Multiple distresses detection for Asphalt Pavement using improved you Only Look Once Algorithm based on convolutional neural network

Leveraging the YOLOv7 object detection framework, this study introduces YOLOv7-CSP, a refined algorithm tailored for identifying asphalt pavement distress with enhanced precision. Utilizing advanced image processing for dataset preprocessing, including data augmentation and denoising, YOLOv7-CSP int...

Full description

Saved in:
Bibliographic Details
Published inThe international journal of pavement engineering Vol. 25; no. 1
Main Authors Dan, Han-Cheng, Yan, Peng, Tan, Jiawei, Zhou, Yinchao, Lu, Bingjie
Format Journal Article
LanguageEnglish
Published Abingdon Taylor & Francis 31.12.2024
Taylor & Francis LLC
Subjects
Algorithms
Artificial neural networks
Asphalt pavements
Clustering
CSPNext
Data augmentation
Datasets
Highway maintenance
Image processing
Image processing systems
Image quality
Machine learning
Object recognition
Pavement distress detection; image recognition
secondary labelling
YOLOv7
Online AccessGet full text

Cover

Abstract Leveraging the YOLOv7 object detection framework, this study introduces YOLOv7-CSP, a refined algorithm tailored for identifying asphalt pavement distress with enhanced precision. Utilizing advanced image processing for dataset preprocessing, including data augmentation and denoising, YOLOv7-CSP integrates the CSPNeXt structure and CA attention mechanism for improved detection accuracy and efficiency. The algorithm optimizes anchor box selection through Kmeans clustering and employs a secondary labeling method to enhance learning efficiency and dataset quality. Comparative tests reveal YOLOv7-CSP's superior performance, with significant improvements in mAP, F1 score, GFLOPS, and FPS metrics, demonstrating its effectiveness in detecting various pavement distresses. This innovative approach marks a significant advancement in automatic pavement distress recognition, offering a robust solution for highway maintenance decision-making.
AbstractList Leveraging the YOLOv7 object detection framework, this study introduces YOLOv7-CSP, a refined algorithm tailored for identifying asphalt pavement distress with enhanced precision. Utilizing advanced image processing for dataset preprocessing, including data augmentation and denoising, YOLOv7-CSP integrates the CSPNeXt structure and CA attention mechanism for improved detection accuracy and efficiency. The algorithm optimizes anchor box selection through Kmeans clustering and employs a secondary labeling method to enhance learning efficiency and dataset quality. Comparative tests reveal YOLOv7-CSP's superior performance, with significant improvements in mAP, F1 score, GFLOPS, and FPS metrics, demonstrating its effectiveness in detecting various pavement distresses. This innovative approach marks a significant advancement in automatic pavement distress recognition, offering a robust solution for highway maintenance decision-making.
