Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning
Masonry structures represent the highest proportion of building stock worldwide. Currently, the structural condition of such structures is predominantly manually inspected which is a laborious, costly and subjective process. With developments in computer vision, there is an opportunity to use digital images to automate the visual inspection process. The aim of … celý popis
Uloženo v:
Podrobná bibliografie
- Publikováno v
- Automation in construction Ročník 125; s. 103606
- Hlavní autoři
- , , ,
- Typ dokumentu
- Journal Article
- Jazyk
- English
- Vydáno
-
Amsterdam
Elsevier B.V
01. 05. 2021
Elsevier BV - Témata
- ISSN
- 0926-5805
1872-7891 - DOI
- 10.1016/j.autcon.2021.103606
| Abstract | Masonry structures represent the highest proportion of building stock worldwide. Currently, the structural condition of such structures is predominantly manually inspected which is a laborious, costly and subjective process. With developments in computer vision, there is an opportunity to use digital images to automate the visual inspection process. The aim of this study is to examine deep learning techniques for crack detection on images from masonry walls. A dataset with photos from masonry structures is produced containing complex backgrounds and various crack types and sizes. Different deep learning networks are considered and by leveraging the effect of transfer learning crack detection on masonry surfaces is performed on patch level with 95.3% accuracy and on pixel level with 79.6% F1 score. This is the first implementation of deep learning for pixel-level crack segmentation on masonry surfaces. Codes, data and networks relevant to the herein study are available in: github.com/dimitrisdais/crack_detection_CNN_masonry.
•Crack detection on masonry surfaces performed on patch level with 95.3% accuracy.•Crack detection on masonry surfaces performed on pixel level with 79.6% F1 score.•DL for pixel-level masonry crack segmentation is implemented for the first time.•Transfer learning boosts the performance of crack classification and segmentation. |
|---|---|
| AbstractList | Masonry structures represent the highest proportion of building stock worldwide. Currently, the structural condition of such structures is predominantly manually inspected which is a laborious, costly and subjective process. With developments in computer vision, there is an opportunity to use digital images to automate the visual inspection process. The aim of this study is to examine deep learning techniques for crack detection on images from masonry walls. A dataset with photos from masonry structures is produced containing complex backgrounds and various crack types and sizes. Different deep learning networks are considered and by leveraging the effect of transfer learning crack detection on masonry surfaces is performed on patch level with 95.3% accuracy and on pixel level with 79.6% F1 score. This is the first implementation of deep learning for pixel-level crack segmentation on masonry surfaces. Codes, data and networks relevant to the herein study are available in: github.com/dimitrisdais/crack_detection_CNN_masonry. Masonry structures represent the highest proportion of building stock worldwide. Currently, the structural condition of such structures is predominantly manually inspected which is a laborious, costly and subjective process. With developments in computer vision, there is an opportunity to use digital images to automate the visual inspection process. The aim of this study is to examine deep learning techniques for crack detection on images from masonry walls. A dataset with photos from masonry structures is produced containing complex backgrounds and various crack types and sizes. Different deep learning networks are considered and by leveraging the effect of transfer learning crack detection on masonry surfaces is performed on patch level with 95.3% accuracy and on pixel level with 79.6% F1 score. This is the first implementation of deep learning for pixel-level crack segmentation on masonry surfaces. Codes, data and networks relevant to the herein study are available in: github.com/dimitrisdais/crack_detection_CNN_masonry. •Crack detection on masonry surfaces performed on patch level with 95.3% accuracy.•Crack detection on masonry surfaces performed on pixel level with 79.6% F1 score.•DL for pixel-level masonry crack segmentation is implemented for the first time.•Transfer learning boosts the performance of crack classification and segmentation. |
| ArticleNumber | 103606 |
| Author | Bal, İhsan Engin Smyrou, Eleni Sarhosis, Vasilis Dais, Dimitris |
| Author_xml | – sequence: 1 givenname: Dimitris surname: Dais fullname: Dais, Dimitris email: d.dais@pl.hanze.nl organization: Research Center for Built Environment NoorderRuimte, Hanze University of Applied Sciences, Zernikeplein 11, 9701 DA Groningen, the Netherlands – sequence: 2 givenname: İhsan Engin surname: Bal fullname: Bal, İhsan Engin organization: Research Center for Built Environment NoorderRuimte, Hanze University of Applied Sciences, Zernikeplein 11, 9701 DA Groningen, the Netherlands – sequence: 3 givenname: Eleni surname: Smyrou fullname: Smyrou, Eleni organization: Research Center for Built Environment NoorderRuimte, Hanze University of Applied Sciences, Zernikeplein 11, 9701 DA Groningen, the Netherlands – sequence: 4 givenname: Vasilis surname: Sarhosis fullname: Sarhosis, Vasilis organization: School of Civil Engineering, University of Leeds, Woodhouse, LS2 9JT Leeds, UK |
| BookMark | eNqNkM1rVDEUxYMoOK39D1wE3LjwjUlekveyEUrxCwpudB0y-aiZvknG3KS1C_93M33iUoTAhZvfOfdwztCFafW7TzVaU71D6CUlW0qofLvf9h-b05YRRvtqlEQ-QRs6T2yYZkWfog1RTA5iJuI5OgPYE0ImItUG_bpsNR9M98S2GHuL7WIAYjjdiDlhkxwGf3PoZ9dFfwcDOZUHDK0EYz3gBjHd4B7gLi_tRJkFJ9_K46j3udzCo1EtJkHwBS_elNQ1L9CzYBbwF3_mOfr24f3Xq0_D9ZePn68urwfLuayDcortJi_8RMnO7QQ31AUxe6UEd9KFwB2XhDIyBUaNVXx0zImdpEpMxhE-nqNXq--x5B_NQ9X73EqPCZqJkVElmZg7xVfKlgxQfNDHEg-mPGhK9Klovddr0fpUtF6L7rI3qwxsPjb4K2IamCZ6Fl06qnEUUtefteOv_xPv6LsV9b2bu-iLBht9st7F4m3VLsd_R_sNhWysyA |
| CitedBy_id | crossref_primary_10_1016_j_measurement_2022_111590 crossref_primary_10_1016_j_conbuildmat_2022_127562 crossref_primary_10_1016_j_conbuildmat_2022_129226 crossref_primary_10_1177_14759217231183663 crossref_primary_10_1016_j_autcon_2022_104575 crossref_primary_10_1016_j_tust_2022_104403 crossref_primary_10_1016_j_ecoinf_2022_101832 crossref_primary_10_1016_j_autcon_2021_103633 crossref_primary_10_1016_j_dibe_2023_100191 crossref_primary_10_1007_s00500_023_09103_x crossref_primary_10_1016_j_istruc_2023_02_033 crossref_primary_10_1007_s42107_022_00526_9 crossref_primary_10_1007_s13349_022_00643_8 crossref_primary_10_1108_SASBE_09_2023_0251 crossref_primary_10_1007_s12145_023_01217_y crossref_primary_10_1007_s13349_023_00684_7 crossref_primary_10_1109_ACCESS_2023_3343619 crossref_primary_10_1016_j_ymssp_2023_110286 crossref_primary_10_1016_j_autcon_2022_104182 crossref_primary_10_1016_j_engstruct_2024_118113 crossref_primary_10_1109_TITS_2022_3150536 crossref_primary_10_48175_IJARSCT_13674 crossref_primary_10_1109_JSEN_2023_3240092 crossref_primary_10_1016_j_jenvman_2023_119689 crossref_primary_10_1016_j_autcon_2022_104469 crossref_primary_10_3390_asi7010011 crossref_primary_10_1111_mice_13212 crossref_primary_10_1016_j_istruc_2023_105640 crossref_primary_10_1049_itr2_12173 crossref_primary_10_3390_app13031904 crossref_primary_10_1016_j_conbuildmat_2024_136573 crossref_primary_10_2355_isijinternational_ISIJINT_2022_108 crossref_primary_10_1016_j_measurement_2021_110641 