[1]王安,方贤勇. 基于显著前景块模型的贝叶斯目标跟踪[J].计算机技术与发展,2016,26(11):25-30.
　WANG An,FANG Xian-yong. Bayesian Object Tracking Based on Salient Foreground Patch Model[J].,2016,26(11):25-30.
点击复制

 基于显著前景块模型的贝叶斯目标跟踪()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
26
期数:
2016年11期
页码:
25-30
栏目:
智能、算法、系统工程
出版日期:
2016-11-10

文章信息/Info

Title:
 Bayesian Object Tracking Based on Salient Foreground Patch Model
文章编号:
1673-629X（2016)11-0025-06
作者:
 王安; 方贤勇
 安徽大学 计算机科学与技术学院
Author(s):
 WANG An ; FANG Xian-yong
关键词:
目标跟踪; 外观模型; 显著前景模型; 模板更新
Keywords:
 ; object tracking; appearance model; salient foreground model; template updating
分类号:
TP301
文献标志码:
A
摘要:
 光照变化、背景混淆、形态变化等仍然是视频目标跟踪中具有挑战性的问题，有效、自适应的外观模型是基于外观模型的目标跟踪方法用以克服这些问题的关键。针对此问题，提出了一种基于显著前景块模型的在线贝叶斯目标跟踪方法。首先，提出一种精确显著的前景提取方法，建立基于块的显著前景块模型，可以有效抑制非前景因素的影响。同时，提出一种与显著前景块模型适应的模板更新方法，有效适应目标前景的变化。然后，结合多层背景块模型，获得有效、自适应的基于块的外观模型。最后，建立基于贝叶斯框架的目标跟踪方法。经过多组具有挑战性的视频序列测试，该跟踪方法可以有效抑制光照变化、背景混淆及形态变化等问题，具有较好的自适应性。通过对比实验，结果表明该跟踪方法较现有常见的方法有较强的鲁棒性和较好的精确性。
Abstract:
 Illumination variation,background clutter and deformation are still challenging problems in visual object tracking. Efficient self-adapting appearance model can be one of the keys to overcome these limits. In view of these problems,a new online Bayesian tracking method is put forward based on salient foreground patch model. First,a new method is introduced to extract an accurate and salient fore-ground for constructing a patch-based salient foreground model. The foreground patch model can effectively suppress the affections of non-foreground factors. A template update method is also presented to adapt the changes of foreground. Then,an efficient and self-adap-ting patch-based appearance model incorporating the patch-based multiple background patch model is obtained. Finally,the objects can be tracked based on the Bayesian framework. Experiment on more groups video sequence test with challenge demonstrates that the pro-posed tracking algorithm can effectively suppress the illumination variation,background clutter and deformation and outperform conven-tional tracking algorithms in robustness and accuracy.

相似文献/References:

[1]刘翔 吴谨 祝愿博 康晓晶.基于视频序列的目标检测与跟踪技术研究[J].计算机技术与发展,2009,(11):179.
　LIU Xiang,WU Jin,ZHU Yuan-bo,et al.A Study of Object Detecting and Tracking Based on Video Sequences[J].,2009,(11):179.
[2]雷云 王夏黎 孙华.基于视频的交通目标跟踪方法研究[J].计算机技术与发展,2010,(07):44.
　LEI Yun,WANG Xia-li,SUN Hua.The Research about Transport Target Tracking Based on Video[J].,2010,(11):44.
[3]谢之宇 蒋晓瑜 汪熙 裴闯.基于多线索融合的目标跟踪算法研究[J].计算机技术与发展,2011,(03):125.
　XIE Zhi-yu,JIANG Xiao-yu,WANG Xi,et al.A Target Tracking Algorithm Research Based on Multi-Cue Fusion[J].,2011,(11):125.
[4]尤天来 周海徽[].红外目标跟踪技术研究[J].计算机技术与发展,2011,(10):140.
　YOU Tian-lai,ZHOU Hai-hui.Research of Infrared Target Tracking Technology[J].,2011,(11):140.
[5]赵侃 漆德宁.基于UKF滤波的FDOA和TDOA联合定位跟踪算法[J].计算机技术与发展,2012,(05):127.
　ZHAO Kan,QI De-ning.A Tracking TDOA/FDOA Joint Location Algorithm Based on UKF[J].,2012,(11):127.
[6]姚放吾 许辰铭.基于目标质心的Meanshift跟踪算法[J].计算机技术与发展,2012,(06):104.
　YAO Fang-wu,XU Chen-ming.A Meanshift Tracking Algorithm Based on Centroid[J].,2012,(11):104.
[7]张璐,张国良,张维平,等.改进IMM算法在机器人目标跟踪中的应用[J].计算机技术与发展,2013,(02):149.
　ZHANG Lu,ZHANG Guo-liang,ZHANG Wei-ping,et al.Application of Improved IMM Algorithm in Robot Target Tracking[J].,2013,(11):149.
[8]吴佳家,高珏,李敏,等.基于均值漂移和卡尔曼滤波的跟踪算法研究[J].计算机技术与发展,2014,24(01):5.
　WU Jia-jia[,GAO Jue[],LI Min[],et al.Research on Target Tracking Algorithm Based on Mean Shift and Kalman Filter[J].,2014,24(11):5.
[9]郝杰,任静. 高超声速飞行器交互式多模型跟踪算法仿真[J].计算机技术与发展,2015,25(02):204.
　HAO Jie,REN Jing. Tracking Algorithm Simulation of Interactive Multiple Model for Hypersonic Flight Vehicle[J].,2015,25(11):204.
[10]高翔,朱婷婷,刘洋. 多摄像头系统的目标检测与跟踪方法研究[J].计算机技术与发展,2015,25(07):221.
　GAO Xiang,ZHU Ting-ting,LIU Yang. Research of Target Detection and Tracking Method for Multi-camera System[J].,2015,25(11):221.

更新日期/Last Update: 2016-12-09