采用改进粒子群优化粒子滤波的三维人手跟踪

李东年; 周以齐

doi:10.3788/OPE.20142210.2870

您当前的位置：

首页 >

文章列表页 >

采用改进粒子群优化粒子滤波的三维人手跟踪

信息科学 | 更新时间：2020-08-13

- 采用改进粒子群优化粒子滤波的三维人手跟踪
- Three dimensional hand tracking by improved particle swarm optimized particle filter
- 光学精密工程 2014年22卷第10期页码：2870-2878
- 作者机构：
  
  1. 山东大学机械工程学院虚拟工程研究中心,山东济南,250061
  2. 山东大学高效洁净机械制造教育部重点实验室,山东济南,250061
- 作者简介：
- 基金信息：
  
  山东省科技攻关计划资助项目(No.2010G0020233)()
- DOI：10.3788/OPE.20142210.2870
  中图分类号： TP391.4
- 收稿日期：2014-03-24，
  
  修回日期：2014-05-29，
  
  纸质出版日期：2014-10-25
- 稿件说明：
移动端阅览
李东年, 周以齐,. 采用改进粒子群优化粒子滤波的三维人手跟踪[J]. 光学精密工程, 2014,22(10): 2870-2878

LI Dong-nian, ZHOU Yi-qi,. Three dimensional hand tracking by improved particle swarm optimized particle filter[J]. Editorial Office of Optics and Precision Engineering, 2014,22(10): 2870-2878
李东年, 周以齐,. 采用改进粒子群优化粒子滤波的三维人手跟踪[J]. 光学精密工程, 2014,22(10): 2870-2878 DOI： 10.3788/OPE.20142210.2870.

LI Dong-nian, ZHOU Yi-qi,. Three dimensional hand tracking by improved particle swarm optimized particle filter[J]. Editorial Office of Optics and Precision Engineering, 2014,22(10): 2870-2878 DOI： 10.3788/OPE.20142210.2870.

摘要

针对高维人手状态空间中的采样稀疏问题

提出了一种基于改进粒子群优化粒子滤波的关节人手跟踪方法

用于从Kinect获取的深度图像序列中恢复三维人手运动.首先

利用简单几何基元建立三维人手模型

并为其添加自由度节点

用于在跟踪过程中生成可与观测特征进行比较的人手姿势假设.然后

在粒子滤波框架下

使用深度图像作为观测输入

融合深度特征与区域特征建立了系统观测模型.最后

将粒子群优化粒子滤波应用于关节人手运动跟踪.为避免在高维空间中的早熟收敛问题

利用模拟退火思想和局部随机化方法对算法进行改进

增强了算法的全局搜索能力.通过合成序列和真实序列上的跟踪实验对该方法进行了评价

结果表明该方法的关节角度跟踪误差均值约为2.3°

标准差约为1.7°

优于标准粒子滤波和标准粒子群优化跟踪方法

可以准确、鲁棒地从深度图像跟踪三维人手运动.

Abstract

To overcome the difficulty of dense sampling in a high-dimensional hand state space

an improved Particle Swarm Optimized Particle Filter (PSOPF) algorithm was proposed to track articulated hand motion from single depth images obtained by a Kinect sensor. Firstly

a 3D hand model was built with basic geometric primitives

and the nodes with degrees of freedom (DOFs) were added into the model to generate the hand pose hypotheses to compare with the observation feature in the tracking process. Then

the single depth images were used as the only input

and the system observation model was established by combining depth features and silhouette features in the framework of particle filter. Finally

the PSOPF was applied to articulated hand tracking. To avoid the premature convergence in the high-dimensional space

the global search ability of the algorithm was improved by applying simulated annealing and partial randomization on the particles. Experiments were conducted both on synthetic data and real sequences for evaluation of the proposed method. It shows that the average of the joint angle errors for proposed method is about 2.3° and the standard deviation is about 1.7°

which are better than those of the standard Particle Filter(PF) and the standard Particle Swarm Optimization (PSO) method. The results show that the proposed method may track 3D articulated hand motion accurately and robustly from single depth images.

关键词

Keywords

references

KESKIN C, KIRAÇ F, KARA Y E, et al.. Hand pose estimation and hand shape classification using multi-layered randomized decision forests[C]. Proceedings of the 12th European Conference on Computer Vision, Berlin Heidelberg: Springer, 2012, 6: 852-863.