crossref_primary_10_1007_s00371_024_03531_y crossref_primary_10_1007_s13349_022_00632_x crossref_primary_10_1080_14680629_2023_2266853 crossref_primary_10_3389_fbuil_2023_1144606 crossref_primary_10_3390_lubricants12050172 crossref_primary_10_1016_j_jobe_2024_109827 crossref_primary_10_1016_j_jobe_2023_107105 crossref_primary_10_1007_s12596_023_01340_5 crossref_primary_10_1016_j_culher_2024_05_009 crossref_primary_10_1016_j_engstruct_2024_118402 crossref_primary_10_3390_a15080281 crossref_primary_10_1016_j_autcon_2024_105601 crossref_primary_10_1016_j_compind_2023_103921 crossref_primary_10_1016_j_aei_2022_101687 crossref_primary_10_1016_j_autcon_2022_104313 crossref_primary_10_1016_j_autcon_2022_104427 crossref_primary_10_1016_j_engstruct_2024_117708 crossref_primary_10_1016_j_istruc_2022_01_061 crossref_primary_10_3390_w16101348 crossref_primary_10_1016_j_engappai_2023_107164 crossref_primary_10_1016_j_engstruct_2022_115291 crossref_primary_10_3390_su15129314 crossref_primary_10_1016_j_autcon_2024_105299 crossref_primary_10_1016_j_rineng_2024_101822 crossref_primary_10_1016_j_engappai_2023_106876 crossref_primary_10_3390_buildings12101520 crossref_primary_10_55525_tjst_1291814 crossref_primary_10_1016_j_autcon_2024_105297 crossref_primary_10_1016_j_conbuildmat_2022_129438 crossref_primary_10_1016_j_culher_2024_01_005 crossref_primary_10_1016_j_measurement_2023_113964 crossref_primary_10_1016_j_engstruct_2024_117604 crossref_primary_10_3390_s23010504 crossref_primary_10_1061_JCEMD4_COENG_13196 crossref_primary_10_1155_2023_2177724 crossref_primary_10_1088_1742_6596_2647_18_182036 crossref_primary_10_1007_s41024_023_00371_6 crossref_primary_10_1016_j_istruc_2022_02_003 crossref_primary_10_1016_j_autcon_2022_104316 crossref_primary_10_1109_TSMC_2023_3274878 crossref_primary_10_1007_s12273_022_0927_7 crossref_primary_10_1007_s10064_024_03710_0 crossref_primary_10_1061__ASCE_AE_1943_5568_0000569 crossref_primary_10_3390_rs13142665 crossref_primary_10_1016_j_softx_2023_101323 crossref_primary_10_1007_s41024_023_00274_6 crossref_primary_10_1016_j_autcon_2023_105186 crossref_primary_10_1061_PPSCFX_SCENG_1410 crossref_primary_10_3390_buildings12040432 crossref_primary_10_1016_j_autcon_2022_104494 crossref_primary_10_1016_j_conbuildmat_2021_124013 crossref_primary_10_1016_j_autcon_2023_105181 crossref_primary_10_1016_j_jobe_2023_107961 crossref_primary_10_1016_j_engfailanal_2021_105262 crossref_primary_10_3390_buildings13123113 crossref_primary_10_1109_TIM_2023_3324689 crossref_primary_10_1111_mice_12832 crossref_primary_10_1016_j_engstruct_2022_115306 crossref_primary_10_1016_j_autcon_2023_104894 crossref_primary_10_1016_j_engstruct_2023_115945 crossref_primary_10_1061_JCCEE5_CPENG_5478 crossref_primary_10_1111_mice_13003 crossref_primary_10_1007_s11668_022_01430_9 crossref_primary_10_3390_s22228714 crossref_primary_10_1016_j_jpowsour_2023_233129 crossref_primary_10_1680_jenhh_21_00007 crossref_primary_10_1016_j_engappai_2023_106452 crossref_primary_10_1016_j_heliyon_2024_e32189 crossref_primary_10_1016_j_conbuildmat_2024_135151 crossref_primary_10_2139_ssrn_4353622 crossref_primary_10_1016_j_engfailanal_2024_108420 crossref_primary_10_1016_j_autcon_2022_104383 crossref_primary_10_1016_j_advengsoft_2024_103691 crossref_primary_10_1016_j_autcon_2023_105215 crossref_primary_10_1088_1755_1315_1124_1_012004 crossref_primary_10_1016_j_engappai_2024_108218 crossref_primary_10_1007_s13369_022_07567_x crossref_primary_10_1016_j_engstruct_2024_117903 crossref_primary_10_1016_j_autcon_2022_104389 crossref_primary_10_1016_j_autcon_2022_104543 crossref_primary_10_1016_j_autcon_2023_105213 crossref_primary_10_1016_j_engstruct_2023_116912 crossref_primary_10_1109_TITS_2023_3314680 crossref_primary_10_1002_eng2_12692 crossref_primary_10_1016_j_measen_2023_100940 crossref_primary_10_3390_app132111800 crossref_primary_10_1080_15583058_2023_2260771 crossref_primary_10_3390_buildings13010055 crossref_primary_10_1016_j_tust_2023_105310 crossref_primary_10_1016_j_autcon_2024_105367 crossref_primary_10_1177_14759217231177314 crossref_primary_10_1016_j_autcon_2021_104106 crossref_primary_10_1080_13632469_2024_2302033 crossref_primary_10_1016_j_aei_2024_102498 crossref_primary_10_1016_j_engstruct_2022_115256 crossref_primary_10_3390_s23135878 crossref_primary_10_1061_JPCFEV_CFENG_4709 crossref_primary_10_1111_mice_13231 crossref_primary_10_1007_s00521_021_06279_x crossref_primary_10_1142_S1793431123500367 crossref_primary_10_1177_14759217221137931 crossref_primary_10_1007_s11760_022_02393_y crossref_primary_10_1016_j_autcon_2022_104364 crossref_primary_10_1016_j_measurement_2023_112832 crossref_primary_10_1109_TIM_2024_3374293 crossref_primary_10_3390_s22093471 crossref_primary_10_1016_j_conbuildmat_2023_132402 crossref_primary_10_1080_15583058_2022_2134062 crossref_primary_10_1016_j_autcon_2023_105112 crossref_primary_10_1016_j_jobe_2023_108063 crossref_primary_10_1016_j_undsp_2023_09_012 crossref_primary_10_1007_s12596_023_01304_9 crossref_primary_10_1016_j_procir_2022_05_254 crossref_primary_10_3390_buildings14010151 crossref_primary_10_1016_j_conbuildmat_2021_124831 crossref_primary_10_3390_s22093118 |
| Cites_doi | 10.1111/mice.12387 10.1061/(ASCE)CP.1943-5487.0000775 10.3390/s18093042 10.1111/mice.12263 10.1016/j.autcon.2018.11.028 10.1016/j.autcon.2019.103018 10.3390/app9142867 10.1155/2011/989354 10.1109/TPAMI.2018.2858826 10.1109/TPAMI.2017.2699184 10.1016/j.neucom.2019.01.036 10.1002/stc.2286 10.1016/j.autcon.2019.04.005 10.1109/TIP.2018.2878966 10.1111/mice.12334 10.1016/j.autcon.2020.103199 10.1109/TITS.2016.2552248 10.1007/s10845-019-01476-x 10.1109/TIE.2019.2945265 10.1109/ACCESS.2019.2961375 10.1061/(ASCE)1084-0702(2004)9:4(403) 10.3390/app9132686 10.1109/TITS.2019.2910595 10.1111/mice.12363 10.1177/1475921719883202 10.1007/s13349-020-00409-0 10.1111/mice.12412 10.21660/2019.59.8272 10.1016/j.engstruct.2019.110157 10.1016/j.conbuildmat.2018.08.011 10.1016/j.eng.2018.11.030 10.3390/s20030717 10.1111/mice.12297 10.1061/(ASCE)1076-0342(2010)16:2(129) 10.1061/(ASCE)CP.1943-5487.0000890 10.1111/mice.12433 10.1111/mice.12440 10.1109/ACCESS.2019.2916330 10.1016/j.autcon.2019.03.003 10.1007/s12205-019-0437-z 10.1016/j.autcon.2020.103291 10.1109/TNNLS.2018.2876865 10.3390/s18061881 10.1061/(ASCE)CP.1943-5487.0000854 10.1016/j.autcon.2019.102846 |
| ContentType | Journal Article |
| Copyright | 2021 The Authors Copyright 2021 Elsevier B.V., All rights reserved. Copyright Elsevier BV May 2021 |
| Copyright_xml | – notice: 2021 The Authors – notice: Copyright 2021 Elsevier B.V., All rights reserved. – notice: Copyright Elsevier BV May 2021 |
| DBID | 6I. AAFTH BKL AAYXX CITATION 7SC 7SP 8FD FR3 JQ2 KR7 L7M L~C L~D |
| DOI | 10.1016/j.autcon.2021.103606 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access Scopus CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database Engineering Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | Elsevier Scopus CrossRef Civil Engineering Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Civil Engineering Abstracts Elsevier Scopus |
| Database_xml | – sequence: 1 dbid: BKL name: Scopus url: https://www.scopus.com sourceTypes: Enrichment Source Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Economics Engineering |
| EID | 2-s2.0-85101393356 |
| EISSN | 1872-7891 |
| ExternalDocumentID | 10_1016_j_autcon_2021_103606 scopus_primary_2011158809 S0926580521000571 |
| GrantInformation | RVO.nl RAAK.MKB09.021 Rijksdienst voor Ondernemend Nederland |
