Please wait a minute...
J4  2009, Vol. 43 Issue (09): 1580-1584    DOI: 10.3785/j.issn.1008973X.2009.09.006
自动化技术、计算机技术     
基于实时图像的乒乓机器人Kalman跟踪算法
张远辉,韦巍,虞旦
(浙江大学 电气工程学院,浙江 杭州 310027)
Kalman tracking algorithm based on realtime vision of pingpong robot
 ZHANG Yuan-Hui, HUI Wei, YU Dan
(College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China)
 全文: PDF(897 KB)   HTML
摘要:

针对乒乓球高速运动图像模糊、空气阻力以及摄像机成像畸变等因素导致的误差问题,提出一种自适应测量协方差的离散Kalman轨迹估计算法.该算法通过动态调整测量协方差的大小,实现了对目标运动轨迹的准确跟踪,并进一步为乒乓球落点预测和手臂击打奠定了基础.实验表明,在图像采集速率高于70 帧/s、乒乓球速度超过5 m/s的情况下,该算法能有效地克服测量噪声和数据丢失的干扰情况的影响,给出优良的跟踪结果.同时该算法跟踪精度高,计算量小,适用于高速目标跟踪的场合.

Abstract:

An adapted measurement covariance digital Kalman filter method was proposed to eliminate the locating noises caused by motion blurring, airdrag and camera image distortion. The method implemented a precise tracking of the target motion trajectory by dynamically changing the measurement covariance, and laid a foundation for target prediction and arm motion. Experimental data showed a good tracking result in condition of camera capturing rate over 70 frame/s and ball motion speed over 5 m/s since the method effectively suppressed interference of noisy measurement and data losing. The method can be employed in cases of fast object tracking for its low computation load and high tracking precision.

:  TP 391.4  
基金资助:

浙江省人才基金资助项目(R105341);国家“863”高技术研究发展计划资助项目(2008AA042602);浙江省新世纪151人才工程资助项目.

通讯作者: 韦巍,男,教授,博导.     E-mail: wwei@cee.zju.edu.cn
作者简介: 张远辉(1982-),男,浙江绍兴人,博士生,从事机器人智能控制、计算机视觉和图像处理等的研究.
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  

引用本文:

张远辉, 韦巍, 虞旦. 基于实时图像的乒乓机器人Kalman跟踪算法[J]. J4, 2009, 43(09): 1580-1584.

ZHANG Yuan-Hui, HUI Wei, YU Dan. Kalman tracking algorithm based on realtime vision of pingpong robot. J4, 2009, 43(09): 1580-1584.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008973X.2009.09.006        http://www.zjujournals.com/eng/CN/Y2009/V43/I09/1580

