使用簡易深度成像設(shè)備的高爾夫揮桿動態(tài)貝葉斯網(wǎng)絡(luò)三維重建
doi: 10.11999/JEIT150165
基金項(xiàng)目:
國家自然科學(xué)基金(61431017)和科技部國際科技合作專項(xiàng)(2012DFG11820)
Dynamic Bayesian Network Model Based Golf Swing 3D Reconstruction Using Simple Depth Imaging Device
-
摘要: 基于簡易深度成像設(shè)備的動作捕捉系統(tǒng)因其與傳統(tǒng)設(shè)備相比更加廉價(jià)且易于使用而倍受關(guān)注。然而,此類設(shè)備圖像分辨率很低,肢體間互相遮擋,缺乏3維動作重建的基本數(shù)據(jù)條件。該文融合人體關(guān)節(jié)點(diǎn)父子關(guān)系與關(guān)節(jié)點(diǎn)在運(yùn)動中的多階馬爾可夫性,提出一個(gè)描述人體關(guān)節(jié)點(diǎn)空間關(guān)系與動態(tài)特性的動態(tài)貝葉斯網(wǎng)絡(luò)(DBN)模型,基于該DBN模型并利用高爾夫揮桿運(yùn)動的相似性,構(gòu)建了一種高爾夫揮桿3維重建系統(tǒng)DBN-Motion(DBN-based Motion reconstruction system),使用簡易深度成像設(shè)備Kinect,有效地解決了肢體遮擋的問題,實(shí)現(xiàn)了高爾夫揮桿動作的捕獲和3維重建。實(shí)驗(yàn)結(jié)果表明,該系統(tǒng)能夠在重建精度上媲美商用光學(xué)動作捕捉系統(tǒng)。
-
關(guān)鍵詞:
- 信號處理 /
- 高爾夫揮桿重建 /
- 動態(tài)貝葉斯網(wǎng)絡(luò)模型 /
- 深度成像設(shè)備
Abstract: The simple depth imaging device gains more and more attention because of its lower cost and easy- to-use property compared with traditional motion capture systems. However, this kind of devices lack the basic data condition of 3D motion reconstruction due to low resolution, occlusions, and mixing up of body parts. In this paper, a Dynamic Bayesian Network (DBN) model is proposed to describe the spatial and temporal characteristics of human body joints. The model is based on fusion of the parent-child characteristics of joints and multi-order Markov property of joint during motion. A golf swing capture and reconstruction system DBN-Motion (DBN-based Motion reconstruction system), is presented based on the DBN model and the similarity of swing with a simple depth imaging device, Kinect, as capturing device. The proposed system effectively solves the problem of occlusions and mixing up of body parts, and successfully captures and reconstructs golf swing in 3D space. Experimental results prove that the proposed system can achieve comparable reconstruction accuracy to the commercial optical motion caption system. -
Zhou H and Hu H. Human motion tracking for rehabilitation a survey[J]. Biomedical Signal Processing and Control, 2008, 3(1): 1-18. Noiumkar S and Tirakoat S. Use of optical motion capture in sports science: a case study of golf swing[C]. 2013 International Conference on Informatics and Creative Multimedia (ICICM), Kuala Lumpur, 2013: 310-313. 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]. IEEE Journal of Selected Topics in Signal Processing, 2012, 6(5): 553-565. Nam C N K, Kang H J, and Suh Y S. Golf swing motion tracking using inertial sensors and a stereo camera[J]. IEEE Transactions on Instrumentation and Measurement, 2014, 63(4): 943-952. 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. Livingston M A, Sebastian J, Ai Z, et al.. Performance measurements for the microsoft kinect skeleton[C]. 2012 IEEE Virtual Reality Short Papers and Posters (VRW), Costa Mesa, CA, 2012: 119-120. Shum H P, Ho E S, Jiang Y, et al.. Real-time posture reconstruction for Microsoft Kinect[J]. IEEE Transactions on Cybernetics, 2013, 43(5): 1357-1369. Rosado J, Silva F, Santos V, et al.. Reproduction of human arm movements using kinect-based motion capture data[C]. 2013 IEEE International Conference on Robotics and Biomimetics (ROBIO), Shenzhen, 2013: 885-890. Xiang C, Hsu H H, Hwang W Y, et al.. Comparing real-time human motion capture system using inertial sensors with microsoft kinect[C]. 2014 7th International Conference on Ubi-Media Computing and Workshops (UMEDIA), Ulaanbaatar, 2014: 53-58. Kao W C, Hsu S C, and Huang C L. Human upper-body motion capturing using kinect[C]. 2014 International Conference on Audio, Language and Image Processing (ICALIP), Shanghai, 2014: 245-250. Zhang L, Hsieh J C, Ting T T, et al.. A kinect based golf swing score and grade system using GMM and SVM[C]. 2012 5th International Congress on Image and Signal Processing (CISP), Chongqing, 2012: 711-715. Zhang L, Hsieh J C, and Wang J. A kinect-based golf swing classification system using HMM and Neuro-Fuzzy[C]. 2012 International Conference on Computer Science and Information Processing (CSIP), Xi,an, 2012: 1163-1166. Lin Y H, Huang S Y, Huang S Y, et al.. A kinect-based system for golf beginners training[J]. Information Technology Convergence, 2013, 253(1): 121-129. Shen W, Deng K, Bai X, et al.. Exemplar-based human action pose correction and tagging[C]. 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, USA, 2012: 1784-1791. Smisek J, Jancosek M, and Pajdla T. 3D with kinect[C]. 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), Barcelona, 2011: 1154-1160. Arvind D and Bates A. The speckled golfer[C]. The ICST 3rd International Conference on Body Area Networks, Tempe, Arizona, 2008: 1-7. McGuan S P. Achieving commercial success with biomechanics simulation[C]. 20 International Symposium on Biomechanics in Sports, Cceres, Spain, 2002: 20, 451-460. . 8. -
計(jì)量
- 文章訪問數(shù): 1320
- HTML全文瀏覽量: 126
- PDF下載量: 667
- 被引次數(shù): 0