| GrantInformation_xml | – fundername: RVO grantid: RAAK.MKB09.021 – fundername: Rijksdienst voor het Cultureel Erfgoed grantid: 126761 – fundername: Rijksdienst voor Ondernemend Nederland grantid: RAAK.MKB09.021 funderid: 100013405 |
| GroupedDBID | --K --M .~1 0R~ 1B1 1~. 1~5 23N 4.4 457 4G. 5GY 5VS 6I. 7-5 71M 8P~ 9JN AACTN AAEDT AAEDW AAFTH AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AARIN AAXUO ABFNM ABMAC ABXDB ABYKQ ACDAQ ACGFS ACIWK ACNNM ACRLP ADBBV ADEZE ADMUD ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ APLSM ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA HVGLF HZ~ IHE J1W JJJVA KOM LY7 M41 MO0 N9A NEJ O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 R2- RIG RNS ROL RPZ SDF SDG SDP SES SET SEW SPC SPCBC SSB SSD SST SSZ T5K WUQ ZMT ~G- AAXKI ABJNI AEIPS AKRWK ANKPU BKL AATTM AAYXX ABWVN ACRPL ADNMO AFJKZ BNPGV CITATION SSH 7SC 7SP 8FD FR3 JQ2 KR7 L7M L~C L~D |
| ID | FETCH-LOGICAL-c446t-9d92b7e5e710bdb54a1df58e9954d6dff4d4601207f21ac943d2d5b61957ad043 |
| IEDL.DBID | FDB |
| ISSN | 0926-5805 |
| IngestDate | Wed Apr 02 08:49:12 EDT 2025 Wed Apr 02 04:46:03 EDT 2025 Fri Jan 10 22:01:22 EST 2025 Thu Mar 27 02:59:12 EDT 2025 Fri Feb 23 02:43:58 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning CNN Segmentation Transfer learning Classification Crack detection Masonry |
| Language | English |
| License | This is an open access article under the CC BY license. http://creativecommons.org/licenses/by/4.0 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c446t-9d92b7e5e710bdb54a1df58e9954d6dff4d4601207f21ac943d2d5b61957ad043 |
| OpenAccessLink | https://www.sciencedirect.com/science/article/pii/S0926580521000571 |
| PQID | 2532196258 |
| PQPubID | 2045277 |
| ParticipantIDs | elsevier_sciencedirect_doi_10_1016_j_autcon_2021_103606 crossref_primary_10_1016_j_autcon_2021_103606 proquest_journals_2532196258 scopus_primary_2_s2_0_85101393356 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | May 2021 2021-05-01 2021-05-00 20210501 |
| PublicationDateYYYYMMDD | 2021-05-01 |
| PublicationDate_xml | – month: 05 year: 2021 text: May 2021 |
| PublicationDecade | 2020 |
| PublicationPlace | Amsterdam |
| PublicationPlace_xml | – name: Amsterdam |
| PublicationTitle | Automation in construction |
| PublicationYear | 2021 |
| Publisher | Elsevier B.V Elsevier BV |
| Publisher_xml | – name: Elsevier B.V – name: Elsevier BV |
| References | Mei, Gül, Azim (bb0280) 2020; 110 Chen, Papandreou, Kokkinos, Murphy, Yuille (bb0090) 2018; 40 Ali (bb0265) 2019; 17 Chen, Zhu, Papandreou, Schroff, Adam (bb0365) 2018 Howard, Zhu, Chen, Kalenichenko, Wang, Weyand, Andreetto, Adam (bb0300) 2017 Liu, Anguelov, Erhan, Szegedy, Reed, Fu, Berg (bb0340) 2016 Zhao, Zheng, Xu, Wu (bb0040) 2019; 30 Chollet (bb0190) 2017 (bb0395) 2019 Zhang, Zhang, Cheng (bb0270) 2020 Chollet (bb0330) 2015 Maeda, Sekimoto, Seto, Kashiyama, Omata (bb0345) 2018; 33 Alipour, Harris, Miller (bb0285) 2019; 33 Liu, Cao, Wang, Wang (bb0150) 2019; 104 Choi, Cha (bb0095) 2020; 67 Bang, Park, Kim, Kim (bb0205) 2019; 34 Tabernik, Šela, Skvarč, Skočaj (bb0290) 2020; 31 Hoskere, Narazaki, Hoang, Spencer (bb0130) 2020; 10 Huang, Rathod, Sun, Zhu, Korattikara, Fathi, Fischer, Wojna, Song, Guadarrama, Murphy (bb0335) 2017 Chambon, Moliard (bb0380) 2011; 2011 Tomazevic (bb0005) 1999 Huang, Liu, Van Der Maaten, Weinberger (bb0315) 2017 Dais, Sarhosis, Smyrou, Bal, Coningham, Joshi, Acharya, Maskey, Weise, Kunwar (bb0010) 2019 Zhang, Wang, Li, Yang, Dai, Peng, Fei, Liu, Li, Chen (bb0375) 2017; 32 Sandler, Howard, Zhu, Zhmoginov, Chen (bb0305) 2018 Yakubovskiy (bb0325) 2019 Spencer, Hoskere, Narazaki (bb0035) 2019; 5 Dung, Anh (bb0115) 2019; 99 Yang, Li, Yu, Luo, Huang, Yang (bb0120) 2018; 33 Xu, Su, Wang, Cai, Cui, Chen (bb0355) 2019; 9 Kingma, Ba (bb0360) 2015 Gao, Mosalam (bb0210) 2018; 33 Kalfarisi, Wu, Soh (bb0215) 2020; 34 Ronneberger, Fischer, Brox (bb0135) 2015; 9351 Valero, Forster, Bosché, Hyslop, Wilson, Turmel (bb0245) 2019; 106 Song, Wu, Xin, Yang, Yang, Chen, Liu, Hu, Chai, Li (bb0350) 2019; 7 Kang, Benipal, Gopal, Cha (bb0220) 2020; 118 Gilbert (bb0020) 2009 Dorafshan, Thomas, Maguire (bb0275) 2018; 186 Wang, Zhao, Zhao, Zhang, Zou, Ou (bb0260) 2019; 103 Redmon, Farhadi (bb0170) 2018 Liu, Deng (bb0295) 2015 Lin, Goyal, Girshick, He, Dollar (bb0370) 2020; 42 Cha, Choi, Suh, Mahmoudkhani, Büyüköztürk (bb0080) 2018; 33 Mohtasham Khani, Vahidnia, Ghasemzadeh, Ozturk, Yuvalaklioglu, Akin, Ure (bb0055) 2020; 19 Liu, Yao, Lu, Xie, Li (bb0085) 2019; 338 Zhang, Wang, Fei, Liu, Tao, Chen, Li, Li (bb0060) 2018; 32 Najimi, Jonas, McCormick, Kimkeran (bb0255) 2014 Zhang, Chang, Jamshidi (bb0180) 2018 Long, Shelhamer, Darrell (bb0110) 2015 Rosebrock (bb0045) 2017 Zhang, Lu, Wang, Wang, Yue (bb0065) 2019; 9 Feng, Zhang, Wang, Li, Wang, Yan (bb0070) 2019; 23 Kim, Jeon, Baek, Hong, Jung (bb0050) 2018; 18 Laefer, Gannon, Deely (bb0030) 2010; 16 Phares, Washer, Rolander, Graybeal, Moore (bb0025) 2004; 9 Yang, Zhang, Yu, Prokhorov, Mei, Ling (bb0175) 2020; 21 Yang, Shi, Chen, Lin (bb0200) 2020; 116 Ibrahim, Nagy, Benedek (bb0250) 2019 Garcia-Garcia, Orts-Escolano, Oprea, Villena-Martinez, Garcia-Rodriguez (bb0105) 2017 Bal, Dais, Smyrou, Sarhosis (bb0015) 2020 Lin, Dollar, Girshick, He, Hariharan, Belongie (bb0160) 2017 Li, Zhao, Zhou (bb0125) 2019; 34 Özgenel, Sorguç (bb0240) 2018 He, Zhang, Ren, Sun (bb0320) 2016 Ma, Ren, Liu (bb0155) 2020; 20 Alipour, Harris (bb0235) 2020; 206 Cha, Choi, Büyüköztürk (bb0075) 2017; 32 Shi, Cui, Qi, Meng, Chen (bb0390) 2016; 17 He, Gkioxari, Dollar, Girshick (bb0165) 2017 Li, Li, Wang (bb0100) 2018; 18 Ni, Zhang, Chen (bb0185) 2019; 26 Brackenbury, Brilakis, DeJong (bb0230) 2019 Zou, Zhang, Li, Qi, Wang, Wang (bb0385) 2019; 28 David Jenkins, Carr, Iglesias, Buggy, Morison (bb0145) 2018 Chen, Lin, Yao (bb0225) 2019; 7 Abadi, Agarwal, Barham, Brevdo, Chen, Citro, Corrado, Davis, Dean, Devin, Ghemawat, Goodfellow, Harp, Irving, Isard, Jia, Jozefowicz, Kaiser, Kudlur, Levenberg, Mane, Monga, Moore, Murray, Olah, Schuster, Shlens, Steiner, Sutskever, Talwar, Tucker, Vanhoucke, Vasudevan, Viegas, Vinyals, Warden, Wattenberg, Wicke, Yu, Zheng (bb0195) 2016 Konig, Jenkins, Barrie, Mannion, Morison (bb0140) 2019 Szegedy, Vanhoucke, Ioffe, Shlens, Wojna (bb0310) 2016 Redmon (10.1016/j.autcon.2021.103606_bb0170) 2018 Gao (10.1016/j.autcon.2021.103606_bb0210) 2018; 33 Ni (10.1016/j.autcon.2021.103606_bb0185) 2019; 26 Garcia-Garcia (10.1016/j.autcon.2021.103606_bb0105) 2017 Konig (10.1016/j.autcon.2021.103606_bb0140) 2019 Chambon (10.1016/j.autcon.2021.103606_bb0380) 2011; 2011 Rosebrock (10.1016/j.autcon.2021.103606_bb0045) Kang (10.1016/j.autcon.2021.103606_bb0220) 2020; 118 Özgenel (10.1016/j.autcon.2021.103606_bb0240) 2018 Tomazevic (10.1016/j.autcon.2021.103606_bb0005) 1999 Lin (10.1016/j.autcon.2021.103606_bb0370) 2020; 42 Chen (10.1016/j.autcon.2021.103606_bb0090) 2018; 40 Tabernik (10.1016/j.autcon.2021.103606_bb0290) 2020; 31 Laefer (10.1016/j.autcon.2021.103606_bb0030) 2010; 16 Ibrahim (10.1016/j.autcon.2021.103606_bb0250) 2019 Huang (10.1016/j.autcon.2021.103606_bb0335) 2017 Shi (10.1016/j.autcon.2021.103606_bb0390) 2016; 17 Huang (10.1016/j.autcon.2021.103606_bb0315) 2017 Wang (10.1016/j.autcon.2021.103606_bb0260) 2019; 103 Long (10.1016/j.autcon.2021.103606_bb0110) 2015 Zhang (10.1016/j.autcon.2021.103606_bb0270) 2020 Gilbert (10.1016/j.autcon.2021.103606_bb0020) 2009 Spencer (10.1016/j.autcon.2021.103606_bb0035) 2019; 5 Najimi (10.1016/j.autcon.2021.103606_bb0255) 2014 Abadi (10.1016/j.autcon.2021.103606_bb0195) 2016 Brackenbury (10.1016/j.autcon.2021.103606_bb0230) 2019 Zhang (10.1016/j.autcon.2021.103606_bb0375) 