A framework of tracking by multi-trackers with multi-features in a hybrid cascade way

作者：

Highlights：

• Variant Bayesian based general framework fuses multi-trackers and multi-features.

• Two novel candidate selection strategies consider both intra and inter similarities.

• Tracklet prediction method proposed to handle the inconsistency of decision vectors.

• Correlation based update strategy is proposed to update template and multi-trackers.

摘要

•Variant Bayesian based general framework fuses multi-trackers and multi-features.•Two novel candidate selection strategies consider both intra and inter similarities.•Tracklet prediction method proposed to handle the inconsistency of decision vectors.•Correlation based update strategy is proposed to update template and multi-trackers.

论文关键词：Visual tracking,Multi-trackers and multi-features,Weighted voting strategy,PageRank,Probabilistic graphical model,Decision vector

论文评审过程：Received 30 January 2019, Revised 4 July 2019, Accepted 4 July 2019, Available online 10 July 2019, Version of Record 30 July 2019.

论文官网地址：https://doi.org/10.1016/j.image.2019.07.005