Robust video object tracking via Bayesian model averaging-based feature fusion
Robust video object tracking via Bayesian model averaging-based feature fusion
复制标题
通过基于贝叶斯模型平均的特征融合进行鲁棒视频对象跟踪
DOI:
10.1117/1.oe.55.8.083102
复制
发表时间:
2016-04
影响因子:
1.3
通讯作者:
Liu, Bin
中科院分区:
文献类型:
--
作者:
Dai, Yi;Liu, Bin
Abstract. We are concerned with tracking an object of interest in a video stream. We propose an algorithm that is robust against occlusion, the presence of confusing colors, abrupt changes in the object features and changes in scale. We develop the algorithm within a Bayesian modeling framework. The state-space model is used for capturing the temporal correlation in the sequence of frame images by modeling the underlying dynamics of the tracking system. The Bayesian model averaging (BMA) strategy is proposed for fusing multiclue information in the observations. Any number of object features is allowed to be involved in the proposed framework. Every feature represents one source of information to be fused and is associated with an observation model. The state inference is performed by employing the particle filter methods. In comparison with the related approaches, the BMA-based tracker is shown to have robustness, expressivity, and comprehensibility.
登录
查看更多内容
DOI:
10.1088/1742-6596/656/1/012006
发表时间:
2015-12
期刊:
Journal of Physics: Conference Series
影响因子:
--
作者:
Marc Tinguely;O. Matar;V. Garbin
通讯作者:
Marc Tinguely;O. Matar;V. Garbin
影响因子:
2.2
作者:
Doucet, A;Godsill, S;Andrieu, C
通讯作者:
Andrieu, C
DOI:
10.1007/978-1-4757-3437-9
发表时间:
2001
期刊:
--
影响因子:
--
作者:
A. Doucet;Nando de Freitas;N. Gordon
通讯作者:
A. Doucet;Nando de Freitas;N. Gordon
影响因子:
6.3
作者:
Brendan A. Wintle;M. McCarthy;C. Volinsky;R. Kavanagh
通讯作者:
Brendan A. Wintle;M. McCarthy;C. Volinsky;R. Kavanagh
DOI:
10.1109/icnc.2010.5584200
发表时间:
2010-09
期刊:
2010 Sixth International Conference on Natural Computation
影响因子:
--
作者:
Jianhua Ye;Zhengguang Liu;Jun Zhang
通讯作者:
Jianhua Ye;Zhengguang Liu;Jun Zhang