2017; 32 Kim (10.1016/j.autcon.2021.103606_bb0050) 2018; 18 Zou (10.1016/j.autcon.2021.103606_bb0385) 2019; 28 Liu (10.1016/j.autcon.2021.103606_bb0085) 2019; 338 Valero (10.1016/j.autcon.2021.103606_bb0245) 2019; 106 Szegedy (10.1016/j.autcon.2021.103606_bb0310) 2016 Xu (10.1016/j.autcon.2021.103606_bb0355) 2019; 9 Bal (10.1016/j.autcon.2021.103606_bb0015) 2020 Zhang (10.1016/j.autcon.2021.103606_bb0065) 2019; 9 Liu (10.1016/j.autcon.2021.103606_bb0295) 2015 Sandler (10.1016/j.autcon.2021.103606_bb0305) 2018 (10.1016/j.autcon.2021.103606_bb0395) 2019 Dung (10.1016/j.autcon.2021.103606_bb0115) 2019; 99 Chollet (10.1016/j.autcon.2021.103606_bb0330) Alipour (10.1016/j.autcon.2021.103606_bb0235) 2020; 206 Alipour (10.1016/j.autcon.2021.103606_bb0285) 2019; 33 He (10.1016/j.autcon.2021.103606_bb0320) 2016 Cha (10.1016/j.autcon.2021.103606_bb0075) 2017; 32 Phares (10.1016/j.autcon.2021.103606_bb0025) 2004; 9 Choi (10.1016/j.autcon.2021.103606_bb0095) 2020; 67 Howard (10.1016/j.autcon.2021.103606_bb0300) 2017 Chollet (10.1016/j.autcon.2021.103606_bb0190) 2017 Maeda (10.1016/j.autcon.2021.103606_bb0345) 2018; 33 Yang (10.1016/j.autcon.2021.103606_bb0120) 2018; 33 Dorafshan (10.1016/j.autcon.2021.103606_bb0275) 2018; 186 Bang (10.1016/j.autcon.2021.103606_bb0205) 2019; 34 Ali (10.1016/j.autcon.2021.103606_bb0265) 2019; 17 Chen (10.1016/j.autcon.2021.103606_bb0365) 2018 Dais (10.1016/j.autcon.2021.103606_bb0010) 2019 Yang (10.1016/j.autcon.2021.103606_bb0200) 2020; 116 Lin (10.1016/j.autcon.2021.103606_bb0160) 2017 Ma (10.1016/j.autcon.2021.103606_bb0155) 2020; 20 Li (10.1016/j.autcon.2021.103606_bb0100) 2018; 18 Kingma (10.1016/j.autcon.2021.103606_bb0360) 2015 Song (10.1016/j.autcon.2021.103606_bb0350) 2019; 7 Hoskere (10.1016/j.autcon.2021.103606_bb0130) 2020; 10 Li (10.1016/j.autcon.2021.103606_bb0125) 2019; 34 Kalfarisi (10.1016/j.autcon.2021.103606_bb0215) 2020; 34 Liu (10.1016/j.autcon.2021.103606_bb0150) 2019; 104 Yang (10.1016/j.autcon.2021.103606_bb0175) 2020; 21 David Jenkins (10.1016/j.autcon.2021.103606_bb0145) 2018 Zhang (10.1016/j.autcon.2021.103606_bb0180) 2018 Mohtasham Khani (10.1016/j.autcon.2021.103606_bb0055) 2020; 19 Mei (10.1016/j.autcon.2021.103606_bb0280) 2020; 110 Zhang (10.1016/j.autcon.2021.103606_bb0060) 2018; 32 Yakubovskiy (10.1016/j.autcon.2021.103606_bb0325) Zhao (10.1016/j.autcon.2021.103606_bb0040) 2019; 30 Cha (10.1016/j.autcon.2021.103606_bb0080) 2018; 33 Feng (10.1016/j.autcon.2021.103606_bb0070) 2019; 23 Ronneberger (10.1016/j.autcon.2021.103606_bb0135) 2015; 9351 He (10.1016/j.autcon.2021.103606_bb0165) 2017 Chen (10.1016/j.autcon.2021.103606_bb0225) 2019; 7 Liu (10.1016/j.autcon.2021.103606_bb0340) 2016 |
| References_xml | – volume: 338 start-page: 139 year: 2019 end-page: 153 ident: bb0085 article-title: DeepCrack: a deep hierarchical feature learning architecture for crack segmentation publication-title: Neurocomputing – start-page: 1460 year: 2019 end-page: 1464 ident: bb0140 article-title: A convolutional neural network for pavement surface crack segmentation using residual connections and attention gating publication-title: 2019 IEEE International Conference on Image Processing (ICIP) – start-page: 21 year: 2016 end-page: 37 ident: bb0340 article-title: SSD: Single Shot MultiBox Detector publication-title: Computer Vision – ECCV 2016. ECCV 2016. Lecture Notes in Computer Science – volume: 5 start-page: 199 year: 2019 end-page: 222 ident: bb0035 article-title: Advances in computer vision-based civil infrastructure inspection and monitoring publication-title: Engineering – start-page: 1 year: 2014 end-page: 6 ident: bb0255 article-title: Assessing the condition of railway assets using DIFCAM: Results from tunnel examinations publication-title: 6th IET Conference on Railway Condition Monitoring (RCM 2014) – start-page: 3296 year: 2017 end-page: 3297 ident: bb0335 article-title: Speed/accuracy trade-offs for modern convolutional object detectors publication-title: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – start-page: 3431 year: 2015 end-page: 3440 ident: bb0110 article-title: Fully convolutional networks for semantic segmentation publication-title: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – volume: 32 start-page: 361 year: 2017 end-page: 378 ident: bb0075 article-title: Deep learning-based crack damage detection using convolutional neural Networks publication-title: Comput. Aided Civil Infrastruct. Eng. – volume: 33 start-page: 1090 year: 2018 end-page: 1109 ident: bb0120 article-title: Automatic pixel-level crack detection and measurement using fully convolutional network publication-title: Comput. Aided Civil Infrastruct. Eng. – start-page: 2120 year: 2018 end-page: 2124 ident: bb0145 article-title: A deep convolutional neural network for semantic pixel-wise segmentation of road and pavement surface cracks publication-title: 2018 26th European Signal Processing Conference (EUSIPCO) – start-page: 2261 year: 2017 end-page: 2269 ident: bb0315 article-title: Densely connected convolutional networks publication-title: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – start-page: 3320 year: 2019 end-page: 3328 ident: bb0395 article-title: How transferable are features in deep neural networks? publication-title: Advances in Neural Information Processing Systems 27 – volume: 18 start-page: 3042 year: 2018 ident: bb0100 article-title: Pixel-wise crack detection using deep local pattern predictor for robot application publication-title: Sensors – year: 2017 ident: bb0105 article-title: A review on deep learning techniques applied to semantic segmentation publication-title: ArXiv – volume: 32 start-page: 805 year: 2017 end-page: 819 ident: bb0375 article-title: Automated pixel-level pavement crack detection on 3D asphalt surfaces using a deep-learning network publication-title: Comput. Aided Civil Infrastruct. Eng. – year: 1999 ident: bb0005 article-title: Earthquake-Resistant Design of Masonry Buildings – volume: 10 start-page: 757 year: 2020 end-page: 773 ident: bb0130 article-title: MaDnet: multi-task semantic segmentation of multiple types of structural materials and damage in images of civil infrastructure publication-title: J. Civ. Struct. Heal. Monit. – start-page: 1 year: 2020 end-page: 14 ident: bb0270 article-title: CrackGAN: pavement crack detection using partially accurate ground truths based on generative adversarial learning publication-title: IEEE Transactions on Intelligent Transportation Systems – volume: 32 year: 2018 ident: bb0060 article-title: Deep learning–based fully automated pavement crack detection on 3D asphalt surfaces with an improved CrackNet publication-title: J. Comput. Civ. Eng. – start-page: 1 year: 2020 end-page: 18 ident: bb0015 article-title: Monitoring of a historical masonry structure in case of induced seismicity publication-title: Int. J. Architect. Herit. – volume: 104 start-page: 129 year: 2019 end-page: 139 ident: bb0150 article-title: Computer vision-based concrete crack detection using U-net fully convolutional networks publication-title: Autom. Constr. – start-page: 4510 year: 2018 end-page: 4520 ident: bb0305 article-title: MobileNetV2: inverted residuals and linear bottlenecks publication-title: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition – volume: 17 start-page: 3434 year: 2016 end-page: 3445 ident: bb0390 article-title: Automatic road crack detection using random structured forests publication-title: IEEE Trans. Intell. Transp. Syst. – volume: 9 start-page: 2867 year: 2019 ident: bb0355 article-title: Automatic bridge crack