针对目标跟踪中的目标尺度变化、遮挡、光照变化、相似目标混淆等问题，本文提出多特征融合的协同相关跟踪算法。首先，本文用多种特征构建目标外观模型，提高目标模型的鲁棒性，增强跟踪的抗形变能力和抗光照变化能力。然后，利用定点优化策略，解决多模板滤波优化问题，获得最佳滤波参数，通过多模板相关滤波算法估计目标位置，利用改进的尺度池方法解决目标尺度变化问题。最后，利用目标置信度判别跟踪目标是否发生遮挡，当目标发生遮挡时，利用CUR滤波模块重新检测目标，解决遮挡情况下跟踪任务。本文利用OTB-2013数据集中的方法测试本文算法，实验表明本文算法的整体成功率和精确度为0.622和0.830，本文算法在目标发生尺度变化、遮挡、光照变化、相似目标混淆等问题情况下，能准确、可靠地跟踪目标，具有一定研究价值。

In order to solve the problem of target scale change, occlusion, illumination change, similar target confusion in target tracking, the paper proposes multi-template collaborative correlation tracking by multi-feature fusion algorithm. First, this paper constructs the target appearance model with various features, improves the robustness of the target model, and enhances the ability of anti deformation and the ability of light variation. Then, the fixed-point optimization strategy is used to solve the multi template filtering optimization problem, the optimal filter parameters are obtained and the target position is estimated by the multi-template correlation filtering algorithm. Target scale change is solved by the improved scale pool method. Finally, the target confidence is used to judge whether the tracking target is occluded. When the target is occluded, the CUR filter module is used to re-detect the target. The tracking task in the occlusion case is resolved. In this paper, we use the method of OTB-2013 dataset to test the algorithm. Experimental results show that the overall success rate and accuracy of the algorithm are 0.622 and 0.830.Under the situation of occlusion, scale change, similar target interfere and illumination variation, the algorithm can accurately and reliably track the target which has certain research value.