Real-Time Pixel-Wise Segmentation of Road Surface Damage Using a 2D U-Net Architecture

Road surface integrity is critical for ensuring vehicular safety and reducing maintenance costs, yet traditional visual inspections are laborious and subject to human error. This study presents a tailored 2D U-Net architecture for automated pixel-wise segmentation of pavement damage specifically cra...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Procedia computer science Ročník 269; s. 131 - 139
Hlavní autori: Olzhayev, Olzhas, Kulambayev, Bakhytzhan, Omarov, Batyrkhan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 2025
Predmet:
ISSN:1877-0509, 1877-0509
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Road surface integrity is critical for ensuring vehicular safety and reducing maintenance costs, yet traditional visual inspections are laborious and subject to human error. This study presents a tailored 2D U-Net architecture for automated pixel-wise segmentation of pavement damage specifically cracks and potholes from smartphone-captured RGB imagery. The proposed model employs an encoder–decoder design with symmetric skip connections to merge high-level contextual information and fine-grained spatial features. A weighted cross-entropy loss function is used to mitigate severe class imbalance between sparse damage pixels and dominant intact surface areas. Training on a curated dataset of 1,000 labeled road images demonstrates steady convergence: training loss decreases from 2.65 to 2.25, while validation accuracy rises from 65 % to 76 % over 36 epochs. Qualitative results reveal that coarse crack clusters are reliably detected by epoch 20, with finer details emerging by epoch 30. Mobile deployment tests on a mid-range smartphone yield an average inference time of 45 ms per frame, and TensorFlow Lite quantization reduces model size by 30 % with less than 1 % IoU degradation. These findings confirm that the 2D U-Net framework balances segmentation accuracy and on-device efficiency. Future work will explore hybrid loss formulations and expanded datasets including nighttime and adverse weather conditions to further enhance generalization and robustness.
AbstractList Road surface integrity is critical for ensuring vehicular safety and reducing maintenance costs, yet traditional visual inspections are laborious and subject to human error. This study presents a tailored 2D U-Net architecture for automated pixel-wise segmentation of pavement damage specifically cracks and potholes from smartphone-captured RGB imagery. The proposed model employs an encoder–decoder design with symmetric skip connections to merge high-level contextual information and fine-grained spatial features. A weighted cross-entropy loss function is used to mitigate severe class imbalance between sparse damage pixels and dominant intact surface areas. Training on a curated dataset of 1,000 labeled road images demonstrates steady convergence: training loss decreases from 2.65 to 2.25, while validation accuracy rises from 65 % to 76 % over 36 epochs. Qualitative results reveal that coarse crack clusters are reliably detected by epoch 20, with finer details emerging by epoch 30. Mobile deployment tests on a mid-range smartphone yield an average inference time of 45 ms per frame, and TensorFlow Lite quantization reduces model size by 30 % with less than 1 % IoU degradation. These findings confirm that the 2D U-Net framework balances segmentation accuracy and on-device efficiency. Future work will explore hybrid loss formulations and expanded datasets including nighttime and adverse weather conditions to further enhance generalization and robustness.
Author Kulambayev, Bakhytzhan
Olzhayev, Olzhas
Omarov, Batyrkhan
Author_xml – sequence: 1
  givenname: Olzhas
  surname: Olzhayev
  fullname: Olzhayev, Olzhas
  organization: International Information Technology University, Almaty, Kazakhstan
