loading page

IETAFusion: An Illumination Enhancement and Target-aware Infrared and Visible Image Fusion Network for Security System of Smart City
  • +1
  • Shuang Guo,
  • Kun Wu,
  • Seunggil Jeon,
  • Xiaomin Yang
Shuang Guo
Sichuan University College of Electronics and Information Engineering
Author Profile
Kun Wu
Sichuan University College of Electronics and Information Engineering
Author Profile
Seunggil Jeon
Samsung Electronics
Author Profile
Xiaomin Yang
Sichuan University College of Electronics and Information Engineering

Corresponding Author:arielyang@scu.edu.cn

Author Profile

Abstract

In the environmental security monitoring of smart cities, the infrared and visible image fusion method deployed on intelligent systems based on cloud and fog computing plays an vital role in providing enhanced images for target detection systems. However, the fusion quality can be significantly influenced by the illumination of the monitoring scenario in visible images. Therefore, conventional methods typically suffer a severe performance drop under the condition of insufficient illumination. To tackle this issue, we propose an illumination enhancement and target-aware fusion method (IETAFusion) based on artificial intelligence, which breaks the boundaries between the task of illumination enhancement and image fusion and provide a fusion result with better visual perception in nighttime scene. Specifically, we use a light-weight contrast enhancement module (CEM) restore the brightness of the visble image. Moreover, a Swin Transformer-based backbone network (STBNet) is utilized to facilitate information exchangement between the source images and enhance the capabilities of target awareness. Finally, the fused images are reconstructed by the contrast-texture retention module (CTRM) and reconstructor. The extensive experiments indicates that the proposed approach achieves improved performance both in human perception and quantitative analysis compared with the state-of-the-art (SOTA) methods.
13 Oct 2023Submission Checks Completed
13 Oct 2023Assigned to Editor
25 Oct 2023Reviewer(s) Assigned
18 Nov 2023Review(s) Completed, Editorial Evaluation Pending
19 Nov 2023Editorial Decision: Revise Major