Flame Edge Detection Method Based on a Convolutional Neural Network
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...
Gespeichert in:
Veröffentlicht in: | ACS omega 2022-08, Vol.7 (30), p.26680-26686 |
---|---|
Hauptverfasser: | , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 26686 |
---|---|
container_issue | 30 |
container_start_page | 26680 |
container_title | ACS omega |
container_volume | 7 |
creator | Sun, Haoliang Hao, Xiaojian Wang, Jia Pan, Baowu Pei, Pan Tai, Bin Zhao, Yangcan Feng, Shenxiang |
description | 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. |
doi_str_mv | 10.1021/acsomega.2c02858 |
format | Article |
fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_9352261</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2699959626</sourcerecordid><originalsourceid>FETCH-LOGICAL-a410t-c17b430430478807c89ccad706196198a0f9d637393c875ccee1c5a35887ff0b3</originalsourceid><addsrcrecordid>eNp1UE1PwkAQ3RiNEOTusUcPFvej3Y-LiSKoCepFz5tlO4Vi28Vui_HfuwgaPZhM8mby3ryZPIROCR4RTMmFsd5VsDAjajGVqTxAfZoIHBOWsMNffQ8NvV9hjAmXVFJ-jHosVYwnSdJH42lpKogm2QKiG2jBtoWrowdoly6Lro2HLAqzicau3riy27KmjB6ha76gfXfN6wk6yk3pYbjHAXqZTp7Hd_Hs6fZ-fDWLTUJwG1si5gnD2xJSYmGlstZkAnOiQkmDc5VxJphiVorUWgBiU8NSKUWe4zkboMud77qbV5BZqNvwhV43RWWaD-1Mof8ydbHUC7fRiqWUchIMzvYGjXvrwLe6KryFsjQ1uM5rypVSqeKUByneSW3jvG8g_zlDsN7Gr7_j1_v4w8r5biUweuW6JiTl_5d_As7Uhu0</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2699959626</pqid></control><display><type>article</type><title>Flame Edge Detection Method Based on a Convolutional Neural Network</title><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><source>Access via American Chemical Society (ACS)</source><creator>Sun, Haoliang ; Hao, Xiaojian ; Wang, Jia ; Pan, Baowu ; Pei, Pan ; Tai, Bin ; Zhao, Yangcan ; Feng, Shenxiang</creator><creatorcontrib>Sun, Haoliang ; Hao, Xiaojian ; Wang, Jia ; Pan, Baowu ; Pei, Pan ; Tai, Bin ; Zhao, Yangcan ; Feng, Shenxiang</creatorcontrib><description>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.</description><identifier>ISSN: 2470-1343</identifier><identifier>EISSN: 2470-1343</identifier><identifier>DOI: 10.1021/acsomega.2c02858</identifier><identifier>PMID: 35936444</identifier><language>eng</language><publisher>American Chemical Society</publisher><ispartof>ACS omega, 2022-08, Vol.7 (30), p.26680-26686</ispartof><rights>2022 The Authors. Published by American Chemical Society</rights><rights>2022 The Authors. Published by American Chemical Society 2022 The Authors</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a410t-c17b430430478807c89ccad706196198a0f9d637393c875ccee1c5a35887ff0b3</citedby><cites>FETCH-LOGICAL-a410t-c17b430430478807c89ccad706196198a0f9d637393c875ccee1c5a35887ff0b3</cites><orcidid>0000-0003-2227-6297 ; 0000-0002-2856-0013</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://pubs.acs.org/doi/pdf/10.1021/acsomega.2c02858$$EPDF$$P50$$Gacs$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://pubs.acs.org/doi/10.1021/acsomega.2c02858$$EHTML$$P50$$Gacs$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,864,885,27080,27924,27925,53791,53793,56762,56812</link.rule.ids></links><search><creatorcontrib>Sun, Haoliang</creatorcontrib><creatorcontrib>Hao, Xiaojian</creatorcontrib><creatorcontrib>Wang, Jia</creatorcontrib><creatorcontrib>Pan, Baowu</creatorcontrib><creatorcontrib>Pei, Pan</creatorcontrib><creatorcontrib>Tai, Bin</creatorcontrib><creatorcontrib>Zhao, Yangcan</creatorcontrib><creatorcontrib>Feng, Shenxiang</creatorcontrib><title>Flame Edge Detection Method Based on a Convolutional Neural Network</title><title>ACS omega</title><addtitle>ACS Omega</addtitle><description>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.</description><issn>2470-1343</issn><issn>2470-1343</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>N~.