基于多级动态模型的2维人体姿态估计

doi:10.13973/j.cnki.robot.2016.0578

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (715 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
马淼, 李贻斌. 基于多级动态模型的2维人体姿态估计[J]. 机器人, 2016, 38(5): 578-587.DOI: 10.13973/j.cnki.robot.2016.0578. MA Miao, LI Yibin. 2D Human Pose Estimation Using Multi-level Dynamic Model. ROBOT, 2016, 38(5): 578-587. DOI: 10.13973/j.cnki.robot.2016.0578.

摘要提出一种利用多级动态模型来估计单目视频中的人体姿态的方法．首先，构建了一种多级动态人体姿态模型，该模型将人体姿态视为各部位姿态的铰接组合，用部位姿态的最优估计来逼近整体姿态的最优估计，从而解决了整体姿态估计带来的歧义性问题．其次，提出了一种通过构建虚拟姿态来计算视频相邻帧之间姿态一致性的算法，该算法能够有效利用视频中表观特征及运动特征的连续性，从而提高姿态估计精度．此外，使用粒子群优化算法用较小的姿态样本优化出最优部位姿态，并将最优部位姿态重组为最优的人体姿态．通过实验验证了所提方法的有效性，并与几种前沿方法进行了比较．实验结果表明，本文方法有效提高了人体姿态估计的准确度．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	马淼
	李贻斌

关键词 ：人体姿态估计, 多级动态模型, 视频理解, 人体行为理解

Abstract：A human pose estimation algorithm with a multi-level dynamic model for monocular videos is presented. Firstly, a multi-level dynamic model of human pose is constructed to decompose human entire pose into articulated pose parts, and approach optimal human pose candidates by optimizing pose parts candidates. This model solves the ambiguity problem caused by the entire pose estimation method. Secondly, an algorithm for calculating the pose consistency between the adjacent video frames is proposed by constructing virtual poses. This method can make use of the continuity of appearance features and motion features between the adjacent frames to improve the estimation accuracy. Thirdly, particle swarm optimization method is utilized to search for the best pose parts candidates with a small amount of candidates, and then the achieved pose parts are recomposed into the optimal human entire poses. The efficiency of the proposed method is tested and experimentally compared with several related state-of-the-art methods on challenging video sequences, which shows significant improvements.

Key words： human pose estimation multi-level dynamic model video understanding human activity understanding

收稿日期: 2016-03-07 录用日期: 2016-07-18

TP391

基金资助:国家863计划（2015AA042201）；国家自然科学基金（61233014）

通讯作者: 马淼，mamiaosdu@hotmail.com；李贻斌，liyb@sdu.edu.cn E-mail: mamiaosdu@hotmail.com;liyb@sdu.edu.cn

作者简介: 马淼（1989-），女，博士生．研究领域：机器视觉，智能机器人，模式识别与智能系统．
李贻斌（1960-），男，博士，教授．研究领域：智能机器人，特种机器人，智能车辆．

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.2016.0578 或 https://robot.sia.cn/CN/Y2016/V38/I5/578

[1] Dautenhahn K. Socially intelligent robots:Dimensions of human-robot interaction[J]. Philosophical Transactions of the Royal Society of London, B:Biological Sciences, 2007, 362(1480):679-704.

[2] Atkeson C G, Hale J G, Pollick F E, et al. Using humanoid robots to study human behavior[J]. IEEE Intelligent Systems and Their Applications, 2000, 15(4):46-55.

[3] 田国会,尹建芹,韩旭,等.一种基于关节点信息的人体行为识别新方法[J].机器人,2014,36(3):285-292. Tian G H, Yin J Q, Han X, et al. A novel human activity recognition method using joint points information[J]. Robot, 2014, 36(3):285-292.
[4] Yang Y Z, Li Y, Fermüller C, et al. Robot learning manipulation action plans by "watching" unconstrained videos from the World Wide Web[C]//Proceedings of the 29th AAAI Conference on Artificial Intelligence. 2015:3686-3693.
[5] Koppula H S, Gupta R, Saxena A. Learning human activities and object affordances from RGB-D videos[J]. International Journal of Robotics Research, 2013, 32(8):951-970.

