Multiple instance deep learning for weakly-supervised visual object tracking

作者：

Highlights：

• The proposed method can cope with variant number of lanes as well as lane changes.

• In addition, our method is robust to different weather condition and can be achieved in real time.

摘要

•The proposed method can cope with variant number of lanes as well as lane changes.•In addition, our method is robust to different weather condition and can be achieved in real time.

论文关键词：Multiple instance learning (MIL),Weakly-supervised,Object tracking,Multi-view feature learning,Gaussian mixture model

论文评审过程：Received 2 May 2019, Revised 2 February 2020, Accepted 5 February 2020, Available online 8 February 2020, Version of Record 18 March 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.115807