基于特征显著性的均值漂移鲁棒目标跟踪附视频

被引:4
作者
陈东岳
陈宗文
机构
[1] 东北大学信息科学与工程学院
关键词
目标跟踪; 均值漂移; 特征显著性; Gabor小波; 稀疏编码;
D O I
10.16183/j.cnki.jsjtu.2013.11.029
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
在均值漂移算法框架下,提出基于目标显著性的特征融合与在线模板更新策略,实现复杂动态环境下的鲁棒跟踪.通过目标区域与背景区域的特征对比定义了特征显著性测度.提出了基于特征显著性的色彩空间选择以及基于Gabor小波稀疏编码的纹理特征提取算法.通过特征显著性加权实现参考直方图模板的初始化,并在此基础上针对遮挡现象与目标自身形变的区别设计了在线模板更新策略.实验结果表明,本文方法与其他跟踪算法相比具有较强的鲁棒性和较高的准确性.
引用
收藏
页码:1807 / 1812
页数:6
相关论文
共 19 条
[1]  
Real-time tracking of non-rigid objects using mean shift. Comaniciu D,Ramesh V,Meer P. Proceedings of the International Conference on Computer Vision and Pattern Recognition . 2000
[2]  
Two-stage object tracking method based on kernel and active contour. Chen, Qiang,Sun, Quan-Sen,Heng, Pheng Ann,Xia, De-Shen. IEEE Transactions on Circuits and Systems for Video Technology . 2010
[3]  
Contour-based motion estimation and object tracking for real-time applications. TECHMER A. Proceedings of International Conference on Image Processing . 2001
[4]  
Robust visual tracking using L1minimization. Mei X,Ling H. IEEE 12th InternationalConference on Computer Vision . 2009
[5]  
"Better Proposal Distributions:Object Tracking Using Unscented Particle Filter". Rui Yong,Chen Yunqiang. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition . 2001
[6]  
Visual tracking decomposition. Kwon J,Lee K M. Proceedingsof the IEEE Conference on Computer Vision and PatternRecognition . 2010
[7]   应用自适应多测量融合粒子滤波的视场跟踪 [J].
田隽 ;
钱建生 ;
李世银 ;
厉丹 .
光学精密工程, 2010, 18 (10) :2254-2261
[8]  
Mean Shift tracking with multiple reference color histograms[J] . Ido Leichter,Michael Lindenbaum,Ehud Rivlin. &nbspComputer Vision and Image Understanding . 2009 (3)
[9]  
Gabor texture representation method for face recognition using the Gamma and generalized Gaussian models[J] . Lei Yu,Zhongshi He,Qi Cao. &nbspImage and Vision Computing . 2009 (1)
[10]  
SURFTrac: Efficient Trackingand Continuous Object Recognition using Local Feature Descriptors. Duy-Nguyen Ta,Wie-Chao Chen,Natasha Gelfand. IEEECoomputer Society Conference on Computer Vision and Pattern Recognition . 2009