Cargando…

An ENet Semantic Segmentation Method Combined with Attention Mechanism

Image semantic segmentation is one of the core tasks for computer vision. It is widely used in fields such as unmanned driving, medical image processing, geographic information systems, and intelligent robots. Aiming at the problem that the existing semantic segmentation algorithm ignores the differ...

Descripción completa

Detalles Bibliográficos
Autor principal: Bai, Wei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9977519/
https://www.ncbi.nlm.nih.gov/pubmed/36873381
http://dx.doi.org/10.1155/2023/6965259
_version_ 1784899309570883584
author Bai, Wei
author_facet Bai, Wei
author_sort Bai, Wei
collection PubMed
description Image semantic segmentation is one of the core tasks for computer vision. It is widely used in fields such as unmanned driving, medical image processing, geographic information systems, and intelligent robots. Aiming at the problem that the existing semantic segmentation algorithm ignores the different channel and location features of the feature map and the simple method when the feature map is fused, this paper designs a semantic segmentation algorithm that combines the attention mechanism. First, dilated convolution is used, and a smaller downsampling factor is used to maintain the resolution of the image and to obtain its detailed information. Secondly, the attention mechanism module is introduced to assign weights to different parts of the feature map, which reduces the accuracy loss. The design feature fusion module assigns weights to the feature maps of different receptive fields obtained by the two paths and merges them together to obtain the final segmentation result. Finally, through experiments, it was verified on the Camvid, Cityscapes, and PASCAL VOC2012 data sets. Mean intersection over union (MIoU) and mean pixel accuracy (MPA) are used as metrics. The method in this paper can make up for the loss of accuracy caused by downsampling while ensuring the receptive field and improving the resolution, which can better guide the model learning. And the proposed feature fusion module can better integrate the features of different receptive fields. Therefore, the proposed method can significantly improve the segmentation performance compared to the traditional method.
format Online
Article
Text
id pubmed-9977519
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Hindawi
record_format MEDLINE/PubMed
spelling pubmed-99775192023-03-02 An ENet Semantic Segmentation Method Combined with Attention Mechanism Bai, Wei Comput Intell Neurosci Research Article Image semantic segmentation is one of the core tasks for computer vision. It is widely used in fields such as unmanned driving, medical image processing, geographic information systems, and intelligent robots. Aiming at the problem that the existing semantic segmentation algorithm ignores the different channel and location features of the feature map and the simple method when the feature map is fused, this paper designs a semantic segmentation algorithm that combines the attention mechanism. First, dilated convolution is used, and a smaller downsampling factor is used to maintain the resolution of the image and to obtain its detailed information. Secondly, the attention mechanism module is introduced to assign weights to different parts of the feature map, which reduces the accuracy loss. The design feature fusion module assigns weights to the feature maps of different receptive fields obtained by the two paths and merges them together to obtain the final segmentation result. Finally, through experiments, it was verified on the Camvid, Cityscapes, and PASCAL VOC2012 data sets. Mean intersection over union (MIoU) and mean pixel accuracy (MPA) are used as metrics. The method in this paper can make up for the loss of accuracy caused by downsampling while ensuring the receptive field and improving the resolution, which can better guide the model learning. And the proposed feature fusion module can better integrate the features of different receptive fields. Therefore, the proposed method can significantly improve the segmentation performance compared to the traditional method. Hindawi 2023-02-22 /pmc/articles/PMC9977519/ /pubmed/36873381 http://dx.doi.org/10.1155/2023/6965259 Text en Copyright © 2023 Wei Bai. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Bai, Wei
An ENet Semantic Segmentation Method Combined with Attention Mechanism
title An ENet Semantic Segmentation Method Combined with Attention Mechanism
title_full An ENet Semantic Segmentation Method Combined with Attention Mechanism
title_fullStr An ENet Semantic Segmentation Method Combined with Attention Mechanism
title_full_unstemmed An ENet Semantic Segmentation Method Combined with Attention Mechanism
title_short An ENet Semantic Segmentation Method Combined with Attention Mechanism
title_sort enet semantic segmentation method combined with attention mechanism
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9977519/
https://www.ncbi.nlm.nih.gov/pubmed/36873381
http://dx.doi.org/10.1155/2023/6965259
work_keys_str_mv AT baiwei anenetsemanticsegmentationmethodcombinedwithattentionmechanism
AT baiwei enetsemanticsegmentationmethodcombinedwithattentionmechanism