Super-resolution reconstruction of variable length infrared image sequences based on convolutional neural networks and pixel shuffling

Shijing Ji; Kun Gao; Kunxin Ke; Zibo Hu; Yanjun Huang; Yutong Liu; Pengyu Wang

doi:10.1117/12.3030372

3 June 2024 Super-resolution reconstruction of variable length infrared image sequences based on convolutional neural networks and pixel shuffling

Shijing Ji, Kun Gao, Kunxin Ke, Zibo Hu, Yanjun Huang, Yutong Liu, Pengyu Wang

Author Affiliations +

Proceedings Volume 13182, 2024 International Conference on Optoelectronic Information and Optical Engineering (OIOE 2024); 1318208 (2024) https://doi.org/10.1117/12.3030372
Event: 2024 International Conference on Optoelectronic Information and Optical Engineering (OIOE 2024), 2024, Kunming, China

Abstract

Infrared image super-resolution reconstruction technology can improve image resolution without changing the hardware of the imaging system, and has high cost-effectiveness. In this paper, a super-resolution reconstruction method based on convolutional neural network and pixel shuffle is proposed for the variable length infrared image sequences. Global residual learning and local residual block are introduced to accelerate the convergence speed of the network. Non-local residual block, progressive fusion residual blocks and pixel shuffle module are used to learn the long-distance time information and rich spatial information of infrared low-resolution image sequences. In addition to the fidelity evaluation indexes commonly used in current representative super-resolution reconstruction methods, we also introduce visual perception and image sharpness evaluation functions for perceptual evaluation. The network in this paper is trained and tested on real-world multi-frame infrared images. The experimental results show that the proposed method has advantages in obtaining better perception quality.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Shijing Ji, Kun Gao, Kunxin Ke, Zibo Hu, Yanjun Huang, Yutong Liu, and Pengyu Wang "Super-resolution reconstruction of variable length infrared image sequences based on convolutional neural networks and pixel shuffling", Proc. SPIE 13182, 2024 International Conference on Optoelectronic Information and Optical Engineering (OIOE 2024), 1318208 (3 June 2024); https://doi.org/10.1117/12.3030372

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image restoration

Infrared imaging

Infrared radiation

Super resolution

Image fusion

Feature extraction

Convolution

Show All Keywords

Keywords/Phrases

Search In:

Publication Years