A target tracking algorithm via On-line Boosting and particle filter

摘要

The on-line boosting algorithm regards tracking problem as a binary classification problem. It is adaptive to the appearance changes of the object because of its capability of on-line learning. With its on-line learning ability, it is adaptive to different appearance of objects. However, this method can lead to tracking failure due to accumulation of error features when the object is seriously or completely obscured. This paper proposed a new tracking algorithm by combining particle filter and on-line boosting to overcome the shortcomings of traditional on-line boosting algorithm. The confidence of the particles' region is set to be the weight of the particles and the object tracking situations under serious occlusions was solved. The proposed algorithm was tested with variant video sequences and the results show that the algorithm can track the object accurately under serious occlusions in less time.