Automatic recognition of pavement cracks from combined GPR B-scan and C-scan images using multiscale feature fusion deep neural networks
Pavement crack detection is critical for transportation infrastructure assessment using ground penetrating radar (GPR). This paper describes a YOLOv3 model with four-scale detection layers (FDL) to detect combined B-scan and C-scan GPR images subject to poor detection effects and a high missed detec...
Saved in:
| Published in | Automation in construction Vol. 146; p. 104698 |
|---|---|
| Main Authors | , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
01.02.2023
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Pavement crack detection is critical for transportation infrastructure assessment using ground penetrating radar (GPR). This paper describes a YOLOv3 model with four-scale detection layers (FDL) to detect combined B-scan and C-scan GPR images subject to poor detection effects and a high missed detection rate of small crack feature sizes. Multiscale fusion structures, efficient intersection over union (EIoU) loss function, K-means++ clustering, and hyperparameter optimization were used in this proposed model to further improve detection performance. Results indicated that the F1 score and mAP of the YOLOv3-FDL model reached 88.1% and 87.8% and had an 8.8% and 7.5% improvement on the GPR dataset of concealed cracks, respectively, compared with the YOLOv3 model. This illustrated that this model solved the problem of missed crack detection to some extent. Future studies can take these results further, especially the three-dimensional feature analysis of pavement cracks.
•B-scan and C-scan were combined to determine concealed crack features in GPR images.•YOLOv3-FDL model with four detection layers was proposed.•EIoU loss function and K-Means++ clustering were used.•Hyperparameter optimization based on evolutionary algorithm was performed. |
|---|---|
| AbstractList | Pavement crack detection is critical for transportation infrastructure assessment using ground penetrating radar (GPR). This paper describes a YOLOv3 model with four-scale detection layers (FDL) to detect combined B-scan and C-scan GPR images subject to poor detection effects and a high missed detection rate of small crack feature sizes. Multiscale fusion structures, efficient intersection over union (EIoU) loss function, K-means++ clustering, and hyperparameter optimization were used in this proposed model to further improve detection performance. Results indicated that the F1 score and mAP of the YOLOv3-FDL model reached 88.1% and 87.8% and had an 8.8% and 7.5% improvement on the GPR dataset of concealed cracks, respectively, compared with the YOLOv3 model. This illustrated that this model solved the problem of missed crack detection to some extent. Future studies can take these results further, especially the three-dimensional feature analysis of pavement cracks.
•B-scan and C-scan were combined to determine concealed crack features in GPR images.•YOLOv3-FDL model with four detection layers was proposed.•EIoU loss function and K-Means++ clustering were used.•Hyperparameter optimization based on evolutionary algorithm was performed. |
| ArticleNumber | 104698 |
| Author | Wang, Danyu Liu, Zhen Chen, Jiaqi Wang, Lutai Chen, Yihan Gu, Xingyu |
| Author_xml | – sequence: 1 givenname: Zhen surname: Liu fullname: Liu, Zhen organization: Department of Roadway Engineering, School of Transportation, Southeast University, Nanjing 211189, China – sequence: 2 givenname: Xingyu surname: Gu fullname: Gu, Xingyu email: guxingyu1976@seu.edu.cn organization: Department of Roadway Engineering, School of Transportation, Southeast University, Nanjing 211189, China – sequence: 3 givenname: Jiaqi surname: Chen fullname: Chen, Jiaqi organization: School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing 210044, China – sequence: 4 givenname: Danyu surname: Wang fullname: Wang, Danyu organization: Department of Roadway Engineering, School of Transportation, Southeast University, Nanjing 211189, China – sequence: 5 givenname: Yihan surname: Chen fullname: Chen, Yihan organization: Department of Roadway Engineering, School of Transportation, Southeast University, Nanjing 211189, China – sequence: 6 givenname: Lutai surname: Wang fullname: Wang, Lutai organization: Department of Roadway Engineering, School of Transportation, Southeast University, Nanjing 211189, China |
| BookMark | eNqFkM1qGzEUhUVJoHaSN-hCLzCupPnTdBFwTOMUDA0hWQuNdGXkzEhG0jj0DfLYkZmuukhX53Iu58D5lujCeQcIfaNkRQltvh9WckrKuxUjjGWrajr-BS0ob1nR8o5eoAXpWFPUnNRf0TLGAyGkJU23QO_rKflRJqtwAOX3zibrHfYGH-UJRnAJqyDVa8Qm-BErP_bWgcbbxyd8V0QlHZZO48182lHuIeIpWrfH4zQkm-0BsAGZppA1f3K7BjhiB1OQQ5b05sNrvEaXRg4Rbv7qFXq5__m8eSh2v7e_NutdoVjZpAKaWvfQas2JaWmrG0L60nQ1JV3FaN2ZhrOKM8Wrsi9rBiXvSG-U6iWhvIKqvEI_5l4VfIwBjFA2yfPoFKQdBCXizFQcxMxUnJmKmWkOV_-EjyFvDn_-F7udY5CHnSwEEZUFp0DbDD0J7e3nBR_HzJdp |