detection using a convolutional neural network publication-title: Appl. Sci. – volume: 21 start-page: 1525 year: 2020 end-page: 1535 ident: bb0175 article-title: Feature pyramid and hierarchical boosting network for pavement crack detection publication-title: IEEE Trans. Intell. Transp. Syst. – volume: 34 start-page: 713 year: 2019 end-page: 727 ident: bb0205 article-title: Encoder–decoder network for pixel-level road crack detection in black-box images publication-title: Comput. Aided Civil Infrastruct. Eng. – volume: 33 start-page: 731 year: 2018 end-page: 747 ident: bb0080 article-title: Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types publication-title: Comput. Aided Civil Infrastruct. Eng. – volume: 186 start-page: 1031 year: 2018 end-page: 1045 ident: bb0275 article-title: Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete publication-title: Constr. Build. Mater. – volume: 33 year: 2019 ident: bb0285 article-title: Robust pixel-level crack detection using deep fully convolutional neural Networks publication-title: J. Comput. Civ. Eng. – volume: 118 start-page: 103291 year: 2020 ident: bb0220 article-title: Hybrid pixel-level concrete crack segmentation and quantification across complex backgrounds using deep learning publication-title: Autom. Constr. – start-page: 833 year: 2018 end-page: 851 ident: bb0365 article-title: Encoder-decoder with atrous separable convolution for semantic image segmentation publication-title: Computer Vision – ECCV 2018. ECCV 2018. Lecture Notes in Computer Science – volume: 7 start-page: 64186 year: 2019 end-page: 64197 ident: bb0350 article-title: Real-time tunnel crack analysis system via deep learning publication-title: IEEE Access – volume: 40 start-page: 834 year: 2018 end-page: 848 ident: bb0090 article-title: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 103 start-page: 53 year: 2019 end-page: 66 ident: bb0260 article-title: Automatic damage detection of historic masonry buildings based on mobile deep learning publication-title: Autom. Constr. – volume: 42 start-page: 318 year: 2020 end-page: 327 ident: bb0370 article-title: Focal loss for dense object detection publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 30 start-page: 3212 year: 2019 end-page: 3232 ident: bb0040 article-title: Object detection with deep learning: a review publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 34 start-page: 616 year: 2019 end-page: 634 ident: bb0125 article-title: Automatic pixel-level multiple damage detection of concrete structure using fully convolutional network publication-title: Comput. Aided Civil Infrastruct. Eng. – volume: 20 start-page: 717 year: 2020 ident: bb0155 article-title: Automatic tunnel crack detection based on U-net and a convolutional neural network with alternately updated clique publication-title: Sensors – start-page: 936 year: 2017 end-page: 944 ident: bb0160 article-title: Feature pyramid networks for object detection publication-title: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – year: 2016 ident: bb0195 article-title: TensorFlow: large-scale machine learning on heterogeneous distributed systems publication-title: ArXiv – start-page: 2980 year: 2017 end-page: 2988 ident: bb0165 article-title: Mask R-CNN publication-title: 2017 IEEE International Conference on Computer Vision (ICCV) – volume: 206 start-page: 110157 year: 2020 ident: bb0235 article-title: Increasing the robustness of material-specific deep learning models for crack detection across different materials publication-title: Eng. Struct. – volume: 67 start-page: 8016 year: 2020 end-page: 8025 ident: bb0095 article-title: SDDNet: real-time crack segmentation publication-title: IEEE Trans. Ind. Electron. – volume: 110 start-page: 103018 year: 2020 ident: bb0280 article-title: Densely connected deep neural network considering connectivity of pixels for automatic crack detection publication-title: Autom. Constr. – start-page: 2818 year: 2016 end-page: 2826 ident: bb0310 article-title: Rethinking the inception architecture for computer vision publication-title: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – volume: 106 start-page: 102846 year: 2019 ident: bb0245 article-title: Automated defect detection and classification in ashlar masonry walls using machine learning publication-title: Autom. Constr. – start-page: 730 year: 2015 end-page: 734 ident: bb0295 article-title: Very deep convolutional neural network based image classification using small training sample size publication-title: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) – start-page: 693 year: 2018 end-page: 700 ident: bb0240 article-title: Performance comparison of pretrained convolutional neural networks on crack detection in buildings publication-title: Proceedings of the 35th International Symposium on Automation and Robotics in Construction (ISARC), Berlin, Germany – volume: 7 start-page: 186657 year: 2019 end-page: 186670 ident: bb0225 article-title: Improving the efficiency of encoder-decoder architecture for pixel-level crack detection publication-title: IEEE Access. – start-page: 58 year: 2009 end-page: 95 ident: bb0020 article-title: Fatigue in railway bridges publication-title: Fatigue in Railway Infrastructure – start-page: 3 year: 2019 end-page: 9 ident: bb0230 article-title: Automated Defect Detection For Masonry Arch Bridges, International Conference on Smart Infrastructure and Construction 2019 (ICSIC) – year: 2019 ident: bb0325 article-title: Segmentation Models, GitHub – year: 2017 ident: bb0300 article-title: MobileNets: efficient convolutional neural networks for mobile vision applications publication-title: ArXiv – volume: 9351 start-page: 234 year: 2015 end-page: 241 ident: bb0135 article-title: U-net: convolutional networks for biomedical image segmentation publication-title: Med. Image Comput. Comput. Assist.Interv. (MICCAI) – year: 2018 ident: bb0180 article-title: Bridge damage detection using a single-stage detector and field inspection images publication-title: ArXiv – volume: 17 start-page: 98 year: 2019 end-page: 105 ident: bb0265 article-title: Damage detection and localization in masonry structure using faster region convolutional networks publication-title: Int. J. GEOMATE – volume: 99 start-page: 52 year: 2019 end-page: 58 ident: bb0115 article-title: Autonomous concrete crack detection using deep fully convolutional neural network publication-title: Autom. Constr. – volume: 116 start-page: 103199 year: 2020 ident: bb0200 article-title: Deep convolution neural network-based transfer learning method for civil infrastructure crack detection publication-title: Autom. Constr. – year: 2015 ident: bb0330 article-title: Keras – volume: 28 start-page: 1498 year: 2019 end-page: 1512 ident: bb0385 article-title: DeepCrack: learning hierarchical convolutional features for crack detection publication-title: IEEE Trans. Image Process. – volume: 16 start-page: 129 year: 2010 end-page: 137 ident: bb0030 article-title: Reliability of crack detection methods for baseline condition assessments publication-title: J. Infrastruct. Syst. – volume: 33 start-page: 748 year: 2018 end-page: 768 ident: bb0210 article-title: Deep transfer learning for image-based structural damage recognition publication-title: Comput. Aided Civil Infrastruct. Eng. – volume: 2011 start-page: 1 year: 2011 end-page: 20 ident: bb0380 article-title: Automatic road pavement assessment with image processing: review and comparison publication-title: Int. J. Geophys. – volume: 19 start-page: 1440 year: 2020 end-page: 1452 ident: bb0055 