</sourceid><recordid>eNp1UE1PwkAQ3RiNEOTusUcPFvej3Y-LiSKoCepFz5tlO4Vi28Vui_HfuwgaPZhM8mby3ryZPIROCR4RTMmFsd5VsDAjajGVqTxAfZoIHBOWsMNffQ8NvV9hjAmXVFJ-jHosVYwnSdJH42lpKogm2QKiG2jBtoWrowdoly6Lro2HLAqzicau3riy27KmjB6ha76gfXfN6wk6yk3pYbjHAXqZTp7Hd_Hs6fZ-fDWLTUJwG1si5gnD2xJSYmGlstZkAnOiQkmDc5VxJphiVorUWgBiU8NSKUWe4zkboMud77qbV5BZqNvwhV43RWWaD-1Mof8ydbHUC7fRiqWUchIMzvYGjXvrwLe6KryFsjQ1uM5rypVSqeKUByneSW3jvG8g_zlDsN7Gr7_j1_v4w8r5biUweuW6JiTl_5d_As7Uhu0</recordid><startdate>20220802</startdate><enddate>20220802</enddate><creator>Sun, Haoliang</creator><creator>Hao, Xiaojian</creator><creator>Wang, Jia</creator><creator>Pan, Baowu</creator><creator>Pei, Pan</creator><creator>Tai, Bin</creator><creator>Zhao, Yangcan</creator><creator>Feng, Shenxiang</creator><general>American Chemical Society</general><scope>N~.</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0003-2227-6297</orcidid><orcidid>https://orcid.org/0000-0002-2856-0013</orcidid></search><sort><creationdate>20220802</creationdate><title>Flame Edge Detection Method Based on a Convolutional Neural Network</title><author>Sun, Haoliang ; Hao, Xiaojian ; Wang, Jia ; Pan, Baowu ; Pei, Pan ; Tai, Bin ; Zhao, Yangcan ; Feng, Shenxiang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a410t-c17b430430478807c89ccad706196198a0f9d637393c875ccee1c5a35887ff0b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Sun, Haoliang</creatorcontrib><creatorcontrib>Hao, Xiaojian</creatorcontrib><creatorcontrib>Wang, Jia</creatorcontrib><creatorcontrib>Pan, Baowu</creatorcontrib><creatorcontrib>Pei, Pan</creatorcontrib><creatorcontrib>Tai, Bin</creatorcontrib><creatorcontrib>Zhao, Yangcan</creatorcontrib><creatorcontrib>Feng, Shenxiang</creatorcontrib><collection>Access via American Chemical Society (ACS)</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>ACS omega</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Sun, Haoliang</au><au>Hao, Xiaojian</au><au>Wang, Jia</au><au>Pan, Baowu</au><au>Pei, Pan</au><au>Tai, Bin</au><au>Zhao, Yangcan</au><au>Feng, Shenxiang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Flame Edge Detection Method Based on a Convolutional Neural Network</atitle><jtitle>ACS omega</jtitle><addtitle>ACS Omega</addtitle><date>2022-08-02</date><risdate>2022</risdate><volume>7</volume><issue>30</issue><spage>26680</spage><epage>26686</epage><pages>26680-26686</pages><issn>2470-1343</issn><eissn>2470-1343</eissn><abstract>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.</abstract><pub>American Chemical Society</pub><pmid>35936444</pmid><doi>10.1021/acsomega.2c02858</doi><tpages>7</tpages><orcidid>https://orcid.org/0000-0003-2227-6297</orcidid><orcidid>https://orcid.org/0000-0002-2856-0013</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2470-1343 |
ispartof | ACS omega, 2022-08, Vol.7 (30), p.26680-26686 |
issn | 2470-1343 2470-1343 |
language | eng |
recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_9352261 |
source | DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals; PubMed Central; Access via American Chemical Society (ACS) |
title | Flame Edge Detection Method Based on a Convolutional Neural Network |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T06%3A24%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Flame%20Edge%20Detection%20Method%20Based%20on%20a%20Convolutional%20Neural%20Network&rft.jtitle=ACS%20omega&rft.au=Sun,%20Haoliang&rft.date=2022-08-02&rft.volume=7&rft.issue=30&rft.spage=26680&rft.epage=26686&rft.pages=26680-26686&rft.issn=2470-1343&rft.eissn=2470-1343&rft_id=info:doi/10.1021/acsomega.2c02858&rft_dat=%3Cproquest_pubme%3E2699959626%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2699959626&rft_id=info:pmid/35936444&rfr_iscdi=true |