Fusion of Images of Different Spectra Based on Generative Adversarial Networks

A method for fusing images of different spectra by using generative adversarial networks is proposed. An original architecture of a FusionNet neural network is developed based on pix2pix. It enables the synthesis of a complex (integrated) image that comprises the most informative fragments of differ...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of computer & systems sciences international Ročník 58; číslo 3; s. 441 - 453
Hlavní autoři: Vizil’ter, Yu. V., Vygolov, O. V., Komarov, D. V., Lebedev, M. A.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Moscow Pleiades Publishing 01.05.2019
Springer Nature B.V
Témata:
Computer vision
Control
Engineering
Generative adversarial networks
Image processing
Infrared imagery
Mechatronics
Neural networks
Pattern Recognition and Image Processing
Robotics
Spectra
Test sets
ISSN:1064-2307, 1555-6530
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:A method for fusing images of different spectra by using generative adversarial networks is proposed. An original architecture of a FusionNet neural network is developed based on pix2pix. It enables the synthesis of a complex (integrated) image that comprises the most informative fragments of different-spectra images, thus being more informative than any of these individual images. A technique for generating training and test sets, as well as the process of data augmentation, is described. The operation of the proposed image fusion method is demonstrated on some real-world infrared and visible images.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1064-2307
1555-6530
DOI:10.1134/S1064230719030201