Discriminative multi-task objects tracking with active feature selection and drift correction

作者：

Highlights：

• Learn the representation of all the particles with joint sparsity and discriminative multi-task learning.

• Active feature selection scheme adaptively chooses suitable number of discriminative features.

• Incorporate the initial information into the tracking framework to correct the tracking drift

摘要

•Learn the representation of all the particles with joint sparsity and discriminative multi-task learning.•Active feature selection scheme adaptively chooses suitable number of discriminative features.•Incorporate the initial information into the tracking framework to correct the tracking drift

论文关键词：Discriminative multi-task objects tracking,Active feature selection,Drift correction,Jointly sparsity

论文评审过程：Received 20 October 2013, Revised 16 June 2014, Accepted 19 June 2014, Available online 8 July 2014.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.06.015