Cargando…

Remote Sensing Image Dataset Expansion Based on Generative Adversarial Networks with Modified Shuffle Attention

With the development of science and technology, neural networks, as an effective tool in image processing, play an important role in gradual remote-sensing image-processing. However, the training of neural networks requires a large sample database. Therefore, expanding datasets with limited samples...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Lu, Wang, Hongjun, Meng, Xianghao
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8309944/
https://www.ncbi.nlm.nih.gov/pubmed/34300604
http://dx.doi.org/10.3390/s21144867
_version_ 1783728642474377216
author Chen, Lu
Wang, Hongjun
Meng, Xianghao
author_facet Chen, Lu
Wang, Hongjun
Meng, Xianghao
author_sort Chen, Lu
collection PubMed
description With the development of science and technology, neural networks, as an effective tool in image processing, play an important role in gradual remote-sensing image-processing. However, the training of neural networks requires a large sample database. Therefore, expanding datasets with limited samples has gradually become a research hotspot. The emergence of the generative adversarial network (GAN) provides new ideas for data expansion. Traditional GANs either require a large number of input data, or lack detail in the pictures generated. In this paper, we modify a shuffle attention network and introduce it into GAN to generate higher quality pictures with limited inputs. In addition, we improved the existing resize method and proposed an equal stretch resize method to solve the problem of image distortion caused by different input sizes. In the experiment, we also embed the newly proposed coordinate attention (CA) module into the backbone network as a control test. Qualitative indexes and six quantitative evaluation indexes were used to evaluate the experimental results, which show that, compared with other GANs used for picture generation, the modified Shuffle Attention GAN proposed in this paper can generate more refined and high-quality diversified aircraft pictures with more detailed features of the object under limited datasets.
format Online
Article
Text
id pubmed-8309944
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83099442021-07-25 Remote Sensing Image Dataset Expansion Based on Generative Adversarial Networks with Modified Shuffle Attention Chen, Lu Wang, Hongjun Meng, Xianghao Sensors (Basel) Article With the development of science and technology, neural networks, as an effective tool in image processing, play an important role in gradual remote-sensing image-processing. However, the training of neural networks requires a large sample database. Therefore, expanding datasets with limited samples has gradually become a research hotspot. The emergence of the generative adversarial network (GAN) provides new ideas for data expansion. Traditional GANs either require a large number of input data, or lack detail in the pictures generated. In this paper, we modify a shuffle attention network and introduce it into GAN to generate higher quality pictures with limited inputs. In addition, we improved the existing resize method and proposed an equal stretch resize method to solve the problem of image distortion caused by different input sizes. In the experiment, we also embed the newly proposed coordinate attention (CA) module into the backbone network as a control test. Qualitative indexes and six quantitative evaluation indexes were used to evaluate the experimental results, which show that, compared with other GANs used for picture generation, the modified Shuffle Attention GAN proposed in this paper can generate more refined and high-quality diversified aircraft pictures with more detailed features of the object under limited datasets. MDPI 2021-07-16 /pmc/articles/PMC8309944/ /pubmed/34300604 http://dx.doi.org/10.3390/s21144867 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Chen, Lu
Wang, Hongjun
Meng, Xianghao
Remote Sensing Image Dataset Expansion Based on Generative Adversarial Networks with Modified Shuffle Attention
title Remote Sensing Image Dataset Expansion Based on Generative Adversarial Networks with Modified Shuffle Attention
title_full Remote Sensing Image Dataset Expansion Based on Generative Adversarial Networks with Modified Shuffle Attention
title_fullStr Remote Sensing Image Dataset Expansion Based on Generative Adversarial Networks with Modified Shuffle Attention
title_full_unstemmed Remote Sensing Image Dataset Expansion Based on Generative Adversarial Networks with Modified Shuffle Attention
title_short Remote Sensing Image Dataset Expansion Based on Generative Adversarial Networks with Modified Shuffle Attention
title_sort remote sensing image dataset expansion based on generative adversarial networks with modified shuffle attention
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8309944/
https://www.ncbi.nlm.nih.gov/pubmed/34300604
http://dx.doi.org/10.3390/s21144867
work_keys_str_mv AT chenlu remotesensingimagedatasetexpansionbasedongenerativeadversarialnetworkswithmodifiedshuffleattention
AT wanghongjun remotesensingimagedatasetexpansionbasedongenerativeadversarialnetworkswithmodifiedshuffleattention
AT mengxianghao remotesensingimagedatasetexpansionbasedongenerativeadversarialnetworkswithmodifiedshuffleattention