Abstract: To solve the problem of poor tracking performance when the moving target has a relatively large scale change, rotation, fast-moving or occlusion, an object tracking method combining Scale Invariant Feature Transform (SIFT) matching and Kalman filter with the Mean Shift algorithm was put forward. First, the Kalman filter was used to predict the movement state of the moving target and its estimated value was taken as the initial position of Mean Shift tracking. Then, when the measure coefficient for the similarity of the candidate target model and the initial target model was less than a certain threshold, SIFT feature matching was used to look for the possible position of the target and the new candidate target model was built there, meanwhile, the similarity with the initial target model was measured. Finally, by comparing the two matching coefficients, the position associated with a larger one was selected as the targets final position. The experimental results show that the average tracking error of this algorithm is decreased by about twenty percent than the tracking algorithms only combining the SIFT feature or Kalman filter with the Mean Shift alone.

Key words: object tracking, Scale Invariant Feature Transform (SIFT), Kalman filter, Mean Shift, scale space

摘要： 为解决目标跟踪中运动目标存在较大尺度变化、旋转、快速运动或遮挡时跟踪效果欠佳的问题，提出了一种将尺度不变特征变换(SIFT)特征匹配和Kalman滤波与Mean Shift结合的运动目标跟踪方法。首先，利用Kalman滤波估计目标运动状态，将其估计值作为Mean Shift跟踪的初始位置；然后，当候选目标模型和初始目标模型的相似性测度系数小于某一阈值时，启用SIFT特征匹配寻找目标可能位置，并在该位置处建立新的候选目标模型，同时进行相似性测度；最后，比较两者所得匹配系数，取其中较大者对应的位置作为目标的最终位置。实验结果表明，该算法的跟踪平均误差较单独将Kalman滤波或SIFT特征与Mean Shift结合的跟踪算法减小了约20%。

关键词: 目标跟踪, 尺度不变特征变换算法, Kalman滤波, Mean Shift, 尺度空间