中文摘要：

目标跟踪一直是计算机视觉领域研究的热点和难点，受自然场景中复杂干扰因素影响，现有方法的速度和精度尚待改善。首先对基于颜色属性的目标跟踪算法进行改进，使之更为鲁棒且速度达到实时；接下来，针对被跟踪目标发生遮挡时，采用基于颜色属性的跟踪算法导致错误累积进而产生漂移甚至跟踪失败的问题，引入运算量较大但对遮挡有较强抵抗能力的稀疏协作表观模型。为了同时保证算法的速度和准确性，构建了一套基于跟踪结果置信度评价的策略选择机制，将两种算法有机整合。在多个公开数据集下的对比实验显示，与现有跟踪算法相比，该方法在跟踪效果和速度上具有较显著优势，并在目标存在严重遮挡、光照变化、运动模糊等情况时，均可以取得较好的跟踪效果。

英文摘要：

Target tracking has always been one of the hot and difficult topics in computer vision. Due to the influences of complicated interference factors in natural scenes, the speed and accuracy of the existing target tracking methods are still to be im- proved. Firstly, this paper enhanced the color attribution based target tracking algorithm and made it be robust and real-time. Next, it introduced sparse collaborative appearance model to deal with the problem of error accumulation which caused drifting or even tracking failure when the object was occluded. In order to achieve fast and accurate tacking, it proposed an adaptive strategy selection mechanism to integrate the two algorithms through confidence evaluation of the tracking results. Experimental results on multiple public datasets show that, compared with the existing object tracking algorithms,the proposed method is accurate and fast. It performs well in regard of serious occlusion,illumination variation and motion blur.