[1]李 金,胡文广.基于颜色的快速人体跟踪及遮挡处理[J].智能系统学报,2010,5(04):353-359.
 LI Jin,HU Wen-guang.Tracking fast movement using colors while accommodating occlusion[J].CAAI Transactions on Intelligent Systems,2010,5(04):353-359.
点击复制

基于颜色的快速人体跟踪及遮挡处理(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第5卷
期数:
2010年04期
页码:
353-359
栏目:
出版日期:
2010-08-25

文章信息/Info

Title:
Tracking fast movement using colors while accommodating occlusion
文章编号:
1673-4785(2010)04-0353-07
作者:
李 金胡文广
哈尔滨工程大学 自动化学院,黑龙江 哈尔滨 150001
Author(s):
LI Jin HU Wen-guang
Automation College, Harbin Engineering University, Harbin 150001, China
关键词:
目标跟踪遮挡处理背景加权Kalman 预测模板更新
Keywords:
object tracking occlusion processing background weighted Kalman prediction template updated
分类号:
TP391
文献标志码:
A
摘要:
为了对被跟踪到的运动员进行运动姿态以及运动参数的分析,给运动员的训练提供科学合理的参考,提高比赛成绩,研究了面向体育视频的运动目标跟踪技术,提出了一种基于Mean Shift的综合算法.首先,根据背景加权直方图选择跟踪目标与背景图像的差别最显著的部分作为跟踪特征,以减少背景信息对跟踪效果的影响;其次,针对Mean Shift算法需要对图像进行穷举匹配的问题,利用Kalman滤波对目标的状态进行有效预测,减少了匹配运算次数,改善了快速运动目标的跟踪效果,提高了跟踪算法的稳健性;最后运用基于核的Mean Shift算法对运动目标进行跟踪,同时进行目标模板的实时更新,实现了对体育视频中运动员的稳定实时的跟踪.该方法成功地解决了部分遮挡、背景混乱以及目标尺寸变化等问题.
Abstract:
A new integrated algorithm was proposed to improve tracking of fast movement in sports videos. First, from the weighted background histogram, the portion of the image with the biggest differences between the tracking target and the background was selected as the tracking feature. This reduced the influence of background information on tracking effects. Next, since the mean shift algorithm needs exhaustive matching with images, we used Kalman filtering to effectively predict the target’s state. This decreased the number of matching calculations and thus improved the robustness of the tracking algorithm. A kernelbased Mean Shift algorithm was then employed to track moving targets. Finally, realtime updating of the target template was provided. The method ensures stable, realtime tracking of athletes in sports videos. Also, other problems, such as partial occlusions, chaotic backgrounds and variation in target size were successfully dealt with using the proposed algorithm.

参考文献/References:

