Enhancement of Dim Imaging Enlargement using Super-Resolution CNN

DOI

10.2991/aebmr.k.220405.093How to use a DOI?

Keywords

Deep-learning; super-resolution; convolutional neural network

Abstract

Dim images are an important branch of various images. Due to the limitations of equipment and technology, it is often impossible to obtain satisfactory results when shooting pictures and videos under night scenes with a limited budget. It is still a blue ocean to increase the resolution of the pictures or videos such as data recovery under night scene monitoring and real-time optimization when taking pictures with mobile phones. The existing method that can increase the resolution the most is SRCNN, but an ordinary SRCNN model is not optimized for the characteristics of dim pictures and runs slowly. Therefore, this paper attempt to introduce an optimized dim-srcnn model with a faster speed for a picture or a video that contains a large number of pure black areas, has fewer features, and the entire picture is dim.

Copyright

© 2022 The Authors. Published by Atlantis Press International B.V.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license.

Download article (PDF)

TY  - CONF
AU  - Ziwei Li
PY  - 2022
DA  - 2022/04/29
TI  - Enhancement of Dim Imaging Enlargement using Super-Resolution CNN
BT  - Proceedings of the 2022 7th International Conference on Social Sciences and Economic Development (ICSSED 2022)
PB  - Atlantis Press
SP  - 563
EP  - 568
SN  - 2352-5428
UR  - https://doi.org/10.2991/aebmr.k.220405.093
DO  - 10.2991/aebmr.k.220405.093
ID  - Li2022
ER  -