| CitedBy_id | crossref_primary_10_1109_ACCESS_2024_3512185 crossref_primary_10_3390_s24092816 crossref_primary_10_1088_1742_6596_2887_1_012019 crossref_primary_10_1117_1_JEI_32_5_053006 crossref_primary_10_1016_j_jreng_2024_01_005 crossref_primary_10_3390_app13106270 crossref_primary_10_3390_rs15030814 crossref_primary_10_1109_TITS_2024_3403144 crossref_primary_10_3390_rs15102598 crossref_primary_10_1051_e3sconf_202451203035 crossref_primary_10_1155_atr_7427074 crossref_primary_10_3390_fire6040139 crossref_primary_10_1051_e3sconf_202451203037 crossref_primary_10_1088_1361_6501_ad317d crossref_primary_10_3390_app13042488 crossref_primary_10_3390_buildings13071752 crossref_primary_10_3390_s23094466 crossref_primary_10_1109_TGRS_2024_3406154 crossref_primary_10_1109_TGRS_2024_3373025 crossref_primary_10_3390_s23146423 crossref_primary_10_3390_rs15051229 crossref_primary_10_1080_10298436_2023_2266098 crossref_primary_10_1109_ACCESS_2024_3481649 crossref_primary_10_3390_rs15143631 crossref_primary_10_1016_j_autcon_2025_106100 crossref_primary_10_1016_j_tust_2024_106275 crossref_primary_10_3390_rs15030549 crossref_primary_10_3390_s24103252 crossref_primary_10_3390_rs15184620 crossref_primary_10_3390_s23167272 crossref_primary_10_1016_j_autcon_2023_105166 crossref_primary_10_1109_JSEN_2023_3325490 crossref_primary_10_1016_j_tust_2024_105873 crossref_primary_10_1109_TITS_2024_3459004 crossref_primary_10_1520_JTE20230209 crossref_primary_10_3390_oral3020016 crossref_primary_10_1016_j_autcon_2024_105569 crossref_primary_10_1109_TGRS_2023_3317846 crossref_primary_10_1061_JPEODX_PVENG_1671 crossref_primary_10_3390_app14156568 crossref_primary_10_1016_j_cscm_2024_e03555 crossref_primary_10_1016_j_dibe_2023_100315 crossref_primary_10_3390_f14020285 crossref_primary_10_3390_su151310397 crossref_primary_10_1109_TGRS_2024_3458452 crossref_primary_10_3390_s23125640 crossref_primary_10_3390_rs16061043 crossref_primary_10_1109_TGRS_2024_3504715 crossref_primary_10_1016_j_autcon_2025_105996 crossref_primary_10_32604_sdhm_2024_042388 crossref_primary_10_3390_ijpb14040087 crossref_primary_10_1016_j_conbuildmat_2024_134893 crossref_primary_10_3390_rs15164019 crossref_primary_10_1016_j_conbuildmat_2024_139026 crossref_primary_10_3390_su15086610 crossref_primary_10_3390_app13116645 crossref_primary_10_3390_app13179847 crossref_primary_10_3390_s24061725 crossref_primary_10_1016_j_measurement_2023_113296 crossref_primary_10_3390_app13010164 crossref_primary_10_1007_s12008_024_01769_3 crossref_primary_10_1080_17538947_2024_2365970 crossref_primary_10_1007_s00371_024_03522_z crossref_primary_10_1109_TGRS_2025_3546212 crossref_primary_10_3390_app13074399 crossref_primary_10_1109_TITS_2023_3300312 crossref_primary_10_1016_j_jclepro_2023_136255 crossref_primary_10_1109_JSTARS_2024_3380064 crossref_primary_10_1109_TGRS_2025_3540974 crossref_primary_10_1016_j_autcon_2024_105594 crossref_primary_10_1016_j_autcon_2025_105979 crossref_primary_10_1016_j_tust_2024_106073 crossref_primary_10_1155_2023_6932621 crossref_primary_10_3390_vehicles5030051 crossref_primary_10_3390_s23063255 crossref_primary_10_1016_j_cscm_2022_e01749 crossref_primary_10_1109_TGRS_2024_3389009 crossref_primary_10_3390_rs15112751 crossref_primary_10_1016_j_autcon_2024_105629 crossref_primary_10_1016_j_autcon_2024_105902 crossref_primary_10_1016_j_compeleceng_2025_110264 crossref_primary_10_1016_j_undsp_2023_10_008 crossref_primary_10_1080_10298436_2023_2217320 crossref_primary_10_3389_fmats_2023_1347176 crossref_primary_10_1016_j_cscm_2024_e03643 crossref_primary_10_1111_mice_13343 crossref_primary_10_3390_jcm12155075 crossref_primary_10_3390_app13137992 crossref_primary_10_1016_j_autcon_2024_105482 crossref_primary_10_3390_plants12173032 crossref_primary_10_3390_s24144569 crossref_primary_10_1016_j_measurement_2024_116429 crossref_primary_10_1016_j_autcon_2024_105772 crossref_primary_10_1016_j_cscm_2023_e02083 crossref_primary_10_1016_j_measurement_2024_115327 crossref_primary_10_3390_s23084077 crossref_primary_10_1109_TITS_2024_3433002 crossref_primary_10_3390_s23041823 crossref_primary_10_1080_10298436_2024_2434910 crossref_primary_10_3390_rs15082211 crossref_primary_10_1109_TGRS_2024_3446029 crossref_primary_10_3390_infrastructures9020028 crossref_primary_10_1080_10589759_2023_2291429 crossref_primary_10_3390_atmos15050553 crossref_primary_10_3390_app13074265 |
| Cites_doi | 10.1016/j.measurement.2022.111248 10.1007/s12205-019-2012-z 10.1007/s10712-019-09556-6 10.1109/TIP.2021.3077144 10.1016/j.conbuildmat.2022.128154 10.1016/j.aci.2018.10.001 10.1109/TII.2020.2995208 10.1016/j.conbuildmat.2020.121949 10.3390/rs14163892 10.1016/j.ndteint.2020.102296 10.1109/TGRS.2018.2862627 10.1109/TII.2020.3024578 10.3390/rs14174190 10.1016/j.isprsjprs.2022.04.014 10.1016/j.autcon.2020.103119 10.1109/TITS.2022.3197712 10.1016/j.autcon.2021.103652 10.3390/rs13061081 10.1016/j.conbuildmat.2018.02.081 10.3390/rs12183056 10.3390/rs13040672 10.1109/TGRS.2015.2411572 10.1016/j.autcon.2021.103934 10.1016/j.autcon.2019.04.025 10.3390/rs14071593 10.1016/j.conbuildmat.2019.117352 10.1016/j.autcon.2020.103279 10.1109/TII.2019.2957379 10.3390/rs11212545 10.1109/TGRS.2020.3030079 10.1109/TITS.2022.3174626 10.1016/j.measurement.2022.111281 10.3390/rs12010044 10.3390/electronics10111269 10.1016/j.autcon.2019.102839 10.1016/j.conbuildmat.2021.126085 10.1177/0361198119841038 10.1016/j.ndteint.2018.08.005 10.1109/TII.2019.2937902 10.1080/10298436.2019.1645846 10.1016/j.atmosenv.2022.119085 |