[6] Yang Y, Ramanan D. Articulated human detection with flexible mixtures of parts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(12):2878-2890.

[7] Dantone M, Gall J, Leistner C, et al. Human pose estimation using body parts dependent joint regressors[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2013:3041-3048.
[8] Fischler M A, Elschlager R A. The representation and matching of pictorial structures[J]. IEEE Transactions on Computers, 1973, 22(1):67-92.
[9] Freifeld O, Weiss A, Zuffi S, et al. Contour people:A parameterized model of 2D articulated human shape[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2010:639-646.
[10] Zuffi S, Freifeld O, Black M J. From pictorial structures to deformable structures[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2012:3546-3553.
[11] Park D, Ramanan D. N-best maximal decoders for part models[C]//IEEE International Conference on Computer Vision. Piscataway, USA:IEEE, 2011:2627-2634.
[12] Sapp B, Toshev A, Taskar B. Cascaded models for articulated pose estimation[C]//11th European Conference on Computer Vision. Berlin, Germany:Springer, 2010:406-420.
[13] Andriluka M, Roth S, Schiele B. Pictorial structures revisited:People detection and articulated pose estimation[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2009:1014-1021.
[14] Ramanan D, Forsyth D A, Zisserman A. Strike a pose:Tracking people by finding stylized poses[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2005:271-278.
[15] Lee M W, Nevatia R. Human pose tracking using multi-level structured models[C]//9th European Conference on Computer Vision. Berlin, Germany:Springer, 2006:368-381.
[16] Felzenszwalb P F, Huttenlocher D P. Pictorial structures for object recognition[J]. International Journal of Computer Vision, 2005, 61(1):55-79.

[17] Sigal L, Black M J. Measure locally, reason globally:Occlusion-sensitive articulated pose estimation[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2006:2041-2048.
[18] Anguelov D, Srinivasan P, Koller D, et al. SCAPE:Shape completion and animation of people[J]. ACM Transactions on Graphics, 2005, 24(3):408-416.

[19] Zuffi S, Romero J, Schmid C, et al. Estimating human pose with flowing puppets[C]//IEEE International Conference on Computer Vision. Piscataway, USA:IEEE, 2013:3312-3319.
[20] Chang C C, Lin C J. LIBSVM:A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3):No.27.
[21] Pan S J, Yang Q. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10):1345-1359.

[22] Sapp B,Weiss D, Taskar B. Parsing human motion with stretchable models[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2011:1281-1288.
[23] Sigal L, Black M J. Predicting 3D people from 2D pictures[C]//4th International Conference on Articulated Motion and Deformable Objects. Berlin, Germany:Springer, 2006:185-195.
[24] Yang Y, Ramanan D. Articulated pose estimation with flexible mixtures-of-parts[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2011:1385-1392.
[25] Poli R, Kennedy J, Blackwell T. Particle swarm optimization:An overview[J]. Swarm Intelligence, 2007, 1(1):33-57.

[26] Rohrbach M, Amin S, Andriluka M, et al. A database for fine grained activity detection of cooking activities[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2012:1194-1201.
[27] 柴汇,孟健,荣学文,等.高性能液压驱动四足机器人SCalf的设计与实现[J].机器人,2014,36(4):385-391. Chai H, Meng J, Rong XW, et al. Design and implementation of SCalf, an advanced hydraulic quadruped robot[J]. Robot, 2014, 36(4):385-391.
[28] 张慧,荣学文,李贻斌,等.四足机器人地形识别与路径规划算法[J].机器人,2015,37(5):546-556. Zhang H, Rong XW, Li Y B, et al. Terrain recognition and path planning for quadruped robot[J]. Robot, 2015, 37(5):546-556.