Author Yan, Peng
Tan, Jiawei
Zhou, Yinchao
Lu, Bingjie
Dan, Han-Cheng
Author_xml – sequence: 1
  givenname: Han-Cheng
  surname: Dan
  fullname: Dan, Han-Cheng
  organization: Central South University
– sequence: 2
  givenname: Peng
  surname: Yan
  fullname: Yan, Peng
  organization: Central South University
– sequence: 3
  givenname: Jiawei
  surname: Tan
  fullname: Tan, Jiawei
  email: jiawei.tan@ntu.edu.sg
  organization: Nanyang Technological University
– sequence: 4
  givenname: Yinchao
  surname: Zhou
  fullname: Zhou, Yinchao
  organization: Hunan Zhongda Design Institute Co., LTD
– sequence: 5
  givenname: Bingjie
  surname: Lu
  fullname: Lu, Bingjie
  organization: Central South University
BookMark eNqFkD9vFDEUxC0UJJLAR0CylHoPe-39pzQ5RUlAOhQKkOgsr_2cOPHaF9t70fV8cLxcaFJA9aaYGc37naAjHzwg9JGSFSU9-URJPfSctaua1HxVM9LTdniDjinvuqpu-59HRRdPtZjeoZOUHgipKSXsGP36Ortstw6wtilHSAkS1pBBZRs8NiHiddreS5fxN7mDCXzGc7L-DttpG8MONN6HGd96t8ebEB6LUoDX7i5Em-8nPMpULKVJBb8Lbl5apcMe5vjn5OcQH9-jt0a6BB9e7in6cX31_fJztbm9-XK53lSKsT5XzTgS1WpQxgztCEQpSbuOKMolZeXrQTPWUTmA4dw0jebQaMkVI2octDSanaKzQ29Z_jRDyuIhzLHsSYLRpuasZ31bXM3BpWJIKYIR22gnGfeCErEAF3-BiwW4eAFecuevcspmuTyco7Tuv-mLQ9r6An2ShYvTIsu9C9FE6ZVdRv6z4jfDVp9Y
CitedBy_id crossref_primary_10_1117_1_JEI_33_5_053056
crossref_primary_10_70693_itphss_v2i3_269
crossref_primary_10_4236_jcc_2024_1210001
crossref_primary_10_1016_j_conbuildmat_2024_139056
crossref_primary_10_3390_jimaging10100248
crossref_primary_10_1016_j_conbuildmat_2024_139031
Cites_doi 10.1117/1.3115362
10.1109/BigData.2018.8622327
10.1109/CIS.2008.208
10.1007/978-3-319-10602-1_48
10.1109/CVPR.2017.195
10.48550/arXiv.2212.07784
10.1109/TPAMI.2016.2577031
10.1109/CVPR46437.2021.01283
10.1002/stc.2551
10.1109/CVPR46437.2021.01352
10.1109/TII.2021.3090036
10.1186/s12911-021-01691-8
10.3390/s22031215
10.1016/j.autcon.2022.104575
10.1111/mice.12622
10.1016/j.autcon.2018.07.008
10.48550/arXiv.1412.6980
10.1016/j.conbuildmat.2017.09.110
10.12677/CSA.2021.112037
10.48550/arXiv.2209.02976
10.48550/arXiv.1605.06409
10.1145/1360612.1360700
10.48550/arXiv.2203.16250
10.1007/978-3-319-46448-0_2
10.48550/arXiv.2207.02696
10.1109/TPAMI.2018.2858826
10.1016/J.OPTLASENG.2009.05.014
10.1016/0167-8655(95)00035-F
10.48550/arXiv.2004.10934
10.1038/s41598-022-19674-8
10.1080/10298436.2018.1485917
10.1155/2013/856876
10.1117/12.259128
10.3969/j.issn.1671-1637.2017.05.012
10.1109/TITS.2019.2910595
10.48550/arXiv.2205.15242
10.1109/CVPR46437.2021.01350
10.48550/arXiv.1804.02767