| ContentType | Journal Article |
| Copyright | 2022 Elsevier B.V. |
| Copyright_xml | – notice: 2022 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.autcon.2022.104698 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Economics Engineering |
| EISSN | 1872-7891 |
| ExternalDocumentID | 10_1016_j_autcon_2022_104698 S0926580522005684 |
| GroupedDBID | --K --M .~1 0R~ 1B1 1~. 1~5 23N 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AACTN AAEDT AAEDW 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- AATTM AAXKI AAYWO AAYXX ABJNI ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AFXIZ AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH |
| ID | FETCH-LOGICAL-c236t-e65dbe7dd80f717d600b3f9510942159f682482c843b352e3890bfccba0184e43 |
| IEDL.DBID | .~1 |
| ISSN | 0926-5805 |
| IngestDate | Thu Apr 24 23:08:46 EDT 2025 Tue Jul 01 03:18:19 EDT 2025 Fri Feb 23 02:39:40 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Ground penetrating radar YOLOv3 Multiscale feature fusion Pavement crack assessment Object detection |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c236t-e65dbe7dd80f717d600b3f9510942159f682482c843b352e3890bfccba0184e43 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_autcon_2022_104698 crossref_primary_10_1016_j_autcon_2022_104698 elsevier_sciencedirect_doi_10_1016_j_autcon_2022_104698 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | February 2023 2023-02-00 |
| PublicationDateYYYYMMDD | 2023-02-01 |
| PublicationDate_xml | – month: 02 year: 2023 text: February 2023 |
| PublicationDecade | 2020 |
| PublicationTitle | Automation in construction |
| PublicationYear | 2023 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Lei, Hou, Xi, Tan, Xu, Jiang, Liu, Gu (bb0080) 2019; 106 Shang, Zhang, Song, Ling, Xiao, Zhang, Qian (bb0115) 2022; 14 Wang, Zhao, Al-Qadi (bb0035) 2020; 41 Yamaguchi, Mizutani, Nagayama (bb0165) 2021; 59 Liu, Lin, Cui, Fan, Xie, Spencer (bb0150) 2020; 118 Liu, Gu, Yang, Wang, Chen, Wang (bb0195) 2022; 23 Liang, Yu, Chen, Jin, Huang (bb0125) 2022; 23 Liu, Chen, Gu, Yeoh, Zhang (bb0175) 2022; 278 Ma, Wu, Zhang, Wu, Jeon, Zhang, Wu (bb0200) 2020; 16 Ma, Liu, Ren, Yu (bb0145) 2020; 12 Liu, Gu, Wu, Zou, Dong, Wang (bb0180) 2022; 197 Tan, Chen, Jiang, Zhong, Du, Qian, Mahalec (bb0095) 2021; 17 Wang, Zhao, Al-Qadi (bb0050) 2018; 100 Wang, Sui, Leng, Jiang, Lu (bb0020) 2022; 344 Liu, Justin, Gu, Qiao, Chen, Wu, Wang, Wang (bib221) 2022 Liu, Wu, Gu, Li, Wang, Zhang (bb0015) 2021; 13 Wang, Liu, Gu, Wu, Chen, Wang (bb0220) 2022; 14 Liu, Xie, Wang, Yang, Sudirman, Zhang, Li, Wang (bb0185) 2021; 17 Kang, An (bb0075) 2020; 12 Kim, Kim, An, Lee (bb0120) 2021; 22 Wang, Al-Qadi (bb0045) 2022; PP(60) Tong, Yuan, Gao, Wei, Dou (bb0160) 2020; 233 Zhao, Al-Qadi (bb0040) 2019; 57 Wei, Khan, Mehmood, Dou, Bateman, Magee, Cohn (bb0135) 2019; 105 Xu, Lei, Yang (bb0100) 2018; 2018 Wang, Gu, Liu, Wu, Wang (bb0025) 2022; 196 Asadi, Gindy, Alvarez (bb0085) 2019; 23 Luo, Lei, Hou, Wang, Ren, Zhang, Luo, Wang, Xu (bb0155) 2021; 10 Rout, Subudhi, Veerakumar, Chaudhury (bb0205) 2020; 16 Dinh, Gucunski, Tran, Novo, Nguyen (bb0130) 2021; 125 Wang, Al-Qadi, Cao (bb0055) 2020; 115 García-Fernández, Álvarez-Narciandi, Álvarez López, F., Andrés (bb0065) 2022; 189 Zhang, Yang, Li, Zhang, Jia (bb0140) 2020; 113 Peng, Yu (bb0215) 2021; 30 Feng, Yu, Liu, Fehler (bb0090) 2015; 53 Kang, Kim, Im, Lee (bb0060) 2019; 11 Li, Gu, Xu, Xu, Zhang, Liu, Dong (bb0170) 2021; 273 Tong, Gao, Zhang (bb0105) 2018; 169 Zheng, Wang, Liu, Li, Ye, Ren (bb0210) 2020; 34 Wang, Zhao, Al-Qadi (bb0030) 2019; 2673 Travassos, Avila, Ida (bb0070) 2018; 17 Ling, Qian, Shang, Guo, Zhao, Liu (bb0110) 2022; 14 Zhao, Zhang, Xue, Zhou, Huang (bb0190) 2021; 132 Solla, Perez-Gracia, Fontul (bb0005) 2021; 13 Liu, Gu, Wu, Ren, Zhou, Tang (bb0010) 2022; 321 Wang (10.1016/j.autcon.2022.104698_bb0050) 2018; 100 Liu (10.1016/j.autcon.2022.104698_bb0175) 2022; 278 Shang (10.1016/j.autcon.2022.104698_bb0115) 2022; 14 Zheng (10.1016/j.autcon.2022.104698_bb0210) 2020; 34 Tan (10.1016/j.autcon.2022.104698_bb0095) 2021; 17 Liu (10.1016/j.autcon.2022.104698_bb0010) 2022; 321 Ma (10.1016/j.autcon.2022.104698_bb0200) 2020; 16 García-Fernández (10.1016/j.autcon.2022.104698_bb0065) 2022; 189 Tong (10.1016/j.autcon.2022.104698_bb0105) 2018; 169 Peng (10.1016/j.autcon.2022.104698_bb0215) 2021; 30 Wang (10.1016/j.autcon.2022.104698_bb0030) 2019; 2673 Zhang (10.1016/j.autcon.2022.104698_bb0140) 2020; 113 Wang (10.1016/j.autcon.2022.104698_bb0220) 2022; 14 Solla (10.1016/j.autcon.2022.104698_bb0005) 2021; 13 Ma (10.1016/j.autcon.2022.104698_bb0145) 2020; 12 Kim (10.1016/j.autcon.2022.104698_bb0120) 2021; 22 Liang (10.1016/j.autcon.2022.104698_bb0125) 2022; 23 Yamaguchi (10.1016/j.autcon.2022.104698_bb0165) 