Non-linear and selective fusion of cross-modal images

作者：

Highlights：

• We explore the relationship between the characteristics of human visual perception system and the task of cross-modal image fusion for the first time.

• We stimulate the non linear and selective characteristics of human visual perception system and propose a non linear and selective cross-modal image fusion method.

• We have done a lot of experiments on FLIR, TNO Gun, and VIFB datasets. The experimental results show that our method is superior to other image fusion methods in complex lighting environment.

摘要

•We explore the relationship between the characteristics of human visual perception system and the task of cross-modal image fusion for the first time.•We stimulate the non linear and selective characteristics of human visual perception system and propose a non linear and selective cross-modal image fusion method.•We have done a lot of experiments on FLIR, TNO Gun, and VIFB datasets. The experimental results show that our method is superior to other image fusion methods in complex lighting environment.

论文关键词：Image fusion,Deep learning,Non-linear characteristic,Feature selection characteristic

论文评审过程：Received 8 September 2020, Revised 16 April 2021, Accepted 11 May 2021, Available online 21 May 2021, Version of Record 4 June 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108042