– sequence: 2
  givenname: Bakhytzhan
  surname: Kulambayev
  fullname: Kulambayev, Bakhytzhan
  organization: Turan University, Almaty, Kazakhstan
– sequence: 3
  givenname: Batyrkhan
  surname: Omarov
  fullname: Omarov, Batyrkhan
  email: b.omarov@iitu.edu.kz
  organization: International Information Technology University, Almaty, Kazakhstan
BookMark eNp9kMtOwzAQRS1UJErpF7DxDyTYTuwkCxZVy0uqAPUBS8uPcXHVJJWdIvh7UmDBitnMLO4ZXZ1zNGjaBhC6pCSlhIqrbboPrYkpI4ynpEyZECdoSMuiSAgn1eDPfYbGMW5JP1lZVrQYopcFqF2y8jXgZ_8Bu-TVR8BL2NTQdKrzbYNbhxetsnh5CE4ZwDNVqw3gdfTNBivMZnidPEKHJ8G8-Q5MdwhwgU6d2kUY_-4RWt_erKb3yfzp7mE6mSeG5plIXMmddplVOjcW8kI4QS0zJtMk19blnIMQmlcFA24dGCYqsFYJ0H2EE52NUPbz14Q2xgBO7oOvVfiUlMijHbmV33bk0Y4kpezt9NT1DwV9tXcPQUbjoTFgfej7S9v6f_kvNzVxRQ
Cites_doi 10.1016/j.autcon.2025.106120
10.1109/TITS.2024.3360263
10.1109/TAFE.2023.3332495
10.3390/s23010053
10.14569/IJACSA.2024.01509107
10.1016/j.aei.2025.103262
10.1109/JIOT.2024.3466390
10.1109/IFSA-SCIS.2017.8023299
10.1109/TITS.2024.3509140
10.1088/1742-6596/2278/1/012020
10.1080/10298436.2023.2219366
10.17654/EC016040801
10.14569/IJACSA.2024.0150333
10.1177/14759217211053776
10.1080/14680629.2024.2374863
10.32604/cmc.2024.057213
10.1007/s12524-024-01963-6
10.14569/IJACSA.2023.0140979
10.22630/MGV.2024.33.3.4
10.32604/cmc.2022.029544
10.1016/j.autcon.2024.105899
10.1016/j.conbuildmat.2023.133582
10.1177/03611981251322484
10.1016/j.autcon.2022.104436
10.1109/TITS.2024.3405995
ContentType Journal Article
Copyright 2025
Copyright_xml – notice: 2025
DBID 6I.
AAFTH
AAYXX
CITATION
DOI 10.1016/j.procs.2025.08.266
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1877-0509
EndPage 139
ExternalDocumentID 10_1016_j_procs_2025_08_266
S1877050925026110
GroupedDBID --K
0R~
1B1
457
5VS
6I.
71M
9DU
AAEDT
AAEDW
AAFTH
AAIKJ
AALRI
AAQFI
AAXUO
AAYWO
ABMAC
ABWVN
ACGFS
ACRPL
ACVFH
ADBBV
ADCNI
ADEZE
ADNMO
ADVLN
AEUPX
AEXQZ
AFPUW
AFTJW
AGHFR
AIGII
AITUG
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
E3Z
EBS
EJD
EP3
FDB
FNPLU
HZ~
IXB
KQ8
M41
M~E
O-L
O9-
OK1
P2P
ROL
SES
SSZ
~HD
AAYXX
CITATION
ID FETCH-LOGICAL-c1436-f85fbf3dab4cde476f61d2cc3b04bdf455e66b5972e5dfec269edda6ebc3b50b3
ISSN 1877-0509
IngestDate Sat Nov 29 06:52:01 EST 2025
Sat Nov 29 17:14:45 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
semantic segmentation
Pixel-wise segmentation
Road damage
2D U-Net
Language English
License This is an open access article under the CC BY license.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c1436-f85fbf3dab4cde476f61d2cc3b04bdf455e66b5972e5dfec269edda6ebc3b50b3
OpenAccessLink https://dx.doi.org/10.1016/j.procs.2025.08.266
PageCount 9
ParticipantIDs crossref_primary_10_1016_j_procs_2025_08_266
elsevier_sciencedirect_doi_10_1016_j_procs_2025_08_266
PublicationCentury 2000
PublicationDate 2025
2025-00-00
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – year: 2025
  text: 2025
PublicationDecade 2020
PublicationTitle Procedia computer science
PublicationYear 2025
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Yang, Y., Zhao, Z., Su, L., Zhou, Y., & Li, H. (2022, May). Research on pavement crack detection algorithm based on deep residual UNET neural network. In Journal of Physics: Conference Series (Vol. 2278, No. 1, p. 012020). IOP Publishing.
Tabernik, Šuc, Skočaj (bib14) 2023; 408
Kulambayev, B., Astaubayeva, G., Tleuberdiyeva, G., Alimkulova, J., Nussupbekova, G., & Kisseleva, O. (2024). Deep CNN Approach with Visual Features for Real-Time Pavement Crack Detection. International Journal of Advanced Computer Science & Applications, 15(3).
Owor, Adu-Gyamfi, Aboah, Amo-Boateng (bib16) 2025; 26
Khan, Khan, Elhassan, Deng (bib11) 2025; 65
Muturi, T. W., & Adu-Gyamfi, Y. (2025). Enhanced Crack Segmentation Using Meta’s Segment Anything Model with Low-Cost Ground Truths and Multimodal Prompts. Transportation Research Record, 03611981251322484.
