CrackCLF: Automatic Pavement Crack Detection based on Closed-Loop Feedback

Automatic pavement crack detection is an important task to ensure the functional performances of pavements during their service life. Inspired by deep learning (DL), the encoder-decoder framework is a powerful tool for crack detection. However, these models are usually open-loop (OL) systems that te...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-11
Hauptverfasser: Li, Chong, Fan, Zhun, Chen, Ying, Lin, Huibiao, Moretti, Laura, Loprencipe, Giuseppe, Sheng, Weihua, Wang, Kelvin C P
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Li, Chong
Fan, Zhun
Chen, Ying
Lin, Huibiao
Moretti, Laura
Loprencipe, Giuseppe
Sheng, Weihua
Wang, Kelvin C P
description Automatic pavement crack detection is an important task to ensure the functional performances of pavements during their service life. Inspired by deep learning (DL), the encoder-decoder framework is a powerful tool for crack detection. However, these models are usually open-loop (OL) systems that tend to treat thin cracks as the background. Meanwhile, these models can not automatically correct errors in the prediction, nor can it adapt to the changes of the environment to automatically extract and detect thin cracks. To tackle this problem, we embed closed-loop feedback (CLF) into the neural network so that the model could learn to correct errors on its own, based on generative adversarial networks (GAN). The resulting model is called CrackCLF and includes the front and back ends, i.e. segmentation and adversarial network. The front end with U-shape framework is employed to generate crack maps, and the back end with a multi-scale loss function is used to correct higher-order inconsistencies between labels and crack maps (generated by the front end) to address open-loop system issues. Empirical results show that the proposed CrackCLF outperforms others methods on three public datasets. Moreover, the proposed CLF can be defined as a plug and play module, which can be embedded into different neural network models to improve their performances.
doi_str_mv 10.48550/arxiv.2311.11815
format Article
fullrecord <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2311_11815</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2894090034</sourcerecordid><originalsourceid>FETCH-LOGICAL-a524-4584ccaa162ba8218bc4b6e53e762fc983dc6a3d0e6f24e5d31609c5290328823</originalsourceid><addsrcrecordid>eNotj0tLxDAUhYMgOIzzA1wZcN2a3DwmdTdU64OCLmZf0vQWOk6b2qaD_ntrx9U9cD8O5yPkhrNYGqXYvR2-m1MMgvOYc8PVBVmBEDwyEuCKbMbxwBgDvQWlxIq8pYN1n2mePdDdFHxrQ-Pohz1hi12gy5M-YkAXGt_R0o5Y0TmkRz-nKPe-pxliVc7cNbms7XHEzf9dk332tE9fovz9-TXd5ZFVICOpjHTOWq6htAa4KZ0sNSqBWw21S4yonLaiYqhrkKgqwTVLnIKECTAGxJrcnmsX0aIfmtYOP8WfcLEIz8TdmegH_zXhGIqDn4Zu3lSASSRLGBNS_AKx9Vaa</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2894090034</pqid></control><display><type>article</type><title>CrackCLF: Automatic Pavement Crack Detection based on Closed-Loop Feedback</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Li, Chong ; Fan, Zhun ; Chen, Ying ; Lin, Huibiao ; Moretti, Laura ; Loprencipe, Giuseppe ; Sheng, Weihua ; Wang, Kelvin C P</creator><creatorcontrib>Li, Chong ; Fan, Zhun ; Chen, Ying ; Lin, Huibiao ; Moretti, Laura ; Loprencipe, Giuseppe ; Sheng, Weihua ; Wang, Kelvin C P</creatorcontrib><description>Automatic pavement crack detection is an important task to ensure the functional performances of pavements during their service life. Inspired by deep learning (DL), the encoder-decoder framework is a powerful tool for crack detection. However, these models are usually open-loop (OL) systems that tend to treat thin cracks as the background. Meanwhile, these models can not automatically correct errors in the prediction, nor can it adapt to the changes of the environment to automatically extract and detect thin cracks. To tackle this problem, we embed closed-loop feedback (CLF) into the neural network so that the model could learn to correct errors on its own, based on generative adversarial networks (GAN). The resulting model is called CrackCLF and includes the front and back ends, i.e. segmentation and adversarial network. The front end with U-shape framework is employed to generate crack maps, and the back end with a multi-scale loss function is used to correct higher-order inconsistencies between labels and crack maps (generated by the front end) to address open-loop system issues. Empirical results show that the proposed CrackCLF outperforms others methods on three public datasets. Moreover, the proposed CLF can be defined as a plug and play module, which can be embedded into different neural network models to improve their performances.