KESKIN C, KIRAC F, KARA Y E, et al.. Real time hand pose estimation using depth sensors[C]. Consumer Depth Cameras for Computer Vision, London: Springer, 2013:119-137.

DOLIOTIS P, ATHITSOS V, KOSMOPOULOS D, et al.. Hand shape and 3D pose estimation using depth data from a single cluttered frame[C]. Advances in Visual Computing, Berlin Heidelberg: Springer, 2012, 1: 148-158.

PRISACARIU V A, REID I. 3D hand tracking for human computer interaction [J]. Image and Vision Computing, 2012, 30(3): 236-250.

KENNEDY J, EBERHART R. Particle swarm optimization[C]. Proceedings of the IEEE International Conference on Neural Networks, Piscataway: IEEE Press, 1995, 4:1942-1948.

BRAY M, KOLLER-MEIER E, VAN GOOL L. Smart particle filtering for 3D hand tracking[C]. Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, Los Alamitos: IEEE Computer Society Press, 2004: 675-680.

吕治国,李焱,徐昕. 快速的三维人手运动跟踪方法研究[J]. 计算机研究与发展,2012,49(7):1398-1407. L ZH G, LI Y, XU X. Research on fast 3D hand motion tracking system [J]. Journal of Computer Research and Development, 2012, 49(7):1398-1407. (in Chinese)

ZHANG Z, SEAH H S, QUAH C K, et al.. GPU-accelerated real-time tracking of full-body motion with multi-layer search [J]. IEEE Transactions on Multimedia, 2013, 15(1): 106-119.

ZHANG Z, SEAH H S. Skeleton body pose tracking from efficient three-dimensional motion estimation and volumetric reconstruction [J]. Applied Optics, 2012, 51(23): 5686-5697.

OIKONOMIDIS I, KYRIAZIS N, ARGYROS A A. Efficient model-based 3D tracking of hand articulations using Kinect[C]. Proceedings of the 22nd British Machine Vision Conference, Guildford: BMVA Press, 2011: 101.1-101.11.

LIANG H, YUAN J S, THALMANN D, et al.. Model-based hand pose estimation via spatial-temporal hand parsing and 3D fingertip localization [J]. The Visual Computer, 2013, 29(6-8): 837-848.

龚俊亮,何昕, 魏仲慧,等. 采用改进辅助粒子滤波的红外多目标跟踪[J]. 光学精密工程,2012,20 (2):413-421. GONG J L, HE X, WEI ZH H, et al.. Multiple infrared target tracking using improved auxiliary particle filter [J]. Opt. Precision Eng., 2012, 20(2): 413-421. (in Chinese)

吴新杰,黄国兴,王静文. 粒子滤波算法在ECT图像重建中的应用[J]. 光学精密工程,2012,20 (8):1824-1830. WU X J, HUANG G X, WANG J W. Application of particle filtering algorithm to image reconstruction of ECT [J]. Opt. Precision Eng., 2012, 20(8): 1824-1830. (in Chinese)

王国良,刘金国. 基于粒子滤波的多自由度运动目标跟踪[J]. 光学精密工程,2011,19 (4):864-869. WANG G L, LIU J G. Moving object tracking with multi-degree-of-freedom based on particle filters [J]. Opt. Precision Eng., 2011, 19(4): 864-869. (in Chinese)

方正,佟国峰,徐心和. 粒子群优化粒子滤波方法[J]. 控制与决策,2007,22(3):273-277. FANG ZH, TONG G F, XU X H. Particle swarm optimized particle filter [J]. Control and Decision, 2007, 22(3): 273-277. (in Chinese)

KROHLING R A. Gaussian swarm: a novel particle swarm optimization algorithm[C]. Proceedings of the 2004 IEEE Conference on Cybernetics and Intelligent Systems, Piscataway: IEEE Press, 2004, 1: 372-376.

YASUDA T, OHKURA K, MATSUMURA Y. Extended PSO with partial randomization for large scale multimodal problems[C]. Proceedings of World Automation Congress, Albuquerque: TSI Press, 2010: 1-6.

EROL A, BEBIS G, NICOLESCU M, et al.. A review on vision-based full DOF hand motion estimation[C]. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Los Alamitos: IEEE Computer Society Press, 2005: 75-82.

浏览量

304

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于像素投票的人手全局姿态估计

基于场景辅助特征的T-S目标跟踪

基于稀疏正则约束的子空间视觉跟踪

基于显著性直方图的粒子滤波跟踪

基于仿射变换与均匀采样建模的目标跟踪