article-title: Deep-learning-based crack detection with applications for the structural health monitoring of gas turbines publication-title: Struct. Health Monit. – year: 2017 ident: bb0045 article-title: Deep Learning for Computer Vision with Python – year: 2017 ident: bb0190 article-title: Deep Learning with Python – volume: 23 start-page: 4493 year: 2019 end-page: 4502 ident: bb0070 article-title: Structural damage detection using deep convolutional neural network and transfer learning publication-title: KSCE J. Civ. Eng. – volume: 26 year: 2019 ident: bb0185 article-title: Pixel-level crack delineation in images with convolutional feature fusion publication-title: Struct. Control. Health Monit. – year: 2015 ident: bb0360 article-title: Adam: A method for stochastic optimization publication-title: 3rd International Conference on Learning Representations (ICLR 2015), San Diego, USA – volume: 34 year: 2020 ident: bb0215 article-title: Crack detection and segmentation using deep learning with 3D reality mesh model for quantitative assessment and integrated visualization publication-title: J. Comput. Civ. Eng. – volume: 9 start-page: 403 year: 2004 end-page: 413 ident: bb0025 article-title: Routine highway bridge inspection condition documentation accuracy and reliability publication-title: J. Bridg. Eng. – volume: 9 start-page: 2686 year: 2019 ident: bb0065 article-title: Concrete cracks detection based on FCN with dilated convolution publication-title: Appl. Sci. – volume: 31 start-page: 759 year: 2020 end-page: 776 ident: bb0290 article-title: Segmentation-based deep-learning approach for surface-defect detection publication-title: J. Intell. Manuf. – start-page: 770 year: 2016 end-page: 778 ident: bb0320 article-title: Deep residual learning for image recognition publication-title: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – volume: 33 start-page: 1127 year: 2018 end-page: 1141 ident: bb0345 article-title: Road damage detection and classification using deep neural networks with smartphone images publication-title: Comput. Aided Civil Infrastruct. Eng. – volume: 18 start-page: 1881 year: 2018 ident: bb0050 article-title: Application of crack identification techniques for an aging concrete bridge inspection using an unmanned aerial vehicle publication-title: Sensors – year: 2018 ident: bb0170 article-title: YOLOv3: an incremental improvement publication-title: ArXiv – start-page: 332 year: 2019 end-page: 344 ident: bb0250 article-title: CNN-based watershed marker extraction for brick segmentation in masonry walls publication-title: Image Analysis and Recognition. ICIAR 2019 – year: 2019 ident: bb0010 article-title: Investigations on the restoration and seismic enhancement options for the Jaisedewal Temple after the Gorkha earthquake in Nepal publication-title: SECED 2019 Conference, Greenwich, UK – volume: 33 start-page: 1127 issue: 12 year: 2018 ident: 10.1016/j.autcon.2021.103606_bb0345 article-title: Road damage detection and classification using deep neural networks with smartphone images publication-title: Comput. Aided Civil Infrastruct. Eng. doi: 10.1111/mice.12387 – start-page: 21 year: 2016 ident: 10.1016/j.autcon.2021.103606_bb0340 article-title: SSD: Single Shot MultiBox Detector – volume: 32 issue: 5 year: 2018 ident: 10.1016/j.autcon.2021.103606_bb0060 article-title: Deep learning–based fully automated pavement crack detection on 3D asphalt surfaces with an improved CrackNet publication-title: J. Comput. Civ. Eng. doi: 10.1061/(ASCE)CP.1943-5487.0000775 – volume: 18 start-page: 3042 issue: 9 year: 2018 ident: 10.1016/j.autcon.2021.103606_bb0100 article-title: Pixel-wise crack detection using deep local pattern predictor for robot application publication-title: Sensors doi: 10.3390/s18093042 – year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0010 article-title: Investigations on the restoration and seismic enhancement options for the Jaisedewal Temple after the Gorkha earthquake in Nepal – volume: 9351 start-page: 234 year: 2015 ident: 10.1016/j.autcon.2021.103606_bb0135 article-title: U-net: convolutional networks for biomedical image segmentation publication-title: Med. Image Comput. Comput. Assist.Interv. (MICCAI) – start-page: 2261 year: 2017 ident: 10.1016/j.autcon.2021.103606_bb0315 article-title: Densely connected convolutional networks – year: 2015 ident: 10.1016/j.autcon.2021.103606_bb0360 article-title: Adam: A method for stochastic optimization – start-page: 3296 year: 2017 ident: 10.1016/j.autcon.2021.103606_bb0335 article-title: Speed/accuracy trade-offs for modern convolutional object detectors – volume: 32 start-page: 361 issue: 5 year: 2017 ident: 10.1016/j.autcon.2021.103606_bb0075 article-title: Deep learning-based crack damage detection using convolutional neural Networks publication-title: Comput. Aided Civil Infrastruct. Eng. doi: 10.1111/mice.12263 – start-page: 3431 year: 2015 ident: 10.1016/j.autcon.2021.103606_bb0110 article-title: Fully convolutional networks for semantic segmentation – volume: 99 start-page: 52 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0115 article-title: Autonomous concrete crack detection using deep fully convolutional neural network publication-title: Autom. Constr. doi: 10.1016/j.autcon.2018.11.028 – start-page: 2980 year: 2017 ident: 10.1016/j.autcon.2021.103606_bb0165 article-title: Mask R-CNN – start-page: 770 year: 2016 ident: 10.1016/j.autcon.2021.103606_bb0320 article-title: Deep residual learning for image recognition – start-page: 936 year: 2017 ident: 10.1016/j.autcon.2021.103606_bb0160 article-title: Feature pyramid networks for object detection – volume: 110 start-page: 103018 year: 2020 ident: 10.1016/j.autcon.2021.103606_bb0280 article-title: Densely connected deep neural network considering connectivity of pixels for automatic crack detection publication-title: Autom. Constr. doi: 10.1016/j.autcon.2019.103018 – start-page: 1 year: 2020 ident: 10.1016/j.autcon.2021.103606_bb0270 article-title: CrackGAN: pavement crack detection using partially accurate ground truths based on generative adversarial learning – volume: 9 start-page: 2867 issue: 14 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0355 article-title: Automatic bridge crack detection using a convolutional neural network publication-title: Appl. Sci. doi: 10.3390/app9142867 – year: 2018 ident: 10.1016/j.autcon.2021.103606_bb0170 article-title: YOLOv3: an incremental improvement publication-title: ArXiv – year: 2018 ident: 10.1016/j.autcon.2021.103606_bb0180 article-title: Bridge damage detection using a single-stage detector and field inspection images publication-title: ArXiv – volume: 2011 start-page: 1 year: 2011 ident: 10.1016/j.autcon.2021.103606_bb0380 article-title: Automatic road pavement assessment with image processing: review and comparison publication-title: Int. J. Geophys. doi: 10.1155/2011/989354 – volume: 42 start-page: 318 issue: 2 year: 2020 ident: 10.1016/j.autcon.2021.103606_bb0370 article-title: Focal loss for dense object detection publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2018.2858826 – start-page: 1 year: 2020 ident: 10.1016/j.autcon.2021.103606_bb0015 article-title: Monitoring of a historical masonry structure in case of induced seismicity publication-title: Int. J. Architect. Herit. – ident: 10.1016/j.autcon.2021.103606_bb0330 – volume: 40 start-page: 834 issue: 4 year: 2018 ident: 10.1016/j.autcon.2021.103606_bb0090 article-title: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2017.2699184 – volume: 338 start-page: 139 