2021; 59 Wang (10.1016/j.autcon.2022.104698_bb0025) 2022; 196 Wang (10.1016/j.autcon.2022.104698_bb0035) 2020; 41 Liu (10.1016/j.autcon.2022.104698_bib221) 2022 Wei (10.1016/j.autcon.2022.104698_bb0135) 2019; 105 Zhao (10.1016/j.autcon.2022.104698_bb0190) 2021; 132 Wang (10.1016/j.autcon.2022.104698_bb0045) 2022; PP(60) Kang (10.1016/j.autcon.2022.104698_bb0060) 2019; 11 Lei (10.1016/j.autcon.2022.104698_bb0080) 2019; 106 Ling (10.1016/j.autcon.2022.104698_bb0110) 2022; 14 Liu (10.1016/j.autcon.2022.104698_bb0180) 2022; 197 Rout (10.1016/j.autcon.2022.104698_bb0205) 2020; 16 Travassos (10.1016/j.autcon.2022.104698_bb0070) 2018; 17 Dinh (10.1016/j.autcon.2022.104698_bb0130) 2021; 125 Wang (10.1016/j.autcon.2022.104698_bb0020) 2022; 344 Asadi (10.1016/j.autcon.2022.104698_bb0085) 2019; 23 Zhao (10.1016/j.autcon.2022.104698_bb0040) 2019; 57 Wang (10.1016/j.autcon.2022.104698_bb0055) 2020; 115 Liu (10.1016/j.autcon.2022.104698_bb0195) 2022; 23 Xu (10.1016/j.autcon.2022.104698_bb0100) 2018; 2018 Liu (10.1016/j.autcon.2022.104698_bb0015) 2021; 13 Luo (10.1016/j.autcon.2022.104698_bb0155) 2021; 10 Tong (10.1016/j.autcon.2022.104698_bb0160) 2020; 233 Liu (10.1016/j.autcon.2022.104698_bb0185) 2021; 17 Feng (10.1016/j.autcon.2022.104698_bb0090) 2015; 53 Liu (10.1016/j.autcon.2022.104698_bb0150) 2020; 118 Kang (10.1016/j.autcon.2022.104698_bb0075) 2020; 12 Li (10.1016/j.autcon.2022.104698_bb0170) 2021; 273 |
| References_xml | – volume: 14 year: 2022 ident: bb0220 article-title: Automatic detection of pothole distress in asphalt pavement using improved convolutional neural networks publication-title: Remote Sens. – volume: 23 start-page: 2618 year: 2019 end-page: 2627 ident: bb0085 article-title: A machine learning based approach for automatic rebar detection and quantification of deterioration in concrete bridge deck ground penetrating radar B-scan images publication-title: KSCE J. Civ. Eng. – volume: 23 start-page: 22258 year: 2022 end-page: 22268 ident: bb0195 article-title: Novel YOLOv3 model with structure and hyperparameter optimization for detection of pavement concealed cracks in GPR images publication-title: IEEE Trans. Intell. Transp. Syst. – volume: 106 year: 2019 ident: bb0080 article-title: Automatic hyperbola detection and fitting in GPR B-scan image publication-title: Autom. Constr. – volume: 16 start-page: 5929 year: 2020 end-page: 5937 ident: bb0200 article-title: Research on sea clutter reflectivity using deep learning model in industry 4.0 publication-title: IEEE Trans. Indus. Inform. – volume: 13 year: 2021 ident: bb0015 article-title: Application of combining YOLO models and 3D GPR images in road detection and maintenance publication-title: Remote Sens. – volume: 125 year: 2021 ident: bb0130 article-title: Full-resolution 3D imaging for concrete structures with dual-polarization GPR publication-title: Autom. Constr. – volume: 14 year: 2022 ident: bb0115 article-title: Fast segmentation and dynamic monitoring of time-lapse 3D GPR data based on U-net publication-title: Remote Sens. – volume: 23 start-page: 22269 year: 2022 end-page: 22277 ident: bb0125 article-title: Automatic classification of pavement distress using 3D ground-penetrating radar and deep convolutional neural network publication-title: IEEE Trans. Intell. Transp. Syst. – volume: 22 start-page: 740 year: 2021 end-page: 751 ident: bb0120 article-title: A novel 3D GPR image arrangement for deep learning-based underground object classification publication-title: Int. J. Pavem. Eng. – volume: 41 start-page: 431 year: 2020 end-page: 445 ident: bb0035 article-title: Real-time density and thickness estimation of thin asphalt pavement overlay during compaction using ground penetrating radar data publication-title: Surv. Geophys. – volume: 197 year: 2022 ident: bb0180 article-title: GPR-based detection of internal cracks in asphalt pavement: a combination method of DeepAugment data and object detection publication-title: Measurement – volume: 17 start-page: 3303 year: 2021 end-page: 3313 ident: bb0095 article-title: A circular target feature detection framework based on DCNN for industrial applications publication-title: IEEE Trans. Indus. Inform. – start-page: 104689 year: 2022 ident: bib221 article-title: Automatic pixel-level detection of vertical cracks in asphalt pavement based on GPR investigation and improved mask R-CNN publication-title: Automation in Construction – volume: 30 start-page: 5032 year: 2021 end-page: 5044 ident: bb0215 article-title: A systematic IoU-related method: beyond simplified regression for better localization publication-title: IEEE Trans. Image Process. – volume: 11 year: 2019 ident: bb0060 article-title: 3D GPR image-based UcNet for enhancing underground cavity detectability publication-title: Remote Sens. – volume: 13 year: 2021 ident: bb0005 article-title: A review of GPR application on transport infrastructures: troubleshooting and best practices publication-title: Remote Sens. – volume: PP(60) start-page: 1 year: 2022 end-page: 14 ident: bb0045 article-title: