THE IMPROVEMENT AND REALIZATION OF A KIND OF MEAN-SHIFT TRACKING ALGORITHM

被引：0

作者：

Wang, Ming ^{[1
]}

机构：

[1] Ningbo Dahongying Univ, Ningbo 315175, Zhejiang, Peoples R China

来源：

INTERNATIONAL SYMPOSIUM ON COMPUTER SCIENCE & TECHNOLOGY, PROCEEDINGS | 2009年

关键词：

Mean-Shift; Object Tracking; Kernel Function Bandwidth; Object Model Update;

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

This paper puts forward an improved model of Mean-Shift tracking algorithm. Aiming at the problem of unchanged kernel function bandwidth in the tracking process, it puts forward the improved Camshift algorithm and discusses the object model updating algorithm based on Kalman filter. The experiment shows that the Mean-Shift tracking algorithm by using LabVIEW can track a single object and multi-objects in outdoor scenes and can be applied in video monitoring.

引用

页码：255 / 257

页数：3

共 5 条

[1] MEAN SHIFT, MODE SEEKING, AND CLUSTERING
CHENG, YZ
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1995, 17 (08) : 790 - 799
[2] Kernel-based object tracking
Comaniciu, D
Ramesh, V
Meer, P
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2003, 25 (05) : 564 - 577
[3] Comaniciu D., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P1197, DOI 10.1109/ICCV.1999.790416
[4] FUKUNAGA K, 1975, IEEE T INFORM THEORY, V21, P32, DOI 10.1109/TIT.1975.1055330
[5] Nguyen HT, 2001, EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL I, PROCEEDINGS, P678, DOI 10.1109/ICCV.2001.937587

← 1 →