An adaptive background model for CAMSHIFT tracking with a moving camera

被引:0
作者
Stolkin, R. [1 ]
Florescu, I. [2 ]
Kamberov, G. [3 ]
机构
[1] Stevens Inst Technol, Ctr Maritime Syst, Hoboken, NJ 07030 USA
[2] Stevens Inst Technol, Dept Math Sci, Hoboken, NJ 07030 USA
[3] Stevens Inst Technol, Dept Comp Sci, Hoboken, NJ 07030 USA
来源
PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON ADVANCES IN PATTERN RECOGNITION | 2007年
关键词
CAMSHIFT; mean shift; ABCshift; tracking; adaptive; background model; robot vision;
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
Continuously Adaptive Mean shift (CAMSHIFT) is a popular algorithm for visual tracking, providing speed and robustness with minimal training and computational cost. While it performs well with a fixed camera and static background scene, it can fail rapidly when the camera moves or the background changes since it relies on static models of both the background and the tracked object. Furthermore it is unable to track objects passing in front of backgrounds with which they share significant colours. We describe a new algorithm, the Adaptive Background CAMSHIFT (ABCshift), which addresses both of these problems by using a background model which can be continuously relearned for every frame with minimal additional computational expense. Further, we show how adaptive background relearning can occasionally lead to a particular mode of instability which we resolve by comparing background and tracked object distributions using a metric based on the Bhattacharyya coefficient.
引用
收藏
页码:147 / +
页数:3
相关论文
共 10 条
[1]  
ALLEN JG, 2004, ACM INT C P SERIES, V100
[2]  
Bhattacharyya A., 1943, B CALCUTTA MATH SOC, V35, P99, DOI DOI 10.1038/157869B0
[3]   Gene placement [J].
Bradley, D .
PHARMACEUTICAL SCIENCE & TECHNOLOGY TODAY, 1998, 1 (01) :2-2
[4]  
Bradski G.R., 1998, P IEEE WORKSH APPL C, P214
[5]   Kernel-based object tracking [J].
Comaniciu, D ;
Ramesh, V ;
Meer, P .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2003, 25 (05) :564-577
[6]   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
[7]   AN INVARIANT FORM FOR THE PRIOR PROBABILITY IN ESTIMATION PROBLEMS [J].
JEFFREYS, H .
PROCEEDINGS OF THE ROYAL SOCIETY OF LONDON SERIES A-MATHEMATICAL AND PHYSICAL SCIENCES, 1946, 186 (1007) :453-461
[8]  
LIU N, 2001, IVCNZ 2001
[9]  
NUMMIARO LVG, 2002, LECT NOTES COMPUTER, V2449
[10]  
PEREZ P, 2002, LECT NOTES COMPUTER, V2350