10.1109/TITS.2022.3142393
10.1080/10298436.2020.1714047
10.1109/iccsce.2018.8685007
10.1109/ICCV.2015.169
10.1016/j.autcon.2022.104383
10.1109/TPAMI.2018.2844175
10.1007/s11263-009-0275-4
10.1109/TITS.2019.2891167
ContentType Journal Article
Copyright 2024 Informa UK Limited, trading as Taylor & Francis Group 2024
2024 Informa UK Limited, trading as Taylor & Francis Group
Copyright_xml – notice: 2024 Informa UK Limited, trading as Taylor & Francis Group 2024
– notice: 2024 Informa UK Limited, trading as Taylor & Francis Group
DBID AAYXX
CITATION
8FD
FR3
KR7
DOI 10.1080/10298436.2024.2308169
DatabaseName CrossRef
Technology Research Database
Engineering Research Database
Civil Engineering Abstracts
DatabaseTitle CrossRef
Technology Research Database
Civil Engineering Abstracts
Engineering Research Database
DatabaseTitleList
Technology Research Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1477-268X
ExternalDocumentID 10_1080_10298436_2024_2308169
2308169
Genre Research Article
GrantInformation_xml – fundername: Hunan Transportation Science and Technology Foundation
  grantid: 202104
– fundername: National Natural Science Foundation of China
  grantid: 52278468
  funderid: 10.13039/501100001809
GroupedDBID .7F
.QJ
0BK
0R~
29J
30N
4.4
5GY
5VS
AAENE
AAJMT
AALDU
AAMIU
AAPUL
AAQRR
ABCCY
ABDBF
ABFIM
ABHAV
ABJNI
ABLIJ
ABPAQ
ABPEM
ABTAI
ABXUL
ABXYU
ACGEJ
ACGFS
ACGOD
ACIWK
ACTIO
ADCVX
ADGTB
ADXPE
AEISY
AENEX
AEOZL
AEPSL
AEYOC
AFKVX
AGDLA
AGMYJ
AHDZW
AIJEM
AJWEG
AKBVH
AKOOK
ALMA_UNASSIGNED_HOLDINGS
ALQZU
AQRUH
AVBZW
AWYRJ
BLEHA
CCCUG
CE4
CS3
DKSSO
DU5
EAP
EBS
EST
ESX
E~A
E~B
GTTXZ
H13
HF~
HZ~
H~P
IPNFZ
J.P
KYCEM
LJTGL
M4Z
NA5
O9-
P2P
PQQKQ
RIG
RNANH
ROSJB
RTWRZ
S-T
SNACF
TBQAZ
TDBHL
TEN
TFL
TFT
TFW
TNC
TTHFI
TUROJ
TWF
UT5
UU3
ZGOLN
~S~
AAGDL
AAHIA
AAYXX
ADYSH
AFRVT
AIYEW
AMPGV
CITATION
DGEBU
8FD
ACUHS
FR3
KR7
TASJS
ID FETCH-LOGICAL-c338t-5bb0c6decff96be0cca1770c14a133089d3371a9ef44f55d4e5da4c30cb9dafd3
ISSN 1029-8436
IngestDate Wed Aug 13 09:18:44 EDT 2025
Tue Jul 01 00:17:43 EDT 2025
Thu Apr 24 23:02:14 EDT 2025
Tue Jan 07 04:16:54 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c338t-5bb0c6decff96be0cca1770c14a133089d3371a9ef44f55d4e5da4c30cb9dafd3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
PQID 3152438386
PQPubID 53119
ParticipantIDs proquest_journals_3152438386
crossref_citationtrail_10_1080_10298436_2024_2308169
informaworld_taylorfrancis_310_1080_10298436_2024_2308169
crossref_primary_10_1080_10298436_2024_2308169
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2024-12-31
