Super-resolution of large field of view infrared image based on convolutional sparse auto-encoder

Yu-dan Chen; Wen-gang Hu; Jie Liu; Jian-ling Yin

doi:10.1117/12.2665988

4 April 2023 Super-resolution of large field of view infrared image based on convolutional sparse auto-encoder

Yu-dan Chen, Wen-gang Hu, Jie Liu, Jian-ling Yin

Proceedings Volume 12617, Ninth Symposium on Novel Photoelectronic Detection Technology and Applications; 126173G (2023) https://doi.org/10.1117/12.2665988
Event: 9th Symposium on Novel Photoelectronic Detection Technology and Applications (NDTA 2022), 2022, Hefei, China

Abstract

Based on the auto-encoder, shallow and deep auto-encoders with residual concept are constructed. The effects of different depth auto-encoders on large-field of view infrared image reconstruction are discussed under four conditions: no sparse constraint, regularization constraint, KL divergence sparse constraint and both constraints. From the reconstructed image quality and index parameters, it can be concluded that with the increase of the auto-encoder depth, sparse constraints have a greater impact on the reconstruction effect of the network.

Citation Download Citation

Yu-dan Chen, Wen-gang Hu, Jie Liu, and Jian-ling Yin "Super-resolution of large field of view infrared image based on convolutional sparse auto-encoder", Proc. SPIE 12617, Ninth Symposium on Novel Photoelectronic Detection Technology and Applications, 126173G (4 April 2023); https://doi.org/10.1117/12.2665988

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available