Zhong, Zhu, Huyan, Ma, Zhang (bib10) 2022; 141
Jing, Ding, Yang, Feng, Guan, Han, Wang (bib13) 2025; 174
Li, P., Wang, M., Fan, Z., Huang, H., Zhu, G., & Zhuang, J. (2024). OUR-Net: a multi-frequency network with octave max unpooling and octave convolution residual block for pavement crack segmentation. IEEE Transactions on Intelligent Transportation Systems.
Zhang, Zhang, Dong, He, Liu, Zhan, Wang (bib9) 2024; 25
Omarov, Suliman, Tsoy (bib2) 2016; 16
Kulambayev, B., Beissenova, G., Katayev, N., Abduraimova, B., Zhaidakbayeva, L., Sarbassova, A., ... & Shyrakbayev, A. (2022). A Deep Learning-Based Approach for Road Surface Damage Detection. Computers, Materials & Continua, 73(2).
Zhang, Wang, Lu (bib4) 2023; 11
Altayeva, A., Omarov, B., Suleimenov, Z., & Im Cho, Y. (2017, June). Application of multi-agent control systems in energy-efficient intelligent building. In 2017 Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems (IFSA-SCIS) (pp. 1-5). IEEE.
Meivel, Devi, Subramanian, Kalaiarasi (bib25) 2025; 53
Zhang, Xu, Ding, Qian, Dong, Zhang, He (bib22) 2025; 151
Kulambayev, B., Gleb, B., Katayev, N., Menglibay, I., & Momynkulov, Z. (2024). Real-Time Road Damage Detection System on Deep Learning Based Image Analysis. International Journal of Advanced Computer Science & Applications, 15(9).
Alshawabkeh, S., Wu, L., Dong, D., Cheng, Y., & Li, L. (2025). A Hybrid Approach for Pavement Crack Detection Using Mask R-CNN and Vision Transformer Model. Computers, Materials & Continua, 82(1).
Xue, F., Chang, Y., Xu, W., Liang, W., Sheng, F., & Ming, A. (2025). Evidence-Based Real-Time Road Segmentation With RGB-D Data Augmentation. IEEE Transactions on Intelligent Transportation Systems.
Wang, Zhu, Zhu, Xie, He, Liu, You (bib8) 2023; 24
Kulambayev, B., Nurlybek, M., Astaubayeva, G., Tleuberdiyeva, G., Zholdasbayev, S., & Tolep, A. (2023). Real-time road surface damage detection framework based on mask r-cnn model. International Journal of Advanced Computer Science and Applications, 14(9).
Chang, J. Y., & Xu, Z. X. (2024). Enhanced Water Puddle Segmentation and Detection Using DCU-Net. IEEE Internet of Things Journal.
Li, Yuan, Wang, Chen, Ma (bib20) 2025; 170
Kulambayev, Nurlybek, Astaubayeva, Tleuberdiyeva, Zholdasbayev, Tolep (bib1) 2023; 14
Yu, Dong, Wang, Zhou (bib5) 2022; 23
Doghmane, Boukari (bib12) 2024; 33
Donapati, Cheruku, Kodali (bib17) 2023; 1
Kang, Cha (bib21) 2022; 21
Tabernik (10.1016/j.procs.2025.08.266_bib14) 2023; 408
10.1016/j.procs.2025.08.266_bib23
Li (10.1016/j.procs.2025.08.266_bib20) 2025; 170
10.1016/j.procs.2025.08.266_bib24
Khan (10.1016/j.procs.2025.08.266_bib11) 2025; 65
10.1016/j.procs.2025.08.266_bib27
10.1016/j.procs.2025.08.266_bib26
10.1016/j.procs.2025.08.266_bib3
10.1016/j.procs.2025.08.266_bib28
Wang (10.1016/j.procs.2025.08.266_bib8) 2023; 24
Kulambayev (10.1016/j.procs.2025.08.266_bib1) 2023; 14
Zhang (10.1016/j.procs.2025.08.266_bib4) 2023; 11
Meivel (10.1016/j.procs.2025.08.266_bib25) 2025; 53
10.1016/j.procs.2025.08.266_bib7
10.1016/j.procs.2025.08.266_bib6
Yu (10.1016/j.procs.2025.08.266_bib5) 2022; 23
Donapati (10.1016/j.procs.2025.08.266_bib17) 2023; 1
Zhang (10.1016/j.procs.2025.08.266_bib9) 2024; 25
Doghmane (10.1016/j.procs.2025.08.266_bib12) 2024; 33
Zhang (10.1016/j.procs.2025.08.266_bib22) 2025; 151
10.1016/j.procs.2025.08.266_bib19
10.1016/j.procs.2025.08.266_bib15
10.1016/j.procs.2025.08.266_bib18