PublicationDateYYYYMMDD 2024-12-31
PublicationDate_xml – month: 12
  year: 2024
  text: 2024-12-31
  day: 31
PublicationDecade 2020
PublicationPlace Abingdon
PublicationPlace_xml – name: Abingdon
PublicationTitle The international journal of pavement engineering
PublicationYear 2024
Publisher Taylor & Francis
Taylor & Francis LLC
Publisher_xml – name: Taylor & Francis
– name: Taylor & Francis LLC
References e_1_3_5_29_1
e_1_3_5_28_1
e_1_3_5_27_1
e_1_3_5_26_1
e_1_3_5_25_1
e_1_3_5_24_1
e_1_3_5_23_1
e_1_3_5_22_1
e_1_3_5_44_1
e_1_3_5_45_1
e_1_3_5_46_1
e_1_3_5_47_1
e_1_3_5_3_1
e_1_3_5_2_1
e_1_3_5_40_1
e_1_3_5_41_1
e_1_3_5_42_1
e_1_3_5_43_1
e_1_3_5_9_1
e_1_3_5_21_1
e_1_3_5_8_1
e_1_3_5_20_1
e_1_3_5_5_1
e_1_3_5_4_1
e_1_3_5_7_1
e_1_3_5_6_1
e_1_3_5_18_1
e_1_3_5_17_1
e_1_3_5_39_1
e_1_3_5_16_1
e_1_3_5_38_1
e_1_3_5_15_1
e_1_3_5_37_1
e_1_3_5_13_1
e_1_3_5_14_1
e_1_3_5_36_1
e_1_3_5_35_1
e_1_3_5_11_1
e_1_3_5_34_1
e_1_3_5_12_1
e_1_3_5_33_1
e_1_3_5_19_1
e_1_3_5_32_1
e_1_3_5_10_1
e_1_3_5_31_1
e_1_3_5_30_1
References_xml – ident: e_1_3_5_16_1
  doi: 10.1117/1.3115362
– ident: e_1_3_5_35_1
  doi: 10.1109/BigData.2018.8622327
– ident: e_1_3_5_47_1
  doi: 10.1109/CIS.2008.208
– ident: e_1_3_5_27_1
  doi: 10.1007/978-3-319-10602-1_48
– ident: e_1_3_5_6_1
  doi: 10.1109/CVPR.2017.195
– ident: e_1_3_5_34_1
  doi: 10.48550/arXiv.2212.07784
– ident: e_1_3_5_38_1
  doi: 10.1109/TPAMI.2016.2577031
– ident: e_1_3_5_40_1
  doi: 10.1109/CVPR46437.2021.01283
– ident: e_1_3_5_22_1
  doi: 10.1002/stc.2551
– ident: e_1_3_5_8_1
  doi: 10.1109/CVPR46437.2021.01352
– ident: e_1_3_5_10_1
  doi: 10.1109/TII.2021.3090036
– ident: e_1_3_5_39_1
  doi: 10.1186/s12911-021-01691-8
– ident: e_1_3_5_43_1
  doi: 10.3390/s22031215
– ident: e_1_3_5_32_1
  doi: 10.1016/j.autcon.2022.104575
– ident: e_1_3_5_30_1
  doi: 10.1111/mice.12622
– ident: e_1_3_5_36_1
  doi: 10.1016/j.autcon.2018.07.008
– ident: e_1_3_5_24_1
  doi: 10.48550/arXiv.1412.6980
– ident: e_1_3_5_17_1
  doi: 10.1016/j.conbuildmat.2017.09.110
– ident: e_1_3_5_14_1
  doi: 10.12677/CSA.2021.112037
– ident: e_1_3_5_26_1
  doi: 10.48550/arXiv.2209.02976
– ident: e_1_3_5_7_1
  doi: 10.48550/arXiv.1605.06409
– ident: e_1_3_5_19_1
  doi: 10.1145/1360612.1360700
– ident: e_1_3_5_42_1
  doi: 10.48550/arXiv.2203.16250
– ident: e_1_3_5_29_1
  doi: 10.1007/978-3-319-46448-0_2
– ident: e_1_3_5_41_1
  doi: 10.48550/arXiv.2207.02696
– ident: e_1_3_5_28_1
  doi: 10.1109/TPAMI.2018.2858826
– ident: e_1_3_5_46_1
  doi: 10.1016/J.OPTLASENG.2009.05.014