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0085 article-title: DeepCrack: a deep hierarchical feature learning architecture for crack segmentation publication-title: Neurocomputing doi: 10.1016/j.neucom.2019.01.036 – volume: 26 issue: 1 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0185 article-title: Pixel-level crack delineation in images with convolutional feature fusion publication-title: Struct. Control. Health Monit. doi: 10.1002/stc.2286 – year: 2016 ident: 10.1016/j.autcon.2021.103606_bb0195 article-title: TensorFlow: large-scale machine learning on heterogeneous distributed systems publication-title: ArXiv – volume: 104 start-page: 129 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0150 article-title: Computer vision-based concrete crack detection using U-net fully convolutional networks publication-title: Autom. Constr. doi: 10.1016/j.autcon.2019.04.005 – start-page: 693 year: 2018 ident: 10.1016/j.autcon.2021.103606_bb0240 article-title: Performance comparison of pretrained convolutional neural networks on crack detection in buildings – volume: 28 start-page: 1498 issue: 3 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0385 article-title: DeepCrack: learning hierarchical convolutional features for crack detection publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2018.2878966 – volume: 33 start-page: 731 issue: 9 year: 2018 ident: 10.1016/j.autcon.2021.103606_bb0080 article-title: Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types publication-title: Comput. Aided Civil Infrastruct. Eng. doi: 10.1111/mice.12334 – volume: 116 start-page: 103199 year: 2020 ident: 10.1016/j.autcon.2021.103606_bb0200 article-title: Deep convolution neural network-based transfer learning method for civil infrastructure crack detection publication-title: Autom. Constr. doi: 10.1016/j.autcon.2020.103199 – start-page: 2818 year: 2016 ident: 10.1016/j.autcon.2021.103606_bb0310 article-title: Rethinking the inception architecture for computer vision – volume: 17 start-page: 3434 issue: 12 year: 2016 ident: 10.1016/j.autcon.2021.103606_bb0390 article-title: Automatic road crack detection using random structured forests publication-title: IEEE Trans. Intell. Transp. Syst. doi: 10.1109/TITS.2016.2552248 – volume: 31 start-page: 759 issue: 3 year: 2020 ident: 10.1016/j.autcon.2021.103606_bb0290 article-title: Segmentation-based deep-learning approach for surface-defect detection publication-title: J. Intell. Manuf. doi: 10.1007/s10845-019-01476-x – start-page: 332 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0250 article-title: CNN-based watershed marker extraction for brick segmentation in masonry walls – volume: 67 start-page: 8016 issue: 9 year: 2020 ident: 10.1016/j.autcon.2021.103606_bb0095 article-title: SDDNet: real-time crack segmentation publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2019.2945265 – start-page: 2120 year: 2018 ident: 10.1016/j.autcon.2021.103606_bb0145 article-title: A deep convolutional neural network for semantic pixel-wise segmentation of road and pavement surface cracks – start-page: 1 year: 2014 ident: 10.1016/j.autcon.2021.103606_bb0255 article-title: Assessing the condition of railway assets using DIFCAM: Results from tunnel examinations – volume: 7 start-page: 186657 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0225 article-title: Improving the efficiency of encoder-decoder architecture for pixel-level crack detection publication-title: IEEE Access. doi: 10.1109/ACCESS.2019.2961375 – ident: 10.1016/j.autcon.2021.103606_bb0325 – start-page: 833 year: 2018 ident: 10.1016/j.autcon.2021.103606_bb0365 article-title: Encoder-decoder with atrous separable convolution for semantic image segmentation – year: 1999 ident: 10.1016/j.autcon.2021.103606_bb0005 – year: 2017 ident: 10.1016/j.autcon.2021.103606_bb0300 article-title: MobileNets: efficient convolutional neural networks for mobile vision applications publication-title: ArXiv – volume: 9 start-page: 403 issue: 4 year: 2004 ident: 10.1016/j.autcon.2021.103606_bb0025 article-title: Routine highway bridge inspection condition documentation accuracy and reliability publication-title: J. Bridg. Eng. doi: 10.1061/(ASCE)1084-0702(2004)9:4(403) – year: 2017 ident: 10.1016/j.autcon.2021.103606_bb0105 article-title: A review on deep learning techniques applied to semantic segmentation publication-title: ArXiv – ident: 10.1016/j.autcon.2021.103606_bb0045 – volume: 9 start-page: 2686 issue: 13 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0065 article-title: Concrete cracks detection based on FCN with dilated convolution publication-title: Appl. Sci. doi: 10.3390/app9132686 – start-page: 3320 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0395 article-title: How transferable are features in deep neural networks? – volume: 21 start-page: 1525 issue: 4 year: 2020 ident: 10.1016/j.autcon.2021.103606_bb0175 article-title: Feature pyramid and hierarchical boosting network for pavement crack detection publication-title: IEEE Trans. Intell. Transp. Syst. doi: 10.1109/TITS.2019.2910595 – volume: 33 start-page: 748 issue: 9 year: 2018 ident: 10.1016/j.autcon.2021.103606_bb0210 article-title: Deep transfer learning for image-based structural damage recognition publication-title: Comput. Aided Civil Infrastruct. Eng. doi: 10.1111/mice.12363 – volume: 19 start-page: 1440 issue: 5 year: 2020 ident: 10.1016/j.autcon.2021.103606_bb0055 article-title: Deep-learning-based crack detection with applications for the structural health monitoring of gas turbines publication-title: Struct. Health Monit. doi: 10.1177/1475921719883202 – volume: 10 start-page: 757 issue: 5 year: 2020 ident: 10.1016/j.autcon.2021.103606_bb0130 article-title: MaDnet: multi-task semantic segmentation of multiple types of structural materials and damage in images of civil infrastructure publication-title: J. Civ. Struct. Heal. Monit. doi: 10.1007/s13349-020-00409-0 – volume: 33 start-page: 1090 issue: 12 year: 2018 ident: 10.1016/j.autcon.2021.103606_bb0120 article-title: Automatic pixel-level crack detection and measurement using fully convolutional network publication-title: Comput. Aided Civil Infrastruct. Eng. doi: 10.1111/mice.12412 – volume: 17 start-page: 98 issue: 59 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0265 article-title: Damage detection and localization in masonry structure using faster region convolutional networks publication-title: Int. J. GEOMATE doi: 10.21660/2019.59.8272 – start-page: 1460 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0140 article-title: A convolutional neural network for pavement surface crack segmentation using residual connections and attention gating – start-page: 730 year: 2015 ident: 10.1016/j.autcon.2021.103606_bb0295 article-title: Very deep convolutional neural network based image classification using small training sample size – volume: 206 start-page: 110157 year: 2020 ident: 10.1016/j.autcon.2021.103606_bb0235 article-title: Increasing the robustness of material-specific deep learning models for crack detection across different materials publication-title: Eng. Struct. doi: 10.1016/j.engstruct.2019.110157 – volume: 186 start-page: 1031 year: 2018 ident: 10.1016/j.autcon.2021.103606_bb0275 article-title: Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete publication-title: Constr. Build. Mater. doi: 10.1016/j.conbuildmat.2018.08.011 – start-page: 4510 year: 2018 ident: 10.1016/j.autcon.2021.103606_bb0305 article-title: MobileNetV2: inverted residuals and linear bottlenecks – volume: 5 start-page: 199 issue: 2 