遮挡情况下目标跟踪算法综述

目标跟踪是机器视觉的核心问题之一。由于被跟踪目标本身特征的多样性，所处环境的复杂性，使得目标跟踪成为一个极富挑战性的课题。特别是跟踪过程中出现的遮挡问题，一直是目标跟踪中的难点。如何有效处理遮挡，尤其是严重遮挡和全部遮挡，成为限制目标跟踪算法鲁棒性的关键因素。本文对国内外现有的遮挡情况下的目标跟踪算法进行了总结和分类，阐述了各种算法的基本思想，简要介绍了其代表性的算法，指出了算法的适用场合，分析了算法的优缺点。文章最后对遮挡情况下的目标跟踪做了必要的讨论。

Review of tracking algorithms under occlusions

Object tracking is a crucial subject in computer vision. Due to the variety of the target feature and the complexity of the background, target tracking has been a challenging subject all the time. Especially the tracking under occlusions, is one of the difficulties. How to deal with tracking under occlusion effectively, especially tracking under severely occlusion and totally occlusion, becomes the crucial restrictive factor to the robustness of tracking algorithm. This paper summarizes and classifies the main algorithms of tracking under occlusions home and abroad, expounds the basic ideas of these algorithms, introduces briefly the representative algorithms, analyses the advantages and disadvantages of these algorithms, and the situation that the algorithms fit. At last, necessary discussion is given about tracking under occlusions.