融合局部加权余弦与稀疏表示的目标跟踪算法

An Object Tracking Algorithm Fused by Weighted Local Cosine and Sparse Representation

针对目标跟踪算法的鲁棒性难题,在粒子滤波框架下提出基于联合模型的目标跟踪算法。首先,由局部加权余弦相似对目标模板和候选目标进行匹配,其中的局部加权算法增加了未受遮挡、形变等影响的候选目标的权重;其次,通过对目标区域局部图像块稀疏编码来表示目标观测模型,其中字典不进行更新,重建误差的构建考虑了局部图像块之间的空间布局;最后,利用最大后验概率估计目标状态。联合模型将目标的当前状态和原始状态都考虑在内,提高了观测模型的可靠性。实验结果表明,该算法具有较强的鲁棒性。

Focusing on the robustness problem of target tracking algorithm,this paper proposes a target tracking method based on joint model in the particle filter framework. Firstly,the target template and the candidate targets are matched by the weighted local cosine similarity. The proposed local weighted algo-rithm increases the weights of the candidate targets which are not affected by occlusion, deformation, etc. Secondly,the target observation model makes use of the local information of the target by sparse coding and the dictionary is not updated. The construction of the reconstruction error considers the spatial layout be-tween the local image patches. Finally,the maximum posterior probability is used to estimate the target state. The joint model considers the current state and the original state of the target so as to improve the re-liability of the observation model. The experimental results demonstrate the robustness of the algorithm.