Analyzing of Mean-Shift Algorithm in Gray Target Tracking Technology

被引:0
作者
Zhang, Shuang [1 ]
Qin, Yu-Ping [2 ]
Jin, Gang [1 ]
机构
[1] Chengdu Univ Technol, Engn & Tech Coll, Leshan 614000, Peoples R China
[2] Chinese Acad Sci, Inst Opt & Elect, Chengdu, Peoples R China
来源
ARTIFICIAL INTELLIGENCE AND COMPUTATIONAL INTELLIGENCE, PT I | 2011年 / 7002卷
关键词
target tracking; mean-shift; automatic steer; local difference;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Target tracking technology is an extreme important project in computer vision technology area. Its development can directly force the development of the automatic steer technique. According to target tracking, scientists research out many important tracking algorithms. Mean-shift algorithm is an important computational method in various of target tracking algorithms, which adopts the features of anti-size change, anti-rotation change, and few manual intervention showing the extremely vital role in modern target tracking area. While not all tracking techniques can achieve good effects to it. Therefore, the article analyzed the algorithm from the aspect of practical engineering. And use local difference algorithm to make further improvement to it. Finally through three groups of tracking examples to point out the advantages and disadvantages of this algorithm and the advantages of improved algorithm, and expanded the algorithm using sides.
引用
收藏
页码:155 / +
页数:2
相关论文
共 5 条
[1]   Kernel-based object tracking [J].
Comaniciu, D ;
Ramesh, V ;
Meer, P .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2003, 25 (05) :564-577
[2]   Mean shift: A robust approach toward feature space analysis [J].
Comaniciu, D ;
Meer, P .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (05) :603-619
[3]  
FUKUNAGA K, 1975, IEEE T INFORM THEORY, V21, P32, DOI 10.1109/TIT.1975.1055330
[4]  
Kailath T., 1999, IEEE T COMM TECHNOLO, V15, P253
[5]   Distinctive image features from scale-invariant keypoints [J].
Lowe, DG .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 60 (02) :91-110