[1]LI Jin,HU Wen-guang.Tracking fast movement using colors while accommodating occlusion[J].CAAI Transactions on Intelligent Systems,2010,5(4):353-359.
Copy

Tracking fast movement using colors while accommodating occlusion

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 5 Number of periods: 2010 4 Page number: 353-359 Column: 学术论文—机器感知与模式识别 Public date: 2010-08-25
Title:
Tracking fast movement using colors while accommodating occlusion
Author(s):
LI Jin;  HU Wen-guang
Automation College, Harbin Engineering University, Harbin 150001, China
Keywords:
object tracking;  occlusion processing;  background weighted;  Kalman prediction;  template updated
CLC:
TP391
DOI:
-
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.
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.
Similar References:

Memo

-

Last Update: 2010-09-20

Copyright © CAAI Transactions on Intelligent Systems