[1]邓文坛,张三同,余纯. 一种改进的粒子滤波跟踪算法的研究[J].自动化技术与应用,2008, 27 (3): 84-87.
DENG Wentan, ZHANG Santong, YU Chun. A modified particle filtering algorithm for tracking[J]. Techniques of Automation and Application, 2008, 27(3): 84-87. 
[2]胡静,刘志镜.基于动态贝叶斯网络的多人跟踪算法[J].计算机工程,2008, 34(16): 247-248.
 HU Jing, LIU Zhijing. Tracking method of multiactors based on dynamic Bayesian network[J]. Computer Engineering, 2008, 34(16): 247-248.
[3]ZHEN Bin, KOBAYASHI M N, SHIMIZU M. Framed ALOHA for multiple RFID objects identification[J].IEICE Trans on Commun, 2005, 88(3): 991-999.
[4]吴玥,田兴彦.基于单目视频运动跟踪的三维人体动画[J]. 微计算机应用, 2008, 29(5): 42-47.
 WU Yue, TIAN Xingyan.3D human animation based on human motion tracking from monocular video sequences[J]. Micro Computer Application, 2008, 29(5): 42-47.
[5]高书秀,黄剑华,唐降龙,等.基于多区域的人体运动跟踪研究与应用[J].微计算机信息,2008, 24 (19):267-269.
GAO Shuxiu, HUANG Jianhua, TANG Xianglong, et al. Research on human motion tracking based on multiregion and its application[J].Micro Computer Information, 2008, 24(19): 267-269.
[6]熊文平,李锦涛,张勇东,刘金刚.一种有效的体育视频目标跟踪算法[J]. 计算机工程与应用, 2006, 26: 201-207.
XIONG Wenping, LI Jintao, ZHANG Yongdong, LIU Jingang. An efficient object tracking algorithm of sports video[J].Computer Engineering and Application, 2006, 26: 201-207.
[7]NUMMIARO K, KOLLERMEIER E, Van GOOL L. A adaptive colorbased particle filter[J].Image and Vision Computing, 2003, 21(1): 99-110.
[8]马波, 张田文.一种新颖的轮廓线跟踪算法[J].信号处理, 2004, 20(2): 174-178.
 MA Bo, ZHANG Tianwen. A new algorithm based on image contour line[J]. Signal Processing, 2004, 20(2): 174-178.
[9]COMANICIU D, MEER P. Kernelbased object tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-577.
 [10]赵万磊,张学杰. 基于RBK平均带宽设定的Adaptive Mean Shift[J].中国图象图形学报,2006,11(4): 511-515.
ZHAO Wanlei, ZHANG Xuejie. A new bandwidth varivable mean shift based on RBK means[J]. Journal of Image and Graphics, 2006, 11(4): 511-515.
[11]李闯, 丁晓青, 吴佑寿.一种基于直方图特征和AdaBoost的图像中的文字定位算法[J].中国图象图形学报, 2006, 11(3):325-331.
LI Chuang, DING Xiaoqing, WU Youshou. An algorithm for text location in images based on histogram features and adaboost[J]. Journal of Image and Graphics, 2006, 11(3): 325-331.
[12]伊怀峰, 黄贤武. 基于均值偏移的彩色图像分割算法[J].计算机应用, 2006,26(27):1605-1610.
YI Huaifeng, HUANG Xianwu. Color image segmentation algorithm based on mean shift[J]. Journal of Computer Applications, 2006, 26(27): 1605-1610.
[13]潘晨. 基于MeanShift和SVM的血细胞图像分割[J].仪器仪表学报, 2004,25(4):467-472.
PAN Chen. Combining meanshift and SVM for blood cell image segmentation[J]. Chinese Journal of Scientific Instrument, 2004, 25 (4): 467-472.
[14]朱胜利.Mean Shift及相关算法在视频跟踪中的研究[D].杭州:浙江大学, 2006. ZHU Shengli.A study of mean shift and correlative algorithm in visual tracking[D].Hangzhou: Zhejiang Unversity,  2006.

相似文献/References:

[1]王绍钰 蔡自兴,陈爱斌.改进的粒子滤波器目标跟踪方法[J].智能系统学报,2008,3(03):189.
 WANG Shao-yu,CAI Zi-xing,CHEN Ai-bin.Improved object tracking method for particle filters[J].CAAI Transactions on Intelligent Systems,2008,3(04):189.
[2]刘 清,吴志刚,窦 琴,等.粒子滤波的视频目标跟踪算法研究[J].智能系统学报,2009,4(06):538.[doi:10.3969/j.issn.1673-4785.2009.06.012]
 LIU Qing,WU Zhi-gang,DOU Qin,et al.A particle filtering algorithm for tracking moving objects in videos[J].CAAI Transactions on Intelligent Systems,2009,4(04):538.[doi:10.3969/j.issn.1673-4785.2009.06.012]
[3]伍 明,孙继银.一种机器人未知环境下动态目标跟踪交互多模滤波算法[J].智能系统学报,2010,5(02):127.
 WU Ming,SUN Ji-yin.An interacting multiple model filtering algorithm for mobile robots to improve tracking of moving objects in unknown environments[J].CAAI Transactions on Intelligent Systems,2010,5(04):127.
[4]刘侠,陶冶,邢春.统计差分与自启动的Camshift跟踪算法[J].智能系统学报,2011,6(04):355.
 LIU Xia,TAO Ye,XING Chun.An objective tracking Camshift algorithm based onautomatic startup and the statistical differential method[J].CAAI Transactions on Intelligent Systems,2011,6(04):355.
[5]伍明,孙继银.基于粒子滤波的未知环境下机器人同时定位、地图构建与目标跟踪[J].智能系统学报,2013,8(02):168.[doi:10.3969/j.issn.1673-4785.201202001]
 WU Ming,SUN Jiyin.Simultaneous localization, mapping and object tracking in an unknown environment using particle filtering[J].CAAI Transactions on Intelligent Systems,2013,8(04):168.[doi:10.3969/j.issn.1673-4785.201202001]
[6]贺超,刘华平,孙富春,等.采用Kinect的移动机器人目标跟踪与避障[J].智能系统学报,2013,8(05):426.[doi:10.3969/j.issn.1673-4785.201301028]
 HE Chao,LIU Huaping,SUN Fuchun,et al.Target tracking and obstacle avoidance of mobile robot using Kinect[J].CAAI Transactions on Intelligent Systems,2013,8(04):426.[doi:10.3969/j.issn.1673-4785.201301028]
[7]王熙,吴为,钱沄涛.基于轨迹聚类的超市顾客运动跟踪[J].智能系统学报,2015,10(02):187.[doi:10.3969/j.issn.1673-4785.201401002]
 WANG Xi,WU Wei,QIAN Yuntao.Trajectory clustering based customer movement tracking in a supermarket[J].CAAI Transactions on Intelligent Systems,2015,10(04):187.[doi:10.3969/j.issn.1673-4785.201401002]
[8]陈真,王钊.元认知粒子滤波目标跟踪算法[J].智能系统学报,2015,10(03):387.[doi:10.3969/j.issn.1673-4785.201405052]
 CHEN Zhen,WANG Zhao.Object tracking algorithm with metacognitive model-based particle filters[J].CAAI Transactions on Intelligent Systems,2015,10(04):387.[doi:10.3969/j.issn.1673-4785.201405052]
[9]王杰,蒋明敏,花晓慧,等.基于投影直方图匹配的双目视觉跟踪算法[J].智能系统学报,2015,10(5):775.[doi:10.11992/tis.201410009]
 WANG Jie,JIANG Mingmin,HUA Xiaohui,et al.Binocular object tracking method using projection histogram matching[J].CAAI Transactions on Intelligent Systems,2015,10(04):775.[doi:10.11992/tis.201410009]
[10]刘峰,宣士斌,刘香品.佳点集的QMC粒子滤波算法及其应用[J].智能系统学报,2014,9(04):461.[doi:10.3969/j.issn.1673-4785.201305079]
 LIU Feng,XUAN Shibin,LIU Xiangpin.Quasi-Monte Carlo particle filter algorithm based on the good point set and its application[J].CAAI Transactions on Intelligent Systems,2014,9(04):461.[doi:10.3969/j.issn.1673-4785.201305079]

备注/Memo

备注/Memo:
收稿日期:2009-04-13.
基金项目:黑龙江省博士后研究基金资助项目(LBHQ05046).
通信作者:胡文广. E-mail: wghu247131@126.com.
作者简介:
李 金,女,1962年生,教授,博士生导师,黑龙江省教学名师,省级精品课程负责人.主要研究方向为模式识别与智能系统等.出版国家“十一五”规划教材等著作7部.获省部级科技进步二等奖3项、三等奖3项,国家发明专利3项,得黑龙江省留学人员报国奖和哈尔滨市青年科技奖.发表学术论文120余篇,其中被EI等检索40余篇.
胡文广,男,1983年生,硕士研究生,主要研究方向为视频运动检测与跟踪.
更新日期/Last Update: 2010-09-20