– ident: e_1_3_5_3_1
  doi: 10.1016/0167-8655(95)00035-F
– ident: e_1_3_5_4_1
  doi: 10.48550/arXiv.2004.10934
– ident: e_1_3_5_18_1
  doi: 10.1038/s41598-022-19674-8
– ident: e_1_3_5_25_1
  doi: 10.1080/10298436.2018.1485917
– ident: e_1_3_5_2_1
  doi: 10.1155/2013/856876
– ident: e_1_3_5_5_1
  doi: 10.1117/12.259128
– ident: e_1_3_5_23_1
  doi: 10.3969/j.issn.1671-1637.2017.05.012
– ident: e_1_3_5_44_1
  doi: 10.1109/TITS.2019.2910595
– ident: e_1_3_5_9_1
  doi: 10.48550/arXiv.2205.15242
– ident: e_1_3_5_21_1
  doi: 10.1109/CVPR46437.2021.01350
– ident: e_1_3_5_37_1
  doi: 10.48550/arXiv.1804.02767
– ident: e_1_3_5_31_1
  doi: 10.1109/TITS.2022.3142393
– ident: e_1_3_5_11_1
  doi: 10.1080/10298436.2020.1714047
– ident: e_1_3_5_45_1
  doi: 10.1109/iccsce.2018.8685007
– ident: e_1_3_5_15_1
  doi: 10.1109/ICCV.2015.169
– ident: e_1_3_5_33_1
  doi: 10.1016/j.autcon.2022.104383
– ident: e_1_3_5_20_1
  doi: 10.1109/TPAMI.2018.2844175
– ident: e_1_3_5_12_1
  doi: 10.1007/s11263-009-0275-4
– ident: e_1_3_5_13_1
  doi: 10.1109/TITS.2019.2891167
SSID ssj0021103
Score 2.4060786
Snippet Leveraging the YOLOv7 object detection framework, this study introduces YOLOv7-CSP, a refined algorithm tailored for identifying asphalt pavement distress with...
SourceID proquest
crossref
informaworld
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
SubjectTerms Algorithms
Artificial neural networks
Asphalt pavements
Clustering
CSPNext
Data augmentation
Datasets
Highway maintenance
Image processing
Image processing systems
Image quality
Machine learning
Object recognition
Pavement distress detection; image recognition
secondary labelling
YOLOv7
Title Multiple distresses detection for Asphalt Pavement using improved you Only Look Once Algorithm based on convolutional neural network
URI https://www.tandfonline.com/doi/abs/10.1080/10298436.2024.2308169
https://www.proquest.com/docview/3152438386
Volume 25
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lj9MwELaW7gUOiKdYWJAP3KqUJHYePlYLqFqxLIeuWLhEsePQSCWtdlOh5cwf4Z8yYzuP0pWWxyWtJrLjZL7Y48nMN4S8jJMSVqlceCIPlcd1wjwhZeCxXPmKCR1oU3nu5H08O-PH59H53t7PQdTSppET9f3avJJ_0SrIQK-YJfsXmu06BQH8B_3CETQMxz_S8UkbDVhUNudDX44L3WjVBRBOL9f4QRwMRcML3ow3xjdQGVcC2JpXq834tF5ejd9hzsMpvuXT5ZfVRdUsvo5xhSvwawKGprsbAY0iBab5MQHkQ-sWMVdtuRgHxBTrdgi6p0Ds_eRm8pvltXe00L38k5V_GIjmVnRc5d901bu9VxuzmFS1WuSroSsj7AgTHfjmO1VFBhMzhumknDnabCvjSeKFsSlN3M3mNo16iNqdRcJGVWKP2OEER4Lx8Glgi8b8xr_tztwi-yHsRMIR2Z_OXn_-2O3qwX6yWRxugG2aWOq_uvYSWwbQFj3ujjlgbJz5PXLXbU7o1CLtPtnT9QNyZ0BZ-ZD8aDFHe8zRDnMULkMd5miLOWowR1vMUcAcRcxRxBxFzNEOc9RgjkJPW5ijFnPUYe4ROXv7Zn4081wlD08xljZeJKWv4kKrshSx1D5MG0GS-CrgecDgsYiCsSTIhS45L6Oo4Doqcq6Yr6Qo8rJgj8moXtX6CaG8KDUvExlLgZlNYF_HaSpCrVkSwSl5QHj7eDPlaO6x2soyCxwbbquVDLWSOa0ckEnXbG15Xm5qIIa6yxoD3tLiNmM3tD1sFZ259xCbRCHyBqfx0__o-hm53b9Zh2TUXGz0czCbG_nCAfcXKh7EIg
