A generalized mean shift tracking algorithm

被引：4

作者：

Chen JianJun ^{[1
,4
]}

Zhang SuoFei ^{[1
]}

An GuoCheng ^{[2
]}

Wu ZhenYang ^{[1
,3
]}

机构：

[1] Southeast Univ, Sch Informat Sci & Engn, Nanjing 210096, Peoples R China

[2] Chinese Acad Sci, Inst Software, Intelligence Engn Lab, Beijing 100190, Peoples R China

[3] Southeast Univ, Key Lab Underwater Acoust Signal Proc, Minist Educ, Nanjing 210096, Peoples R China

[4] Nanjing Res Inst Elect Technol, Nanjing 210013, Peoples R China

来源：

SCIENCE CHINA-INFORMATION SCIENCES | 2011年 / 54卷 / 11期

基金：

中国博士后科学基金; 中国国家自然科学基金;

关键词：

mean shift; CAMSHIFT; video target tracking; similarity measure;

D O I：

10.1007/s11432-011-4359-8

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

CAMSHIFT algorithm and Comaniciu/Meer algorithm are two fundamental frameworks of mean shift procedure for video target tracking. This paper generalizes the two well-known mean shift tracking algorithms, originally due to Bradski and Comaniciu/Meer. A new general similarity function which defines the distance between the target model and target candidate is employed to calculate the pixel weights and the target location. The target size is iteratively estimated and updated based on the zeroth order moment of the pixel weights. Then we prove that both the CAMSHIFT algorithm and the Comaniciu/Meer algorithm can be included in the generalized mean shift tracking framework. The tracking performances of three mean shift algorithms in the unified framework are shown and compared in the experimental results.

引用

页码：2373 / 2385

页数：13

共 21 条

[1] [Anonymous], 2009, PROC 14 OPTOELECTRON
[2] Real time face and object tracking as a component of a perceptual user interface
Bradski, GR
[J]. FOURTH IEEE WORKSHOP ON APPLICATIONS OF COMPUTER VISION - WACV'98, PROCEEDINGS, 1998, : 214 - 219
[3] Gaussian mean-shift is an EM algorithm
Carreira-Perpinan, Miguel A.
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2007, 29 (05) : 767 - 776
[4] A MEAN SHIFT ALGORITHM BASED ON MODIFIED PARZEN WINDOW FOR SMALL TARGET TRACKING
Chen, Jianjun
An, Guocheng
Zhang, Suofei
Wu, Zhenyang
[J]. 2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, : 1166 - 1169
[5] Augmented reality registration algorithm based on nature feature recognition
Chen Jing
Wang YongTian
Guo JunWei
Liu Wei
Lin JingDun
Xue Kang
Liu Yue
Ding GangYi
[J]. SCIENCE CHINA-INFORMATION SCIENCES, 2010, 53 (08) : 1555 - 1565
[6] MEAN SHIFT, MODE SEEKING, AND CLUSTERING
CHENG, YZ
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1995, 17 (08) : 790 - 799
[7] Kernel-based object tracking
Comaniciu, D
Ramesh, V
Meer, P
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2003, 25 (05) : 564 - 577
[8] Adaptive mixture observation models for multiple object tracking
Cui Peng
Sun LiFeng
Yang ShiQiang
[J]. SCIENCE IN CHINA SERIES F-INFORMATION SCIENCES, 2009, 52 (02): : 226 - 235
[9] Mean shift is a bound optimization
Fashing, M
Tomasi, C
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2005, 27 (03) : 471 - 474
[10] Freedman D, 2009, PROC CVPR IEEE, P1818, DOI 10.1109/CVPRW.2009.5206716

← 1 2 3 →