Fusion of Images of Different Spectra Based on Generative Adversarial Networks
- Autores: Vizil’ter Y.1, Vygolov O.1, Komarov D.1, Lebedev M.1
-
Afiliações:
- State Scientific Research Institute of Aviation Systems (GosNIIAS)
- Edição: Volume 58, Nº 3 (2019)
- Páginas: 441-453
- Seção: Pattern Recognition and Image Processing
- URL: https://journals.rcsi.science/1064-2307/article/view/220389
- DOI: https://doi.org/10.1134/S1064230719030201
- ID: 220389
Citar
Resumo
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.
Sobre autores
Yu. Vizil’ter
State Scientific Research Institute of Aviation Systems (GosNIIAS)
Email: MLebedev@gosniias.ru
Rússia, Moscow, 125319
O. Vygolov
State Scientific Research Institute of Aviation Systems (GosNIIAS)
Email: MLebedev@gosniias.ru
Rússia, Moscow, 125319
D. Komarov
State Scientific Research Institute of Aviation Systems (GosNIIAS)
Email: MLebedev@gosniias.ru
Rússia, Moscow, 125319
M. Lebedev
State Scientific Research Institute of Aviation Systems (GosNIIAS)
Autor responsável pela correspondência
Email: MLebedev@gosniias.ru
Rússia, Moscow, 125319
![](/img/style/loading.gif)