Cargando…

Flame Edge Detection Method Based on a Convolutional Neural Network

[Image: see text] In this study, an improved flame edge detector based on convolutional neural network (CNN) was proposed. The proposed method can generate edge graphs and extract edge graphs relatively effectively. Our network architecture was based on VGG16 primarily, the last two max-pooling oper...

Descripción completa

Detalles Bibliográficos
Autores principales: Sun, Haoliang, Hao, Xiaojian, Wang, Jia, Pan, Baowu, Pei, Pan, Tai, Bin, Zhao, Yangcan, Feng, Shenxiang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2022
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9352261/
https://www.ncbi.nlm.nih.gov/pubmed/35936444
http://dx.doi.org/10.1021/acsomega.2c02858
_version_ 1784762617534873600
author Sun, Haoliang
Hao, Xiaojian
Wang, Jia
Pan, Baowu
Pei, Pan
Tai, Bin
Zhao, Yangcan
Feng, Shenxiang
author_facet Sun, Haoliang
Hao, Xiaojian
Wang, Jia
Pan, Baowu
Pei, Pan
Tai, Bin
Zhao, Yangcan
Feng, Shenxiang
author_sort Sun, Haoliang
collection PubMed
description [Image: see text] In this study, an improved flame edge detector based on convolutional neural network (CNN) was proposed. The proposed method can generate edge graphs and extract edge graphs relatively effectively. Our network architecture was based on VGG16 primarily, the last two max-pooling operators and all full connection layers of the VGG16 network were deleted, and the rest was taken as the basic network. The images output by the five convolution layers were upsampled to the size of the input images and finally fused to the edge image. Error calculation and back propagation of the fusion image and label image are carried out to form a weakly supervised model. Using the open datasets BSDS500 to train the network, the ODS F-measure can reach 0.810. Various experiments were carried out on different flame and fire images, including butane–air flame, oxygen–ethanol flame, energetic material flame, and oxygen–acetylene premixed jet flame, and the infrared thermogram was also verified by our method. The results demonstrate the effectiveness and robustness of the proposed algorithm.
format Online
Article
Text
id pubmed-9352261
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher American Chemical Society
record_format MEDLINE/PubMed
spelling pubmed-93522612022-08-05 Flame Edge Detection Method Based on a Convolutional Neural Network Sun, Haoliang Hao, Xiaojian Wang, Jia Pan, Baowu Pei, Pan Tai, Bin Zhao, Yangcan Feng, Shenxiang ACS Omega [Image: see text] In this study, an improved flame edge detector based on convolutional neural network (CNN) was proposed. The proposed method can generate edge graphs and extract edge graphs relatively effectively. Our network architecture was based on VGG16 primarily, the last two max-pooling operators and all full connection layers of the VGG16 network were deleted, and the rest was taken as the basic network. The images output by the five convolution layers were upsampled to the size of the input images and finally fused to the edge image. Error calculation and back propagation of the fusion image and label image are carried out to form a weakly supervised model. Using the open datasets BSDS500 to train the network, the ODS F-measure can reach 0.810. Various experiments were carried out on different flame and fire images, including butane–air flame, oxygen–ethanol flame, energetic material flame, and oxygen–acetylene premixed jet flame, and the infrared thermogram was also verified by our method. The results demonstrate the effectiveness and robustness of the proposed algorithm. American Chemical Society 2022-07-22 /pmc/articles/PMC9352261/ /pubmed/35936444 http://dx.doi.org/10.1021/acsomega.2c02858 Text en © 2022 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by-nc-nd/4.0/Permits non-commercial access and re-use, provided that author attribution and integrity are maintained; but does not permit creation of adaptations or other derivative works (https://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Sun, Haoliang
Hao, Xiaojian
Wang, Jia
Pan, Baowu
Pei, Pan
Tai, Bin
Zhao, Yangcan
Feng, Shenxiang
Flame Edge Detection Method Based on a Convolutional Neural Network
title Flame Edge Detection Method Based on a Convolutional Neural Network
title_full Flame Edge Detection Method Based on a Convolutional Neural Network
title_fullStr Flame Edge Detection Method Based on a Convolutional Neural Network
title_full_unstemmed Flame Edge Detection Method Based on a Convolutional Neural Network
title_short Flame Edge Detection Method Based on a Convolutional Neural Network
title_sort flame edge detection method based on a convolutional neural network
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9352261/
https://www.ncbi.nlm.nih.gov/pubmed/35936444
http://dx.doi.org/10.1021/acsomega.2c02858
work_keys_str_mv AT sunhaoliang flameedgedetectionmethodbasedonaconvolutionalneuralnetwork
AT haoxiaojian flameedgedetectionmethodbasedonaconvolutionalneuralnetwork
AT wangjia flameedgedetectionmethodbasedonaconvolutionalneuralnetwork
AT panbaowu flameedgedetectionmethodbasedonaconvolutionalneuralnetwork
AT peipan flameedgedetectionmethodbasedonaconvolutionalneuralnetwork
AT taibin flameedgedetectionmethodbasedonaconvolutionalneuralnetwork
AT zhaoyangcan flameedgedetectionmethodbasedonaconvolutionalneuralnetwork
AT fengshenxiang flameedgedetectionmethodbasedonaconvolutionalneuralnetwork