Omarov (10.1016/j.procs.2025.08.266_bib2) 2016; 16
Zhong (10.1016/j.procs.2025.08.266_bib10) 2022; 141
Kang (10.1016/j.procs.2025.08.266_bib21) 2022; 21
Owor (10.1016/j.procs.2025.08.266_bib16) 2025; 26
Jing (10.1016/j.procs.2025.08.266_bib13) 2025; 174
References_xml – volume: 53
  start-page: 327
  year: 2025
  end-page: 343
  ident: bib25
  article-title: Remote sensing analysis of the lidar drone mapping system for detecting damages to buildings, roads, and bridges using the faster cnn method
  publication-title: Journal of the Indian Society of Remote Sensing
– volume: 16
  start-page: 801
  year: 2016
  ident: bib2
  article-title: Parallel backpropagation neural network training for face recognition
  publication-title: Far East Journal of Electronics and Communications
– reference: Kulambayev, B., Beissenova, G., Katayev, N., Abduraimova, B., Zhaidakbayeva, L., Sarbassova, A., ... & Shyrakbayev, A. (2022). A Deep Learning-Based Approach for Road Surface Damage Detection. Computers, Materials & Continua, 73(2).
– volume: 151
  start-page: 04024054
  year: 2025
  ident: bib22
  article-title: Intelligent Detection of Sealed Crack with 2D Asphalt Pavement Images
  publication-title: Journal of Transportation Engineering, Part B: Pavements
– volume: 25
  start-page: 11282
  year: 2024
  end-page: 11303
  ident: bib9
  article-title: Robust semantic segmentation for automatic crack detection within pavement images using multi-mixing of global context and local image features
  publication-title: IEEE Transactions on Intelligent Transportation Systems
– volume: 170
  start-page: 105899
  year: 2025
  ident: bib20
  article-title: Semi-supervised crack detection using segment anything model and deep transfer learning
  publication-title: Automation in Construction
– reference: Xue, F., Chang, Y., Xu, W., Liang, W., Sheng, F., & Ming, A. (2025). Evidence-Based Real-Time Road Segmentation With RGB-D Data Augmentation. IEEE Transactions on Intelligent Transportation Systems.
– reference: Kulambayev, B., Astaubayeva, G., Tleuberdiyeva, G., Alimkulova, J., Nussupbekova, G., & Kisseleva, O. (2024). Deep CNN Approach with Visual Features for Real-Time Pavement Crack Detection. International Journal of Advanced Computer Science & Applications, 15(3).
– reference: Li, P., Wang, M., Fan, Z., Huang, H., Zhu, G., & Zhuang, J. (2024). OUR-Net: a multi-frequency network with octave max unpooling and octave convolution residual block for pavement crack segmentation. IEEE Transactions on Intelligent Transportation Systems.
– reference: Alshawabkeh, S., Wu, L., Dong, D., Cheng, Y., & Li, L. (2025). A Hybrid Approach for Pavement Crack Detection Using Mask R-CNN and Vision Transformer Model. Computers, Materials & Continua, 82(1).
– volume: 33
  start-page: 71
  year: 2024
  end-page: 96
  ident: bib12
  article-title: Enhanced U-Net Model for Accurate Aerial Road Segmentation
  publication-title: Machine Graphics & Vision
– volume: 14
  year: 2023
  ident: bib1
  article-title: Real-time road surface damage detection framework based on mask r-cnn model
  publication-title: International Journal of Advanced Computer Science and Applications
– reference: Kulambayev, B., Gleb, B., Katayev, N., Menglibay, I., & Momynkulov, Z. (2024). Real-Time Road Damage Detection System on Deep Learning Based Image Analysis. International Journal of Advanced Computer Science & Applications, 15(9).
