AIPUB归智期刊联盟

微信公众号

网站二维码

2025年4月1日 9:57 星期二
首页 > 过刊浏览>2018年第27卷第5期 >17-25. DOI:10.15888/j.cnki.csa.006358
PDF HTML阅读 XML下载 导出引用 引用提醒
基于骨骼约束的人体运动捕捉数据失真恢复
作者:
基金项目:

浙江省自然科学基金重点项目（LZ15F020004）；浙江省自然科学基金一般项目（LY17F020034）；机械工程浙江省高校重中之重学科和浙江理工大学重点实验室优秀青年人才培养基金（ZSTUME01B17）


Human Motion Capture Data Recovery Based on Skeleton Constraint
Author:
  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [22]
    • |
  • 相似文献 [20]
    • | | |
  • 文章评论
    摘要:

    针对人体运动捕捉（Motion Capture，MOCAP）数据实际采集过程中，由于光线等因素影响而可能出现的同一帧中相邻标记点在时间域上连续缺失的情形，利用MOCAP数据中存在的潜在相关性和同一运动序列中人体骨骼长度不变特性，提出一种新的MOCAP数据失真恢复算法.该算法首先对MOCAP数据进行预处理，使变换后的数据表示的是相邻标记点的相对位置的变化，由此得到人体骨骼长度约束项，再利用稀疏表示和人体骨骼长度约束项进行字典训练，最后利用训练得到的字典对缺失的数据进行恢复.通过实验对比表明该算法在提高缺失点坐标恢复精度的同时，将骨骼长度恢复精度提高到10–4 cm，验证了算法的可行性和有效性.

    Abstract:

    For the situation that the adjacent markers of Motion Capture (MOCAP) data missing for a period of time due to lights and other factors when practically gathering data, a new MOCAP data recovery algorithm is proposed by using the latent correlation and the skeleton constraint in MOCAP data. The algorithm firstly transforms the MOCAP data to represent the changes of the relative position of adjacent markers to acquire the skeleton constraint term. Then the sparse representation and the skeleton constraint term are used for dictionary training which is utilized to recovery missing data. The experiment results show that the algorithm can improve the recovery accuracy of the coordinates of the missing markers and increase the bone length recovery accuracy to 10-4 cm, and verify the feasibility and effectiveness of the algorithm.