Impact and removal of ground-penetrating radar vibration on continuous asphalt concrete pavement density prediction publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 12 year: 2020 ident: bb0145 article-title: Detection of collapsed buildings in post-earthquake remote sensing images based on the improved YOLOv3 publication-title: Remote Sens. – volume: 273 year: 2021 ident: bb0170 article-title: Detection of concealed cracks from ground penetrating radar images based on deep learning algorithm publication-title: Constr. Build. Mater. – volume: 16 start-page: 5712 year: 2020 end-page: 5722 ident: bb0205 article-title: Walsh-Hadamard-kernel-based features in particle filter framework for underwater object tracking publication-title: IEEE Trans. Indus. Inform. – volume: 12 year: 2020 ident: bb0075 article-title: Frequency-wavenumber analysis of deep learning-based super resolution 3D GPR images publication-title: Remote Sens. – volume: 53 start-page: 4852 year: 2015 end-page: 4861 ident: bb0090 article-title: Combination of H-alpha decomposition and migration for enhancing subsurface target classification of GPR publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 17 start-page: 7589 year: 2021 end-page: 7598 ident: bb0185 article-title: Deep learning based automatic multiclass wild pest monitoring approach using hybrid global and local activated features publication-title: IEEE Trans. Indus. Inform. – volume: 132 year: 2021 ident: bb0190 article-title: A deep learning-based approach for refined crack evaluation from shield tunnel lining images publication-title: Autom. Constr. – volume: 118 year: 2020 ident: bb0150 article-title: Detection and localization of rebar in concrete by deep learning using ground penetrating radar publication-title: Autom. Constr. – volume: 233 year: 2020 ident: bb0160 article-title: Pavement-distress detection using ground-penetrating radar and network in networks publication-title: Constr. Build. Mater. – volume: 2018 year: 2018 ident: bb0100 article-title: Railway subgrade defect automatic recognition method based on improved faster R-CNN publication-title: Sci. Program. – volume: 59 start-page: 6525 year: 2021 end-page: 6536 ident: bb0165 article-title: Mapping subsurface utility pipes by 3-D convolutional neural network and Kirchhoff migration using GPR images publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 10 year: 2021 ident: bb0155 article-title: GPR B-scan image denoising via multi-scale convolutional autoencoder with data augmentation publication-title: Electronics – volume: 321 year: 2022 ident: bb0010 article-title: Studies on the validity of strain sensors for pavement monitoring: A case study for a fiber Bragg grating sensor and resistive sensor publication-title: Constr. Build. Mater. – volume: 344 year: 2022 ident: bb0020 article-title: Asphalt pavement density measurement using non-destructive testing methods: current practices, challenges, and future vision publication-title: Constr. Build. Mater. – volume: 169 start-page: 69 year: 2018 end-page: 82 ident: bb0105 article-title: Innovative method for recognizing subgrade defects based on a convolutional neural network publication-title: Constr. Build. Mater. – volume: 57 start-page: 893 year: 2019 end-page: 901 ident: bb0040 article-title: Super-resolution of 3-D GPR signals to estimate thin asphalt overlay thickness using the XCMP method publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 100 start-page: 48 year: 2018 end-page: 54 ident: bb0050 article-title: Continuous real-time monitoring of flexible pavement layer density and thickness using ground penetrating radar publication-title: Ndt & E Int. – volume: 115 year: 2020 ident: bb0055 article-title: Factors impacting monitoring asphalt pavement density by ground penetrating radar publication-title: Ndt & E Int. – volume: 196 year: 2022 ident: bb0025 article-title: Automatic detection of asphalt pavement thickness: a method combining GPR images and improved Canny algorithm publication-title: Measurement – volume: 105 year: 2019 ident: bb0135 article-title: Web-based visualisation for look-ahead ground imaging in tunnel boring machines publication-title: Autom. Constr. – volume: 113 year: 2020 ident: bb0140 article-title: Automatic detection of moisture damages in asphalt pavements from GPR data with deep CNN and IRS method publication-title: Autom. Constr. – volume: 189 start-page: 128 year: 2022 end-page: 142 ident: bb0065 article-title: Improvements in GPR-SAR imaging focusing and detection capabilities of UAV-mounted GPR systems publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 34 start-page: 12993 year: 2020 end-page: 13000 ident: bb0210 article-title: Distance-IoU loss: faster and better learning for bounding box regression publication-title: Thirty-Fourth Aaai Conference on Artificial Intelligence, the Thirty-Second Innovative Applications of Artificial Intelligence Conference and the Tenth Aaai Symposium on Educational Advances in Artificial Intelligence – volume: 278 year: 