An Unsupervised Deep Neural Network for Image Fusion

Authors

Peipei Zhou, School of Electrical and Information Engineering, Changzhou Institute of Technology, Changzhou 213032, China;Follow
Xinglin Hou, School of Electrical and Information Engineering, Changzhou Institute of Technology, Changzhou 213032, China;Follow

Abstract

Abstract: Due to the low dynamic range of camera, can not be expressed in the different region of the high dynamic scene a single-exposure image. An unsupervised depth neural network is constructed to fuse the multi-exposure images into a high dynamic image. Based on the VGG-Net, encoding and decoding sub-networks are designed. Guided by the structural similarity of the images before and after fusion, a loss function suitable for image fusion is designed by introducing the weight factors based on the local image information, and the valid information of the different input images is given consideration. Compared with the other methods, the subjective visual experience and objective quantitative indicators of the fused images are improved significantly.

Recommended Citation

Zhou, Peipei and Hou, Xinglin (2022) "An Unsupervised Deep Neural Network for Image Fusion," Journal of System Simulation: Vol. 34: Iss. 6, Article 9.
DOI: 10.16182/j.issn1004731x.joss.20-1062
Available at: https://dc-china-simulation.researchcommons.org/journal/vol34/iss6/9

First Page

1267

Revised Date

2021-04-16

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.20-1062

Last Page

1274

CLC

TP391.4

Recommended Citation

Peipei Zhou, Xinglin Hou. An Unsupervised Deep Neural Network for Image Fusion[J]. Journal of System Simulation, 2022, 34(6): 1267-1274.

Corresponding Author

Xinglin Hou,houxl@czu.cn

DOI

10.16182/j.issn1004731x.joss.20-1062