摘要
提出了一种基于局部稀疏表示模型的跟踪方法来有效解决跟踪过程中的目标遮挡问题.首先对目标进行分块,然后对每个块分别构造其稀疏字典,并通过衡量候选区域中每个块与目标模板对应块的相似度,获得每个块在目标图像中可能位置的置信图;再结合每个块置信图从而获得目标位置的最佳估计.实验结果表明,该方法与各种流行跟踪算法相比稳定可靠且具有良好的抗遮挡性,并对海上红外目标跟踪取得良好效果.实验结果验证了将稀疏表示应用在海上红外目标跟踪中的有效性及其良好的应用前景.
The sparse representation has been widely used in many areas. Part-based representation performs outstandingly by using the holistic templates representation to against occlusion. In this paper we propose a robust object tracking method using part based sparsity model for tracking an infrared object on the sea. In this model,one object is represented by image patches. ＂File candidates of these patches are sparsely represented in the space spanned by the patch templates and trivial templates. We use a part-based method that takes the spatial information of each patch into consideration with the vote maps of the multiple patches. Furthermore, the update scheme dynamically keeps the representativeness of the templates. Therefore,our tracker can effectively deal with the changes of ap- pearances and heavy occlusion. On the sequences of infrared object on the sea and public benchmarks sequences, the abundant results of experiments launched demonstrate that our proposed visual tracking method outperforms many existing state-of-the art algo- rithms.
出处
《厦门大学学报（自然科学版）》
CAS
CSCD
北大核心
2013年第3期343-348,共6页
Journal of Xiamen University：Natural Science
基金
国防基础科研计划项目
高等学校博士学科点专项科研基金(20110121110020)
国防科技重点实验室基金
关键词
局部模型
稀疏表示
目标跟踪
海上红外目标
part-based
sparsity representation
visual tracking
infrared object tracking
