] McGuan S P. Achieving commercial success with biomechanics simulation[C]//20 International Symposium on Biomechanics in Sports. Cáceres, Spain: 2002: 451- 460.

基于DBN模型与Kinect数据的高尔夫挥杆重建

DBN model-based golf swing reconstruction using Kinect data

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

访问统计

联系我们

[1]	杨雨龙, 郭田德, 韩丛英. 基于原型学习改进的伪标签半监督学习算法[J]. 中国科学院大学学报, 2021, 38(6): 841-851.
[2]	史达亨, 刘立刚, 周斌, 卜智勇. 跨时间迁移的多源无线信号指纹融合定位方法[J]. 中国科学院大学学报, 2021, 38(6): 817-824.
[3]	庄子俊, 袁晓兵, 裴俊, 王国辉, 刘建坡. 基于无监督表达学习的森林地貌特征建模及林火易发性评估[J]. 中国科学院大学学报, 0, (): 1-1.
[4]	陈汉钦, 秦进, 赵彤, 阎瑶. 面向识别的人脸三维信息估计^*[J]. 中国科学院大学学报, 0, (): 2-2.
[5]	赵敏钧, 赵亚伟, 赵雅捷, 罗刚. 一种新的基于深度学习的重叠关系联合抽取模型[J]. 中国科学院大学学报, 0, (): 55-55.
[6]	马曌月, 肖俊, 王颖. 基于面提取的三维岩体点云孔洞检测与修复方法^*[J]. 中国科学院大学学报, 0, (): 64-64.
[7]	林大权, 范睿, 张良峰. 基于高维特征的图像对抗攻击算法^*[J]. 中国科学院大学学报, 0, (): 74-74.
[8]	王贺, 卜智勇, 谭冲. 基于核相关滤波视觉检测的多旋翼无人机对地目标跟踪与逼近[J]. 中国科学院大学学报, 0, (): 21532-21532.
[9]	赵心驰, 姜策, 何为. 基于注意力生成对抗网络的图像强光去除[J]. 中国科学院大学学报, 0, (): 21548-21548.
[10]	马莹莹, 吴幼龙, 唐华. 基于特征编码和图嵌入的姓名消歧方法[J]. 中国科学院大学学报, 0, (): 21549-21549.
[11]	张韬, 肖俊, 王颖. 基于匹配点逐层过滤的岩体点云配准方法[J]. 中国科学院大学学报, 0, (): 21550-21550.
[12]	杨善强, 李华旺, 常亮, 高才栋, 虞业泺. 一种基于RPC的组态化卫星模拟器故障注入方法[J]. 中国科学院大学学报, 2021, 38(3): 402-408.
[13]	盛晓光, 王颖, 张迎伟, 项若曦, 付红萍. WILS：面向学业预警的非均衡增量式学习方法*[J]. 中国科学院大学学报, 0, (): 17-18.
[14]	周龙, 王伟强, 吕科. FACR：一种快速且准确的车辆识别器[J]. 中国科学院大学学报, 2021, 38(1): 130-136.
[15]	胡莉娜, 高盛华. 基于层次化标签的人体解析[J]. 中国科学院大学学报, 2020, 37(6): 820-827.