 [1] ANDERSSON R L. A robot pingpong player: experiment in realtime intelligent control[M]. London: MIT, 1987.
 [2] ACOSTA L, RODRIGO J J, MENDEZ J A, et al. Pingpong player prototype[J]. Robotics and Automation Magazine, IEEE, 2003, 10(4): 4452.
 [3] MIYAZAKI F, TAKEUCHI M, MATSUSHIMA M, et al. Realization of the table tennis task based on virtual targets[C]//IEEE International Conference on Robotics and Automation. Washington, DC: IEEE, 2002: 38443849.
 [4] RUSDORF S, BRUNNETT G, LORENZ M, et al. Realtime interaction with a humanoid avatar in an immersive table tennis simulation[J]. IEEE Transactions on Visualization and Computer Graphics, 2007, 13(1):1525.
 [5] 刘志明, 韦巍. 基于均值变换的Particle Filter实时跟踪算法[J]. 模式识别与人工智能,2006,19(6):825830.
 LIU Zhiming, WEI Wei. Object tracking using particle filter based on mean shift [J]. Pattern Recognition and Artificial Intelligence, 2006,19(6): 825830.
 [6] 孙光东. 视频图像实时处理硬件结构的设计研究[J]. 哈尔滨工业大学学报,2006,38(6):10031004.
 SUN Guangdong. Research on realtime hardware manipulating visual signal[J]. Journal of Harbin Institute of Technology, 2006, 38(6):10031004.
 [7] 李洁, 孟中, 葛文奇. 数字滤波技术在陀螺噪声滤除中的应用[J]. 光电技术, 2003, 106(4): 2022.
 LI Jie, MENG Zhong, GE Wenqi. Application of digital filter technology in gyro noise elimination[J]. Electronic and Electrooptical Systems, 2003, 106(4):2022.
 [8] 王璐, 崔益安, 苏虹, 等. 移动机器人的运动目标实时检测与跟踪[J]. 计算机工程与应用, 2005, 41(15): 3033.
 WANG Lu, CHUI Yian, SU Hong, et al. Realtime moving object detection and tracking of mobile robots[J]. Computer Engineering and Applications, 2005, 41(15): 3033.
 [9] 彭博, 洪永潮, 杜森森,等.乒乓机器人击打点的预测方法[J]. 江南大学学报:自然科学版,2007, 6(4): 433437.
 PENG Bo, HONG Yongchao, DU Sensen, et al. An approach to hit point prediction for pingpong robot[J]. Journal of Jiangnan University: Natural Science Edition, 2007, 6(4):433437.
 [10] FORSYTH D A, PONCE J. Computer vision: a modern approach[M]. New Jersey: Prentice Hall,2002.
 [11] 张正友, 马颂德. 计算机视觉[M].北京: 科学出版社, 1998.
 [12] OPPENHEIM A V, WILLSKY A S, HAMID W S. Signals and systems[M]. New Jersey: Prentice Hall, 1996.
 [13] OGATA K. Modern control engineering[M]: New Jersey: Prentice Hall, 2001.
 [14] KALMAN R E, BUCY R S. New results in linear filtering and prediction theory[J]. Journal of Basic Engineering, 1961, 82(1): 3545.
 [15] 黄永梅, 傅承毓. 实时跟踪控制系统中的数字滤波技术[J]. 光电工程,1998, 25(2):713.
 HUANG Yongmei, FU Chengyu. Digital filtering technique in real time tracking and control system[J]. OptoElectronic Engineering, 1998, 25(2): 713.
 [16] 董亚卓, 刘明政, 夏飞, 等. 滑动窗口应用循环展开及其数据通路生成[J]. 计算机学报,2008,31(6): 989997.
 DONG Yazhuo, LIU Mingzheng, XIA Fei, et al. Loop unrolling and datapath generation of slidingwindow operation[J]. Chinese Journal of Computers, 2008, 31(6): 989997.

[1] 徐嵩,孙秀霞,何衍. 利用直线段成像特性的摄像机畸变迭代标定方法[J]. J4, 2014, 48(3): 404-413.
[2] 谢天, 解利军, 宋广华, 郑耀. 基于平面颜色分布的增强现实自然特征注册算法[J]. J4, 2013, 47(12): 2243-2252.
[3] 杨冰, 许端清, 杨鑫, 赵磊, 唐大伟. 基于艺术风格相似性规则的绘画图像分类[J]. J4, 2013, 47(8): 1486-1492.
[4] 杨帮华, 何美燕, 刘丽, 陆文宇. 脑机接口中基于BISVM的EEG分类[J]. J4, 2013, 47(8): 1431-1436.
[5] 楼晓俊, 孙雨轩, 刘海涛. 聚类边界过采样不平衡数据分类方法[J]. J4, 2013, 47(6): 944-950.
[6] 孟子博, 姜虹, 陈婧, 袁波, 王立强. 基于特征剪裁的AdaBoost算法及在人脸检测中的应用[J]. J4, 2013, 47(5): 906-911.
[7] 何智翔, 丁晓青, 方驰, 文迪. 基于LBP和CCS-AdaBoost的多视角人脸检测[J]. J4, 2013, 47(4): 622-629.
[8] 刘晓芳,叶修梓,张三元,张引. 并行磁共振图像的非二次正则化保边性重建[J]. J4, 2012, 46(11): 2035-2043.
[9] 张远辉,韦巍. 在线角速度估计的乒乓球机器人视觉测量方法[J]. J4, 2012, 46(7): 1320-1326.
[10] 施锦河, 沈继忠, 王攀. 四类运动想象脑电信号特征提取与分类算法[J]. J4, 2012, 46(2): 338-344.
[11] 张大尉, 朱善安. 基于核邻域保持判别嵌入的人脸识别[J]. J4, 2011, 45(10): 1842-1847.
[12] 舒振宇, 汪国昭. 基于张量投票的快速网格分割算法[J]. J4, 2011, 45(6): 999-1005.
[13] 徐舒畅, 张三元, 张引. 基于彩色图像的皮肤色素浓度提取算法[J]. J4, 2011, 45(2): 253-258.
[14] 佘青山, 孟明, 罗志增, 马玉良. 基于多核学习的下肢肌电信号动作识别[J]. J4, 2010, 44(7): 1292-1297.
[15] 薛凌云, 段会龙, 向学勤, 范影乐. 基于FitzHughNaguno神经元随机共振机制的图像复原[J]. J4, 2010, 44(6): 1103-1107.