Tracking more than 100 arbitrary objects at 25 FPS through deep learning

作者：

Highlights：

• A real-time multiple visual object tracker (MVOT) for motion estimation is proposed.

• Design of the first RoI operator able to work with backbones without padding.

• Definition of a novel pairwise cross-correlation operator for identity matching.

• Quality of our method is superior to is predecessor but with a 10-fold speedup.

摘要

•A real-time multiple visual object tracker (MVOT) for motion estimation is proposed.•Design of the first RoI operator able to work with backbones without padding.•Definition of a novel pairwise cross-correlation operator for identity matching.•Quality of our method is superior to is predecessor but with a 10-fold speedup.

论文关键词：Multiple visual object tracking,Motion estimation,Deep learning,Siamese networks

论文评审过程：Received 23 March 2021, Revised 8 June 2021, Accepted 24 July 2021, Available online 25 July 2021, Version of Record 3 August 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108205