– volume: 11
  start-page: 116
  year: 2023
  ident: bib4
  article-title: ECSNet: An accelerated real-time image segmentation CNN architecture for pavement crack detection
  publication-title: IEEE Transactions on Intelligent Transportation Systems, 24(12), 15105-15112.ssment. Journal of Big Data
– volume: 141
  start-page: 104436
  year: 2022
  ident: bib10
  article-title: Multi-scale feature fusion network for pixel-level pavement distress detection
  publication-title: Automation in Construction
– volume: 24
  start-page: 2219366
  year: 2023
  ident: bib8
  article-title: Fast and accurate semantic segmentation of road crack video in a complex dynamic environment
  publication-title: International Journal of Pavement Engineering
– reference: Chang, J. Y., & Xu, Z. X. (2024). Enhanced Water Puddle Segmentation and Detection Using DCU-Net. IEEE Internet of Things Journal.
– volume: 408
  start-page: 133582
  year: 2023
  ident: bib14
  article-title: Automated detection and segmentation of cracks in concrete surfaces using joined segmentation and classification deep neural network
  publication-title: Construction and Building Materials
– volume: 23
  start-page: 53
  year: 2022
  ident: bib5
  article-title: RUC-Net: A residual-Unet-based convolutional neural network for pixel-level pavement crack segmentation
  publication-title: Sensors
– volume: 21
  start-page: 2190
  year: 2022
  end-page: 2205
  ident: bib21
  article-title: Efficient attention-based deep encoder and decoder for automatic crack segmentation
  publication-title: Structural Health Monitoring
– volume: 1
  start-page: 145
  year: 2023
  end-page: 155
  ident: bib17
  article-title: Real-time seed detection and germination analysis in precision agriculture: A fusion model with u-net and cnn on jetson nano
  publication-title: IEEE Transactions on AgriFood Electronics
– volume: 65
  start-page: 103262
  year: 2025
  ident: bib11
  article-title: Advancing road safety: A lightweight feature fusion model for robust road crack segmentation
  publication-title: Advanced Engineering Informatics
– reference: Altayeva, A., Omarov, B., Suleimenov, Z., & Im Cho, Y. (2017, June). Application of multi-agent control systems in energy-efficient intelligent building. In 2017 Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems (IFSA-SCIS) (pp. 1-5). IEEE.
– reference: Yang, Y., Zhao, Z., Su, L., Zhou, Y., & Li, H. (2022, May). Research on pavement crack detection algorithm based on deep residual UNET neural network. In Journal of Physics: Conference Series (Vol. 2278, No. 1, p. 012020). IOP Publishing.
– volume: 174
  start-page: 106120
  year: 2025
  ident: bib13
  article-title: Topology-informed deep learning for pavement crack detection: Preserving consistent crack structure and connectivity
  publication-title: Automation in Construction
– volume: 26
  start-page: 593
  year: 2025
  end-page: 617
  ident: bib16
  article-title: PaveSAM–segment anything for pavement distress
  publication-title: Road Materials and Pavement Design
– reference: Kulambayev, B., Nurlybek, M., Astaubayeva, G., Tleuberdiyeva, G., Zholdasbayev, S., & Tolep, A. (2023). Real-time road surface damage detection framework based on mask r-cnn model. International Journal of Advanced Computer Science and Applications, 14(9).
– reference: Muturi, T. W., & Adu-Gyamfi, Y. (2025). Enhanced Crack Segmentation Using Meta’s Segment Anything Model with Low-Cost Ground Truths and Multimodal Prompts. Transportation Research Record, 03611981251322484.