2022 ident: bb0175 article-title: Visibility classification and influencing-factors analysis of airport: a deep learning approach publication-title: Atmos. Environ. – volume: 17 start-page: 296 year: 2018 end-page: 308 ident: bb0070 article-title: Artificial neural networks and machine learning techniques applied to ground penetrating radar: a review publication-title: Appl. Comput. Inform. – volume: 2673 start-page: 329 year: 2019 end-page: 338 ident: bb0030 article-title: Real-time monitoring of asphalt concrete pavement density during construction using ground penetrating radar: theory to practice publication-title: Transp. Res. Rec. – volume: 14 year: 2022 ident: bb0110 article-title: Research on the dynamic monitoring technology of road subgrades with time-lapse full-coverage 3D ground penetrating radar (GPR) publication-title: Remote Sens. – volume: 196 year: 2022 ident: 10.1016/j.autcon.2022.104698_bb0025 article-title: Automatic detection of asphalt pavement thickness: a method combining GPR images and improved Canny algorithm publication-title: Measurement doi: 10.1016/j.measurement.2022.111248 – volume: 23 start-page: 2618 issue: 6 year: 2019 ident: 10.1016/j.autcon.2022.104698_bb0085 article-title: A machine learning based approach for automatic rebar detection and quantification of deterioration in concrete bridge deck ground penetrating radar B-scan images publication-title: KSCE J. Civ. Eng. doi: 10.1007/s12205-019-2012-z – volume: 41 start-page: 431 issue: 3 year: 2020 ident: 10.1016/j.autcon.2022.104698_bb0035 article-title: Real-time density and thickness estimation of thin asphalt pavement overlay during compaction using ground penetrating radar data publication-title: Surv. Geophys. doi: 10.1007/s10712-019-09556-6 – volume: 30 start-page: 5032 year: 2021 ident: 10.1016/j.autcon.2022.104698_bb0215 article-title: A systematic IoU-related method: beyond simplified regression for better localization publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2021.3077144 – volume: 344 year: 2022 ident: 10.1016/j.autcon.2022.104698_bb0020 article-title: Asphalt pavement density measurement using non-destructive testing methods: current practices, challenges, and future vision publication-title: Constr. Build. Mater. doi: 10.1016/j.conbuildmat.2022.128154 – volume: 17 start-page: 296 issue: 2 year: 2018 ident: 10.1016/j.autcon.2022.104698_bb0070 article-title: Artificial neural networks and machine learning techniques applied to ground penetrating radar: a review publication-title: Appl. Comput. Inform. doi: 10.1016/j.aci.2018.10.001 – volume: 17 start-page: 7589 issue: 11 year: 2021 ident: 10.1016/j.autcon.2022.104698_bb0185 article-title: Deep learning based automatic multiclass wild pest monitoring approach using hybrid global and local activated features publication-title: IEEE Trans. Indus. Inform. doi: 10.1109/TII.2020.2995208 – volume: 273 year: 2021 ident: 10.1016/j.autcon.2022.104698_bb0170 article-title: Detection of concealed cracks from ground penetrating radar images based on deep learning algorithm publication-title: Constr. Build. Mater. doi: 10.1016/j.conbuildmat.2020.121949 – volume: 14 issue: 16 year: 2022 ident: 10.1016/j.autcon.2022.104698_bb0220 article-title: Automatic detection of pothole distress in asphalt pavement using improved convolutional neural networks publication-title: Remote Sens. doi: 10.3390/rs14163892 – volume: 115 year: 2020 ident: 10.1016/j.autcon.2022.104698_bb0055 article-title: Factors impacting monitoring asphalt pavement density by ground penetrating radar publication-title: Ndt & E Int. doi: 10.1016/j.ndteint.2020.102296 – volume: 34 start-page: 12993 year: 2020 ident: 10.1016/j.autcon.2022.104698_bb0210 article-title: Distance-IoU loss: faster and better learning for bounding box regression – volume: 57 start-page: 893 issue: 2 year: 2019 ident: 10.1016/j.autcon.2022.104698_bb0040 article-title: Super-resolution of 3-D GPR signals to estimate thin asphalt overlay thickness using the XCMP method publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2018.2862627 – volume: 17 start-page: 3303 issue: 5 year: 2021 ident: 10.1016/j.autcon.2022.104698_bb0095 article-title: A circular target feature detection framework based on DCNN for industrial applications publication-title: IEEE Trans. Indus. Inform. doi: 10.1109/TII.2020.3024578 – volume: 14 issue: 17 year: 2022 ident: 10.1016/j.autcon.2022.104698_bb0115 article-title: Fast segmentation and dynamic monitoring of time-lapse 3D GPR data based on U-net publication-title: Remote Sens. doi: 10.3390/rs14174190 – volume: 189 start-page: 128 year: 2022 ident: 10.1016/j.autcon.2022.104698_bb0065 article-title: Improvements in GPR-SAR imaging focusing and detection capabilities of UAV-mounted GPR systems publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2022.04.014 – volume: 113 year: 2020 ident: 10.1016/j.autcon.2022.104698_bb0140 article-title: Automatic detection of moisture damages in asphalt pavements from GPR data with deep CNN and IRS method