DSiamMFT: An RGB-T fusion tracking method via dynamic Siamese networks using multi-layer feature fusion

作者：

Highlights：

• An RGB-T fusion tracking method based on dynamic Siamese Networks is proposed.

• Two Siamese networks are used to process visible and infrared images respectively.

• Multi-layer features are utilized to obtain better results.

• The proposed method strikes a good balance between precision and speed.

摘要

•An RGB-T fusion tracking method based on dynamic Siamese Networks is proposed.•Two Siamese networks are used to process visible and infrared images respectively.•Multi-layer features are utilized to obtain better results.•The proposed method strikes a good balance between precision and speed.

论文关键词：Object tracking,RGB-T fusion tracking,Dynamic Siamese networks,Deep learning,Image fusion

论文评审过程：Received 15 April 2019, Revised 9 November 2019, Accepted 17 December 2019, Available online 5 February 2020, Version of Record 3 March 2020.

论文官网地址：https://doi.org/10.1016/j.image.2019.115756