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2311.11815</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Closed loops ; Computer Science - Computer Vision and Pattern Recognition ; Cracks ; Encoders-Decoders ; Errors ; Feedback ; Flaw detection ; Generative adversarial networks ; Machine learning ; Neural networks ; Pavements ; Service life</subject><ispartof>arXiv.org, 2023-11</ispartof><rights>2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,784,885,27925</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.2311.11815$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.1109/TITS.2023.3332995$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Li, Chong</creatorcontrib><creatorcontrib>Fan, Zhun</creatorcontrib><creatorcontrib>Chen, Ying</creatorcontrib><creatorcontrib>Lin, Huibiao</creatorcontrib><creatorcontrib>Moretti, Laura</creatorcontrib><creatorcontrib>Loprencipe, Giuseppe</creatorcontrib><creatorcontrib>Sheng, Weihua</creatorcontrib><creatorcontrib>Wang, Kelvin C P</creatorcontrib><title>CrackCLF: Automatic Pavement Crack Detection based on Closed-Loop Feedback</title><title>arXiv.org</title><description>Automatic pavement crack detection is an important task to ensure the functional performances of pavements during their service life. Inspired by deep learning (DL), the encoder-decoder framework is a powerful tool for crack detection. However, these models are usually open-loop (OL) systems that tend to treat thin cracks as the background. Meanwhile, these models can not automatically correct errors in the prediction, nor can it adapt to the changes of the environment to automatically extract and detect thin cracks. To tackle this problem, we embed closed-loop feedback (CLF) into the neural network so that the model could learn to correct errors on its own, based on generative adversarial networks (GAN). The resulting model is called CrackCLF and includes the front and back ends, i.e. segmentation and adversarial network. The front end with U-shape framework is employed to generate crack maps, and the back end with a multi-scale loss function is used to correct higher-order inconsistencies between labels and crack maps (generated by the front end) to address open-loop system issues. Empirical results show that the proposed CrackCLF outperforms others methods on three public datasets. Moreover, the proposed CLF can be defined as a plug and play module, which can be embedded into different neural network models to improve their performances.</description><subject>Closed loops</subject><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Cracks</subject><subject>Encoders-Decoders</subject><subject>Errors</subject><subject>Feedback</subject><subject>Flaw detection</subject><subject>Generative adversarial networks</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Pavements</subject><subject>Service life</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotj0tLxDAUhYMgOIzzA1wZcN2a3DwmdTdU64OCLmZf0vQWOk6b2qaD_ntrx9U9cD8O5yPkhrNYGqXYvR2-m1MMgvOYc8PVBVmBEDwyEuCKbMbxwBgDvQWlxIq8pYN1n2mePdDdFHxrQ-Pohz1hi12gy5M-YkAXGt_R0o5Y0TmkRz-nKPe-pxliVc7cNbms7XHEzf9dk332tE9fovz9-TXd5ZFVICOpjHTOWq6htAa4KZ0sNSqBWw21S4yonLaiYqhrkKgqwTVLnIKECTAGxJrcnmsX0aIfmtYOP8WfcLEIz8TdmegH_zXhGIqDn4Zu3lSASSRLGBNS_AKx9Vaa</recordid><startdate>20231120</startdate><enddate>20231120</enddate><creator>Li, Chong</creator><creator>Fan, Zhun</creator><creator>Chen, Ying</creator><creator>Lin, Huibiao</creator><creator>Moretti, Laura</creator><creator>Loprencipe, Giuseppe</creator><creator>Sheng, Weihua</creator><creator>Wang, Kelvin