publication-title: Autom. Constr. doi: 10.1016/j.autcon.2020.103119 – volume: 23 start-page: 22269 issue: 11 year: 2022 ident: 10.1016/j.autcon.2022.104698_bb0125 article-title: Automatic classification of pavement distress using 3D ground-penetrating radar and deep convolutional neural network publication-title: IEEE Trans. Intell. Transp. Syst. doi: 10.1109/TITS.2022.3197712 – volume: 125 year: 2021 ident: 10.1016/j.autcon.2022.104698_bb0130 article-title: Full-resolution 3D imaging for concrete structures with dual-polarization GPR publication-title: Autom. Constr. doi: 10.1016/j.autcon.2021.103652 – volume: 13 issue: 6 year: 2021 ident: 10.1016/j.autcon.2022.104698_bb0015 article-title: Application of combining YOLO models and 3D GPR images in road detection and maintenance publication-title: Remote Sens. doi: 10.3390/rs13061081 – volume: 169 start-page: 69 year: 2018 ident: 10.1016/j.autcon.2022.104698_bb0105 article-title: Innovative method for recognizing subgrade defects based on a convolutional neural network publication-title: Constr. Build. Mater. doi: 10.1016/j.conbuildmat.2018.02.081 – volume: PP(60) start-page: 1 year: 2022 ident: 10.1016/j.autcon.2022.104698_bb0045 article-title: Impact and removal of ground-penetrating radar vibration on continuous asphalt concrete pavement density prediction publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 12 issue: 18 year: 2020 ident: 10.1016/j.autcon.2022.104698_bb0075 article-title: Frequency-wavenumber analysis of deep learning-based super resolution 3D GPR images publication-title: Remote Sens. doi: 10.3390/rs12183056 – volume: 13 issue: 4 year: 2021 ident: 10.1016/j.autcon.2022.104698_bb0005 article-title: A review of GPR application on transport infrastructures: troubleshooting and best practices publication-title: Remote Sens. doi: 10.3390/rs13040672 – volume: 53 start-page: 4852 issue: 9 year: 2015 ident: 10.1016/j.autcon.2022.104698_bb0090 article-title: Combination of H-alpha decomposition and migration for enhancing subsurface target classification of GPR publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2015.2411572 – volume: 132 year: 2021 ident: 10.1016/j.autcon.2022.104698_bb0190 article-title: A deep learning-based approach for refined crack evaluation from shield tunnel lining images publication-title: Autom. Constr. doi: 10.1016/j.autcon.2021.103934 – volume: 105 year: 2019 ident: 10.1016/j.autcon.2022.104698_bb0135 article-title: Web-based visualisation for look-ahead ground imaging in tunnel boring machines publication-title: Autom. Constr. doi: 10.1016/j.autcon.2019.04.025 – volume: 14 issue: 7 year: 2022 ident: 10.1016/j.autcon.2022.104698_bb0110 article-title: Research on the dynamic monitoring technology of road subgrades with time-lapse full-coverage 3D ground penetrating radar (GPR) publication-title: Remote Sens. doi: 10.3390/rs14071593 – volume: 233 year: 2020 ident: 10.1016/j.autcon.2022.104698_bb0160 article-title: Pavement-distress detection using ground-penetrating radar and network in networks publication-title: Constr. Build. Mater. doi: 10.1016/j.conbuildmat.2019.117352 – volume: 118 year: 2020 ident: 10.1016/j.autcon.2022.104698_bb0150 article-title: Detection and localization of rebar in concrete by deep learning using ground penetrating radar publication-title: Autom. Constr. doi: 10.1016/j.autcon.2020.103279 – start-page: 104689 year: 2022 ident: 10.1016/j.autcon.2022.104698_bib221 article-title: Automatic pixel-level detection of vertical cracks in asphalt pavement based on GPR investigation and improved mask R-CNN publication-title: Automation in Construction – volume: 16 start-page: 5929 issue: 9 year: 2020 ident: 10.1016/j.autcon.2022.104698_bb0200 article-title: Research on sea clutter reflectivity using deep learning model in industry 4.0 publication-title: IEEE Trans. Indus. Inform. doi: 10.1109/TII.2019.2957379 – volume: 11 issue: 21 year: 2019 ident: 10.1016/j.autcon.2022.104698_bb0060 article-title: 3D GPR image-based UcNet for enhancing underground cavity detectability publication-title: Remote Sens. doi: 10.3390/rs11212545 – volume: 59 start-page: 6525 issue: 8 year: 2021 ident: 10.1016/j.autcon.2022.104698_bb0165 article-title: Mapping subsurface utility pipes by 3-D convolutional neural network and Kirchhoff migration using GPR images publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2020.3030079 – volume: 23 start-page: 22258 issue: 11 year: 2022 ident: 10.1016/j.autcon.2022.104698_bb0195 article-title: Novel YOLOv3 model with structure and hyperparameter optimization for detection of pavement concealed cracks in GPR images publication-title: IEEE Trans. Intell. Transp. Syst. doi: 10.1109/TITS.2022.3174626 – volume: 197 year: 2022 ident: 10.1016/j.autcon.2022.104698_bb0180 article-title: GPR-based detection of internal cracks in asphalt pavement: a combination method of DeepAugment data and object detection publication-title: Measurement doi: 10.1016/j.measurement.2022.111281 – volume: 12 issue: 1 year: 2020 ident: 10.1016/j.autcon.2022.104698_bb0145 