An Activated Region Analysis Based IR Target Tracking Algorithm

To eliminate the clutter interference in IR videos,a new activated region analysis based target tracking algorithm is proposed in this paper.The algorithm is in the framework of particle filter and uses a covariance operator to extract the apparent features.Firstly,an activated region is established to determine the effective region and reduce the computational cost.Secondly,updating strategies are made with scenario analysis to avoid the adverse effects of interference on the template.Finally,the spatial information is fused with the apparent features to improve the tracking accuracy with an adaptive tracking window.In addition,a new normalized error evaluation criterion is proposed with improvement on the evaluation.Experimental results show that the proposed algorithm is robust and effective under heavy clutter environments.