本文在在尺度不变特征变换(Scale invariant feature transform,SIFT)特征匹配算法的基础上, 提出了一种基于累积特征的多目标的跟踪算法, 通过对目标的SIFT特征进行实时更新来去除由噪声(或形变)带来的\过时"特征信息, 保证了特征的稳定, 提高了匹配准确度. 实验结果表明, 本算法能够有效处理目标由于旋转、形变而导致跟踪性能下降甚至跟踪目标丢失的问题, 同时对跟踪过程中多目标的关联, 也具有较好的鲁棒性.-In this paper, the Scale Invariant Feature Transform (Scale invariant feature transform, SIFT) feature matching algorithm is proposed based on a feature based on the cumulative multi-target tracking algorithm, the target SIFT features real-time updates to remove the noise (or deformation) to bring \ outdated " characteristic information to ensure the characteristics of stability, improved matching accuracy. Experimental results show that the algorithm can handle the target due to the rotation, deformation and the resulting tracking performance target tracking problem of missing or , while the multi-target tracking process association, but also has better robustness.