article-title: Detection of collapsed buildings in post-earthquake remote sensing images based on the improved YOLOv3 publication-title: Remote Sens. doi: 10.3390/rs12010044 – volume: 10 issue: 11 year: 2021 ident: 10.1016/j.autcon.2022.104698_bb0155 article-title: GPR B-scan image denoising via multi-scale convolutional autoencoder with data augmentation publication-title: Electronics doi: 10.3390/electronics10111269 – volume: 106 year: 2019 ident: 10.1016/j.autcon.2022.104698_bb0080 article-title: Automatic hyperbola detection and fitting in GPR B-scan image publication-title: Autom. Constr. doi: 10.1016/j.autcon.2019.102839 – volume: 2018 year: 2018 ident: 10.1016/j.autcon.2022.104698_bb0100 article-title: Railway subgrade defect automatic recognition method based on improved faster R-CNN publication-title: Sci. Program. – volume: 321 year: 2022 ident: 10.1016/j.autcon.2022.104698_bb0010 article-title: Studies on the validity of strain sensors for pavement monitoring: A case study for a fiber Bragg grating sensor and resistive sensor publication-title: Constr. Build. Mater. doi: 10.1016/j.conbuildmat.2021.126085 – volume: 2673 start-page: 329 issue: 5 year: 2019 ident: 10.1016/j.autcon.2022.104698_bb0030 article-title: Real-time monitoring of asphalt concrete pavement density during construction using ground penetrating radar: theory to practice publication-title: Transp. Res. Rec. doi: 10.1177/0361198119841038 – volume: 100 start-page: 48 year: 2018 ident: 10.1016/j.autcon.2022.104698_bb0050 article-title: Continuous real-time monitoring of flexible pavement layer density and thickness using ground penetrating radar publication-title: Ndt & E Int. doi: 10.1016/j.ndteint.2018.08.005 – volume: 16 start-page: 5712 issue: 9 year: 2020 ident: 10.1016/j.autcon.2022.104698_bb0205 article-title: Walsh-Hadamard-kernel-based features in particle filter framework for underwater object tracking publication-title: IEEE Trans. Indus. Inform. doi: 10.1109/TII.2019.2937902 – volume: 22 start-page: 740 issue: 6 year: 2021 ident: 10.1016/j.autcon.2022.104698_bb0120 article-title: A novel 3D GPR image arrangement for deep learning-based underground object classification publication-title: Int. J. Pavem. Eng. doi: 10.1080/10298436.2019.1645846 – volume: 278 year: 2022 ident: 10.1016/j.autcon.2022.104698_bb0175 article-title: Visibility classification and influencing-factors analysis of airport: a deep learning approach publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2022.119085 |
| SSID | ssj0007069 |
| Score | 2.632353 |
| Snippet | Pavement crack detection is critical for transportation infrastructure assessment using ground penetrating radar (GPR). This paper describes a YOLOv3 model... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 104698 |
| SubjectTerms | Ground penetrating radar Multiscale feature fusion Object detection Pavement crack assessment YOLOv3 |
| Title | Automatic recognition of pavement cracks from combined GPR B-scan and C-scan images using multiscale feature fusion deep neural networks |
| URI | https://dx.doi.org/10.1016/j.autcon.2022.104698 |
| Volume | 146 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Ba9swFBYhO3Q7lC3dWNutvEOvWmxLluVjFpamLS1layA3Y8tPI6NzQuNce-7P7pNlZymMDXozQjKynnjve_L3PjF2apUIhcaQE7YWXJpAckL1yKl7gGhkHqM7Gri6VtOZvJjH8x4bd7UwjlbZ-n7v0xtv3bYM29UcrhaL4Y8gjSh8BgQgnJ6ldpqgUiZul395-EPzSALl9fYixV3vrnyu4Xjlm9plnREFsuZnZ6r_Hp52Qs7kLdtvsSKM_HTesR5WA7bXlRKvB-zNjprgAXscbeplo8AKW1rQsoKlhVXeqILXYO5dST24mhKgL6asGEs4u_kOX_ma1hjyqoSxf1z8Jk-zBseL_wkN7ZCa7xAsNlKgYDfunA1KxBU4UUyaaOUp5ev3bDb5djue8vaiBW4ioWqOKi4LTMpSB5bSu5JAUCGsw16pJEiQWqUjqSOjpSgIsCGBnKCwxhR5QAkiSvGB9atlhR8Z5JRf5aFWsZA55V5xYW1Ib9OJlqkJlT5kolvfzLQq5O4yjLuso5v9yrxVMmeVzFvlkPHtqJVX4fhP_6QzXfZsN2UUKP458ujFI4_Za3cVvWd0f2L9-n6Dnwmw1MVJsyNP2KvR-eX0-glgu-tS |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Nb9QwEB2V7aFwQG0BUaDtHHq1Nokdr3NcVpTt16qCVuotSpwxWlSyq272P_RndxwnqyIhkLhFlidybGvmjfPmGeDEaRlLQ7FgbC2FspESjOpJcPeIyKoiJX80cDXT01t1fpfebcGkr4XxtMrO9wef3nrrrmXYzeZwOZ8Pv0dZwuEzYgDh9SyNegHbXp0qHcD2-OxiOts45FGkg-ReooU36CvoWppXsW584plwLGv_d2bmzxHqWdQ53YXXHVzEcRjRHmxRvQ87fTXxah9ePRMUfAOP43WzaEVYccMMWtS4cLgsWmHwBu2Dr6pHX1aC_NGcGFOFX6-_4Wex4mnGoq5wEh7nv9jZrNBT439gyzzk5ntCR60aKLq1P2rDimiJXheTB1oHVvnqLdyefrmZTEV314KwidSNIJ1WJY2qykSOM7yKcVApnYdfmWJUkDltEmUSa5QsGbMR45yodNaWRcQ5Iin5Dgb1oqb3gAWnWEVsdCpVwelXWjoX89vMyKjMxtocgOznN7edELm_D-M-7xlnP_OwKrlflTysygGIjdUyCHH8o_-oX7r8tw2Vc6z4q-WH_7Y8hp3pzdVlfnk2u_gIL_3N9IHg_QkGzcOaDhm_NOVRtz-fAHPa7gM |
| 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+recognition+of+pavement+cracks+from+combined+GPR+B-scan+and+C-scan+images+using+multiscale+feature+fusion+deep+neural+networks&rft.jtitle=Automation+in+construction&rft.au=Liu%2C+Zhen&rft.au=Gu%2C+Xingyu&rft.au=Chen%2C+Jiaqi&rft.au=Wang%2C+Danyu&rft.date=2023-02-01&rft.issn=0926-5805&rft.volume=146&rft.spage=104698&rft_id=info:doi/10.1016%2Fj.autcon.2022.104698&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_autcon_2022_104698 |
| 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 |