摘要： 传统的相关匹配算法在背景比较简单的情况下可以较好地跟踪到目标，但实际获得的图像存在变形、噪声、遮挡等问题，并且也很难获得比较好的跟踪效果。针对上述问题，提出了一种修正的MCD相关匹配算法和多帧累积的模板更新策略，并对实际图像进行了仿真。实验结果表明，算法在图像存在变形、噪声、遮挡时也可以达到比较理想的跟踪效果。

关键词: 相关匹配, MCD, 多帧累积, 自适应模板修正

Abstract: Systems based on correlation-tracking can track objects based on 2-dimensional shape, however traditional correlation-tracking methods have difficulty in detecting an object when the object is transformed or partially obscured by clutter. This paper describes one of the main problems of image-based correlation tracking systems, and proposes a new solution of using modified MCD correlation matching and adaptive modal modification based on multiple frame cumulation. The system is tested on both real and simulated imagery which is found to be robust in the presence of obscuring clutter and transforming and be practical.

Key words: correlation match, MCD, multiple frame cumulation, adaptive modal modification

中图分类号: 

• TN911.73