Dynamic multi-level appearance models and adaptive clustered decision trees for single target tracking
作者：
Highlights：
• A robust tracking algorithm for tracking arbitrary objects in challenging video sequences.
• An adaptive clustered decision tree approach which dynamically selects the minimum combination of features to represent target parts.
• This adaptive clustered decision tree is utilized both to enable robust matching at the part level and to select the new parts for learning.
摘要
•A robust tracking algorithm for tracking arbitrary objects in challenging video sequences.•An adaptive clustered decision tree approach which dynamically selects the minimum combination of features to represent target parts.•This adaptive clustered decision tree is utilized both to enable robust matching at the part level and to select the new parts for learning.
论文关键词：Single target tracking,Adaptive clustered decision trees,Multi-level appearance models
论文评审过程：Received 9 October 2016, Revised 14 February 2017, Accepted 4 April 2017, Available online 14 April 2017, Version of Record 25 April 2017.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.04.001