    参考文献
    [1] Bruderlin A, Williams L. Motion signal processing. Proceedings of the 22nd Annual Conference on Computer Graphics and Interactive Techniques. New York, NY, USA. 1995. 97-104.
    [2] Yamane K, Nakamura Y. Dynamics filter-concept and implementation of online motion generator for human figures. IEEE Trans. on Robotics and Automation, 2003, 19(3):421-432.[DOI:10.1109/TRA.2003.810579]
    [3] Hsieh CC, Kuo PL. An impulsive noise reduction agent for rigid body motion data using B-spline wavelets. Expert Systems with Applications, 2008, 34(3):1733-1741.[DOI:10.1016/j.eswa.2007.01.030]
    [4] Li L, McCann J, Pollard N, et al. BoLeRO:A principled technique for including bone length constraints in motion capture occlusion filling. Proceedings of the 2010 ACM SIGGRAPH/Eurographics Symposium on Computer Animation. Madrid, Spain. 2010. 179-188.
    [5] Li L, McCann J, Pollard NS, et al. DynaMMo:Mining and summarization of coevolving sequences with missing values. Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Paris, France. 2009. 507-516.
    [6] Lai RYQ, Yuen PC, Lee KKW. Motion capture data completion and denoising by singular value thresholding. Proc Eurographics Association, 2011, 11(3):924-929.
    [7] Tan CH, Hou JH, Chau LP. Human motion capture data recovery using trajectory-based matrix completion. Electronics Letters, 2013, 49(12):752-754.[DOI:10.1049/el.2013.0442]
    [8] 彭淑娟, 赫高峰, 柳欣, 等. 基于运动分割和稀疏低秩分解的失真人体运动捕捉数据恢复. 计算机辅助设计与图形学学报, 2015, 27(4):721-730, 737.
    [9] 赫高峰, 彭淑娟, 柳欣, 等. 结合模糊聚类和投影近似点算法的缺失人体运动捕捉数据重构. 计算机辅助设计与图形学学报, 2015, 27(8):1416-1425.
    [10] Feng YF, Xiao J, Zhuang YT, et al. Exploiting temporal stability and low-rank structure for motion capture data refinement. Information Sciences, 2014, 277:777-793.[DOI:10.1016/j.ins.2014.03.013]
    [11] Hou JH, Chau LP, He Y, et al. Human motion capture data recovery via trajectory-based sparse representation. Proceedings of the 20th IEEE International Conference on Image Processing. Melbourne, VIC, Australia. 2014. 709-713.
    [12] Xiao J, Feng YF, Hu WY. Predicting missing markers in human motion capture using l1-sparse representation. Computer Animation & Virtual Worlds, 2011, 22(2-3):221-228.
    [13] Xiao J, Feng YF, Ji MM, et al. Sparse motion bases selection for human motion denoising. Signal Processing, 2015, 110:108-122.[DOI:10.1016/j.sigpro.2014.08.017]
    [14] Feng YF, Ji MM, Xiao J, et al. Mining spatial-temporal patterns and structural sparsity for human motion data denoising. IEEE Trans. on Cybernetics, 2015, 45(12):2693-2706.[DOI:10.1109/TCYB.2014.2381659]
    [15] Wang Z, Feng YF, Liu S, et al. A 3D human motion refinement method based on sparse motion bases selection. Proceedings of the 29th International Conference on Computer Animation and Social Agents. Geneva, Switzerland. 2016. 53-60.
    [16] Tan CH, Hou JH, Chau LP. Motion capture data recovery using skeleton constrained singular value thresholding. The Visual Computer, 2015, 31(11):1521-1532.[DOI:10.1007/s00371-014-1031-5]
    [17] Lai RYQ, Yuen PC, Lee KW, et al. Interactive character posing by sparse coding. arXiv:1201.1409, 2012.
    [18] Elad M. Sparse and Redundant Representations:From Theory to Applications in Signal and Image Processing. New York, USA:Springer, 2010:44-46.
    [19] Lee H, Battle A, Raina R, et al. Efficient sparse coding algorithms. Proceedings of the 19th International Conference on Neural Information Processing Systems. Cambridge, MA, USA. 2006. 801-808.
    [20] Yang AY, Sastry SS, Ganesh A, et al. Fast l1-minimization algorithms and an application in robust face recognition:A review. Proceedings of the 17th IEEE International Conference on Image Processing. Hong Kong, China. 2010. 1849-1852.
    [21] Beck A, Teboulle M. A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM Journal on Imaging Sciences, 2009, 2(1):183-202.[DOI:10.1137/080716542]
    [22] Aharon M, Elad M, Bruckstein A. rmK-SVD:An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. on Signal Processing, 2006, 54(11):4311-4322.[DOI:10.1109/TSP.2006.881199]
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

汪亚明,鲁涛,韩永华.基于骨骼约束的人体运动捕捉数据失真恢复.计算机系统应用,2018,27(5):17-25

复制
分享
文章指标
  • 点击次数:2058
  • 下载次数: 3654
  • HTML阅读次数: 1169
  • 引用次数: 0
历史
  • 收稿日期:2017-09-12
  • 最后修改日期:2017-09-30
  • 在线发布日期: 2018-03-12
文章二维码
友情链接:中国科学院软件研究所中国计算机学会中国科学院国家自然科学基金委员会软件学报
您是第11124360位访问者
版权所有：中国科学院软件研究所 京ICP备05046678号-3
地址：北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码：100190
电话：010-62661041 传真： Email：csa (a) iscas.ac.cn
技术支持：北京勤云科技发展有限公司

京公网安备 11040202500063号