C P</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20231120</creationdate><title>CrackCLF: Automatic Pavement Crack Detection based on Closed-Loop Feedback</title><author>Li, Chong ; Fan, Zhun ; Chen, Ying ; Lin, Huibiao ; Moretti, Laura ; Loprencipe, Giuseppe ; Sheng, Weihua ; Wang, Kelvin C P</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a524-4584ccaa162ba8218bc4b6e53e762fc983dc6a3d0e6f24e5d31609c5290328823</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Closed loops</topic><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Cracks</topic><topic>Encoders-Decoders</topic><topic>Errors</topic><topic>Feedback</topic><topic>Flaw detection</topic><topic>Generative adversarial networks</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Pavements</topic><topic>Service life</topic><toplevel>online_resources</toplevel><creatorcontrib>Li, Chong</creatorcontrib><creatorcontrib>Fan, Zhun</creatorcontrib><creatorcontrib>Chen, Ying</creatorcontrib><creatorcontrib>Lin, Huibiao</creatorcontrib><creatorcontrib>Moretti, Laura</creatorcontrib><creatorcontrib>Loprencipe, Giuseppe</creatorcontrib><creatorcontrib>Sheng, Weihua</creatorcontrib><creatorcontrib>Wang, Kelvin C P</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Li, Chong</au><au>Fan, Zhun</au><au>Chen, Ying</au><au>Lin, Huibiao</au><au>Moretti, Laura</au><au>Loprencipe, Giuseppe</au><au>Sheng, Weihua</au><au>Wang, Kelvin C P</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>CrackCLF: Automatic Pavement Crack Detection based on Closed-Loop Feedback</atitle><jtitle>arXiv.org</jtitle><date>2023-11-20</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Automatic pavement crack detection is an important task to ensure the functional performances of pavements during their service life. Inspired by deep learning (DL), the encoder-decoder framework is a powerful tool for crack detection. However, these models are usually open-loop (OL) systems that tend to treat thin cracks as the background. Meanwhile, these models can not automatically correct errors in the prediction, nor can it adapt to the changes of the environment to automatically extract and detect thin cracks. To tackle this problem, we embed closed-loop feedback (CLF) into the neural network so that the model could learn to correct errors on its own, based on generative adversarial networks (GAN). The resulting model is called CrackCLF and includes the front and back ends, i.e. segmentation and adversarial network. The front end with U-shape framework is employed to generate crack maps, and the back end with a multi-scale loss function is used to correct higher-order inconsistencies between labels and crack maps (generated by the front end) to address open-loop system issues. Empirical results show that the proposed CrackCLF outperforms others methods on three public datasets. Moreover, the proposed CLF can be defined as a plug and play module, which can be embedded into different neural network models to improve their performances.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2311.11815</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-11
issn 2331-8422
language eng
recordid cdi_arxiv_primary_2311_11815
source arXiv.org; Free E- Journals
subjects Closed loops
Computer Science - Computer Vision and Pattern Recognition
Cracks
Encoders-Decoders
Errors
Feedback
Flaw detection
Generative adversarial networks
Machine learning
Neural networks
Pavements
Service life
title CrackCLF: Automatic Pavement Crack Detection based on Closed-Loop Feedback
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T12%3A56%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=CrackCLF:%20Automatic%20Pavement%20Crack%20Detection%20based%20on%20Closed-Loop%20Feedback&rft.jtitle=arXiv.org&rft.au=Li,%20Chong&rft.date=2023-11-20&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2311.11815&rft_dat=%3Cproquest_arxiv%3E2894090034%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2894090034&rft_id=info:pmid/&rfr_iscdi=true