linkProvider Library Specific Holdings
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1BT9swFLYYHNgODBjT2GD4wDVVEjtOfKzQUMfawgEkblFsP5eKLq3a9ABnfvj8nAQV0MShJ0eKnmU7z37vOd_7HiGnIrXOShUykEWsAw4pC6RSUcAKHWomIQJfeW4wFL0bfnGb3K7kwiCsEmNoWxNF-LMaNzdeRreQONfGMuMMEQYxRyhzFgn5gWwlUqRYxYCFw-egy5m3GmQfywBl2iye_3Xzwj69YC99c1p7E3T-meh28DXy5L6zrFRHP77idVxvdrtkp_FQabdWqT2yAeU--bTCW_iFPA0aGCI14zrZBBbUQOVhXSV1k6HdxQz_xNOrwhOSVxQB9iM69ncYYOjDdEkvy8kD7Tsv3z1poN3JaDofV3d_KZpWQ11PiIlv9oYbEnJv-sYj1w_Izfmv67Ne0JRzCLSLg6sgUSrUwoC2VgoFodOdKE1DHfHCBcphJg1jaVRIsJzbJDEcElNwzUKtpCmsYV_JZjkt4Ruh3FjgNlVCSUxvcU6WyDIZA7A0ca_UIeHtR8x1w3WOJTcmedRQoraLnOMi580iH5LOs9isJvt4T0Cuakhe-VsWW5dEydk7sketOuXNuYEiSYzksZn4vkbXJ2S7dz3o5_3fwz8_yEd8VXNTHpHNar6EY-dHVeqn3yj_AMFeEYc
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT9wwELZ4SAgOLa-qFEp94JpVEjtOfFwBK9rClgNI3KLYHsOq2-xqN3uAc394PY6DoAhx4ORI0Vi2M_bMON98Q8iRyK2zUpWMZJXqiEPOIqlUErFKx5pJSMBXnrsYirNr_uMm69CE8wCrxBjatkQR_qzGzT01tkPEuTaVBWcIMEg5IpmLRMhlsiqQPByzOOLhY8zlrFuLsU9lhDJdEs9r3TwzT8_IS18c1t4CDT4S1Y29BZ787i0a1dMP_9E6vmtym-RD8E9pv1WoLbIE9TbZeMJauEP-XgQQIjWjNtUE5tRA40FdNXVzof35FP_D08vK05E3FOH1t3TkbzDA0PvJgv6qx_f03Pn47kkD7Y9vJ7NRc_eHomE11PWEiPiwM9yQkHnTNx63vkuuB6dXx2dRKOYQaRcFN1GmVKyFAW2tFApipzlJnsc64ZULk-NCGsbypJJgObdZZjhkpuKaxVpJU1nDPpGVelLDZ0K5scBtroSSmNziXCxRFDIFYHnmXqk9wrtvWOrAdI4FN8ZlEghRu0UucZHLsMh7pPcoNm2pPt4SkE8VpGz8HYttC6KU7A3Zg06bynBqoEiWInVsIb68o-tvZO3yZFCefx_-3Cfr-KYlpjwgK81sAV-dE9WoQ79N_gFTHhAr
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=Multiple+distresses+detection+for+Asphalt+Pavement+using+improved+you+Only+Look+Once+Algorithm+based+on+convolutional+neural+network&rft.jtitle=The+international+journal+of+pavement+engineering&rft.au=Dan%2C+Han-Cheng&rft.au=Yan%2C+Peng&rft.au=Tan%2C+Jiawei&rft.au=Zhou%2C+Yinchao&rft.date=2024-12-31&rft.pub=Taylor+%26+Francis&rft.issn=1029-8436&rft.eissn=1477-268X&rft.volume=25&rft.issue=1&rft_id=info:doi/10.1080%2F10298436.2024.2308169&rft.externalDocID=2308169
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1029-8436&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1029-8436&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1029-8436&client=summon