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0035 article-title: Advances in computer vision-based civil infrastructure inspection and monitoring publication-title: Engineering doi: 10.1016/j.eng.2018.11.030 – volume: 20 start-page: 717 issue: 3 year: 2020 ident: 10.1016/j.autcon.2021.103606_bb0155 article-title: Automatic tunnel crack detection based on U-net and a convolutional neural network with alternately updated clique publication-title: Sensors doi: 10.3390/s20030717 – volume: 32 start-page: 805 issue: 10 year: 2017 ident: 10.1016/j.autcon.2021.103606_bb0375 article-title: Automated pixel-level pavement crack detection on 3D asphalt surfaces using a deep-learning network publication-title: Comput. Aided Civil Infrastruct. Eng. doi: 10.1111/mice.12297 – volume: 16 start-page: 129 issue: 2 year: 2010 ident: 10.1016/j.autcon.2021.103606_bb0030 article-title: Reliability of crack detection methods for baseline condition assessments publication-title: J. Infrastruct. Syst. doi: 10.1061/(ASCE)1076-0342(2010)16:2(129) – volume: 34 issue: 3 year: 2020 ident: 10.1016/j.autcon.2021.103606_bb0215 article-title: Crack detection and segmentation using deep learning with 3D reality mesh model for quantitative assessment and integrated visualization publication-title: J. Comput. Civ. Eng. doi: 10.1061/(ASCE)CP.1943-5487.0000890 – volume: 34 start-page: 616 issue: 7 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0125 article-title: Automatic pixel-level multiple damage detection of concrete structure using fully convolutional network publication-title: Comput. Aided Civil Infrastruct. Eng. doi: 10.1111/mice.12433 – volume: 34 start-page: 713 issue: 8 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0205 article-title: Encoder–decoder network for pixel-level road crack detection in black-box images publication-title: Comput. Aided Civil Infrastruct. Eng. doi: 10.1111/mice.12440 – volume: 7 start-page: 64186 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0350 article-title: Real-time tunnel crack analysis system via deep learning publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2916330 – start-page: 3 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0230 – volume: 103 start-page: 53 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0260 article-title: Automatic damage detection of historic masonry buildings based on mobile deep learning publication-title: Autom. Constr. doi: 10.1016/j.autcon.2019.03.003 – volume: 23 start-page: 4493 issue: 10 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0070 article-title: Structural damage detection using deep convolutional neural network and transfer learning publication-title: KSCE J. Civ. Eng. doi: 10.1007/s12205-019-0437-z – volume: 118 start-page: 103291 year: 2020 ident: 10.1016/j.autcon.2021.103606_bb0220 article-title: Hybrid pixel-level concrete crack segmentation and quantification across complex backgrounds using deep learning publication-title: Autom. Constr. doi: 10.1016/j.autcon.2020.103291 – start-page: 58 year: 2009 ident: 10.1016/j.autcon.2021.103606_bb0020 article-title: Fatigue in railway bridges – volume: 30 start-page: 3212 issue: 11 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0040 article-title: Object detection with deep learning: a review publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2018.2876865 – volume: 18 start-page: 1881 issue: 6 year: 2018 ident: 10.1016/j.autcon.2021.103606_bb0050 article-title: Application of crack identification techniques for an aging concrete bridge inspection using an unmanned aerial vehicle publication-title: Sensors doi: 10.3390/s18061881 – volume: 33 issue: 6 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0285 article-title: Robust pixel-level crack detection using deep fully convolutional neural Networks publication-title: J. Comput. Civ. Eng. doi: 10.1061/(ASCE)CP.1943-5487.0000854 – year: 2017 ident: 10.1016/j.autcon.2021.103606_bb0190 – volume: 106 start-page: 102846 year: 2019 ident: 10.1016/j.autcon.2021.103606_bb0245 article-title: Automated defect detection and classification in ashlar masonry walls using machine learning publication-title: Autom. Constr. doi: 10.1016/j.autcon.2019.102846 |
| SSID | ssj0007069 |
| ScopusCitedReferencesCount | 288 |
| ScopusCitedReferencesURI | http://www.scopus.com/scopus/openurl/link.url?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&svc_val_fmt=info:ofi/fmt:kev:mtx:sch_svc&svc.citedby=yes&rft_id=info:eid/2-s2.0-85101393356&rfr_dat=partnerID:45 |
| ScopusEID | 2-s2.0-85101393356 |
| Score | 2.7090437 |
| Snippet | Masonry structures represent the highest proportion of building stock worldwide. Currently, the structural condition of such structures is predominantly... |
| Source | Elsevier Scopus |
| SourceID | proquest crossref scopus elsevier |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 103606 |
| SubjectTerms | Artificial neural networks Classification CNN Computer vision Crack detection Deep learning Digital imaging Image segmentation Inspection Machine learning Masonry Pixels Segmentation Transfer learning |
| Title | Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning |
| URI | https://dx.doi.org/10.1016/j.autcon.2021.103606 https://www.proquest.com/docview/2532196258 |
| Volume | 125 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://knihovny.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3dS9xAEF-KPrRSbLWVnr3KCvoYLtnN5uPxvFb6cBRp9cWXZT-S6ylGyYd4D_3fO7PZyAmCUAqBkLAJm8xk5jfk95sl5CgKc6jXRBIwFRooULgNlFbgy4XVSmujuUDt8I85vzhjl3NskjQbtDBIq_Sxv4_pLlr7MxP_Nid3y-XkV5gzSJ8oPkXg4XTkHDwKWz1-PXmMxmmY9P32WBLg6EE-5zheqmux6mSQ6FB9nuC6R8-np3X4iXqRrllLQ6fv_ssDvCfbHoXSaT9uh7wqql3yehApN7tka61P4QfyZ9q1t663KzW1MtfUIOZGkpGzK1WVpU2xuPE6porCdqMAydcr2nR1ibQvigz7BUWWu_d2mAB203Q7x0Vv3I1aB6WLmvoFLRYfycXpt_PZ98Cv2xAYKC7bILc502khCkAv2moRq8iWIiuw9ZxNbFnGNk5QtJuWLFImj7llVmgo5USqbBjzPfJWIb-_ap0O0H4i1FiRlCkXMf44zCKTq1wnFtBbzHRUZnZEgsFu8q7v0yEHAtuV7O0s0c6yt_OIpINx5RNzSUglL1w5HnxB-u-9kUxwCP1QS2Yjctj7x-M0mGyYDGWG0Y_nnAu4xfGLY2T70O7_8yQ_kzd41DMzx2SjrbviC9Qc1fL37X21OiCb09nP-dmB-1b-ApkgHWs |
| linkProvider | Elsevier |
| linkToHtml | http://knihovny.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bS9xAFB6kPtgirbUtbrV2CvUxbDKTyeXRSxfFrRSqL32ZziVZt2KUXEQf-t97zmQiWygIUiEQSCbDJGfmnPOR7ztDyOcozAGviSRgKjQAULgNlFYwlwurldZGc4Ha4ZMpP_vGfkyxSNL-oIVBWqX3_b1Pd97aXxn7rzm-ns_H38OcQfhE8SkmHqgjX45FGiICmxzs3bvjNEz6gnssCbD5oJ9zJC_VtQg7GUQ6lJ8nuPHRv-PTYv6JgpGuWYhDk1f_5Q3WyEufhtLdvt1rslRU62RlUCk36-TFQqHCN-T3btdeueKu1NTKXFCDSTeyjJxhqaosbYrZpRcyVRSOSwWpfH1Hm64ukfdFkWI_o0hz99MdBoDlNN3JkdEb11Hrcumipn5Hi9lbcjb5crp_GPiNGwID6LINcpsznRaigPRFWy1iFdlSZAXWnrOJLcvYxgmqdtOSRcrkMbfMCg1YTqTKhjF_R1YVEvyr1gkB7QahxoqkTLmI8c9hFplc5TqxkL7FTEdlZkckGOwmr_tCHXJgsP2SvZ0l2ln2dh6RdDCu_MtcEmLJA09uDXNB-gXfSCY4-H4Ak9mIfOrnx_0wmGyYDGWG7o_nnAvoYufBNrK9bd8_epAfycrh6depnB6dHG-S53inp2lukWdt3RUfAIBU8_Orm-pu260XSn4eHYBX3GHsSUwK_f4B-z440w |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Automatic+crack+classification+and+segmentation+on+masonry+surfaces+using+convolutional+neural+networks+and+transfer+learning&rft.jtitle=Automation+in+construction&rft.au=Dais%2C+Dimitris&rft.au=Bal%2C+%C4%B0hsan+Engin&rft.au=Smyrou%2C+Eleni&rft.au=Sarhosis%2C+Vasilis&rft.date=2021-05-01&rft.pub=Elsevier+BV&rft.issn=0926-5805&rft.eissn=1872-7891&rft.volume=125&rft.spage=1&rft_id=info:doi/10.1016%2Fj.autcon.2021.103606&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0926-5805&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0926-5805&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0926-5805&client=summon |