– volume: 174
  start-page: 106120
  year: 2025
  ident: 10.1016/j.procs.2025.08.266_bib13
  article-title: Topology-informed deep learning for pavement crack detection: Preserving consistent crack structure and connectivity
  publication-title: Automation in Construction
  doi: 10.1016/j.autcon.2025.106120
– volume: 25
  start-page: 11282
  issue: 9
  year: 2024
  ident: 10.1016/j.procs.2025.08.266_bib9
  article-title: Robust semantic segmentation for automatic crack detection within pavement images using multi-mixing of global context and local image features
  publication-title: IEEE Transactions on Intelligent Transportation Systems
  doi: 10.1109/TITS.2024.3360263
– volume: 1
  start-page: 145
  issue: 2
  year: 2023
  ident: 10.1016/j.procs.2025.08.266_bib17
  article-title: Real-time seed detection and germination analysis in precision agriculture: A fusion model with u-net and cnn on jetson nano
  publication-title: IEEE Transactions on AgriFood Electronics
  doi: 10.1109/TAFE.2023.3332495
– volume: 11
  start-page: 116
  issue: 1
  year: 2023
  ident: 10.1016/j.procs.2025.08.266_bib4
  article-title: ECSNet: An accelerated real-time image segmentation CNN architecture for pavement crack detection
  publication-title: IEEE Transactions on Intelligent Transportation Systems, 24(12), 15105-15112.ssment. Journal of Big Data
– volume: 151
  start-page: 04024054
  issue: 1
  year: 2025
  ident: 10.1016/j.procs.2025.08.266_bib22
  article-title: Intelligent Detection of Sealed Crack with 2D Asphalt Pavement Images
  publication-title: Journal of Transportation Engineering, Part B: Pavements
– volume: 23
  start-page: 53
  issue: 1
  year: 2022
  ident: 10.1016/j.procs.2025.08.266_bib5
  article-title: RUC-Net: A residual-Unet-based convolutional neural network for pixel-level pavement crack segmentation
  publication-title: Sensors
  doi: 10.3390/s23010053
– ident: 10.1016/j.procs.2025.08.266_bib24
  doi: 10.14569/IJACSA.2024.01509107
– volume: 65
  start-page: 103262
  year: 2025
  ident: 10.1016/j.procs.2025.08.266_bib11
  article-title: Advancing road safety: A lightweight feature fusion model for robust road crack segmentation
  publication-title: Advanced Engineering Informatics
  doi: 10.1016/j.aei.2025.103262
– ident: 10.1016/j.procs.2025.08.266_bib23
  doi: 10.1109/JIOT.2024.3466390
– ident: 10.1016/j.procs.2025.08.266_bib7
  doi: 10.1109/IFSA-SCIS.2017.8023299
– ident: 10.1016/j.procs.2025.08.266_bib27
  doi: 10.1109/TITS.2024.3509140
– ident: 10.1016/j.procs.2025.08.266_bib28
  doi: 10.1088/1742-6596/2278/1/012020
– volume: 24
  start-page: 2219366
  issue: 1
  year: 2023
  ident: 10.1016/j.procs.2025.08.266_bib8
  article-title: Fast and accurate semantic segmentation of road crack video in a complex dynamic environment
  publication-title: International Journal of Pavement Engineering
  doi: 10.1080/10298436.2023.2219366
– volume: 16
  start-page: 801
  issue: 4
  year: 2016
  ident: 10.1016/j.procs.2025.08.266_bib2
  article-title: Parallel backpropagation neural network training for face recognition
  publication-title: Far East Journal of Electronics and Communications
  doi: 10.17654/EC016040801
– ident: 10.1016/j.procs.2025.08.266_bib3
  doi: 10.14569/IJACSA.2024.0150333
– volume: 21
  start-page: 2190
  issue: 5
  year: 2022
  ident: 10.1016/j.procs.2025.08.266_bib21
  article-title: Efficient attention-based deep encoder and decoder for automatic crack segmentation
  publication-title: Structural Health Monitoring
  doi: 10.1177/14759217211053776
– volume: 26
  start-page: 593
  issue: 3
  year: 2025
  ident: 10.1016/j.procs.2025.08.266_bib16
  article-title: PaveSAM–segment anything for pavement distress
  publication-title: Road Materials and Pavement Design
  doi: 10.1080/14680629.2024.2374863
– ident: 10.1016/j.procs.2025.08.266_bib19
  doi: 10.32604/cmc.2024.057213
– volume: 53
  start-page: 327
  issue: 2
  year: 2025
  ident: 10.1016/j.procs.2025.08.266_bib25
  article-title: Remote sensing analysis of the lidar drone mapping system for detecting damages to buildings, roads, and bridges using the faster cnn method
  publication-title: Journal of the Indian Society of Remote Sensing
  doi: 10.1007/s12524-024-01963-6
– ident: 10.1016/j.procs.2025.08.266_bib26
  doi: 10.14569/IJACSA.2023.0140979
– volume: 33
  start-page: 71
  issue: 3/4
  year: 2024
  ident: 10.1016/j.procs.2025.08.266_bib12
  article-title: Enhanced U-Net Model for Accurate Aerial Road Segmentation
  publication-title: Machine Graphics & Vision
  doi: 10.22630/MGV.2024.33.3.4
– ident: 10.1016/j.procs.2025.08.266_bib6
  doi: 10.32604/cmc.2022.029544
– volume: 170
  start-page: 105899
  year: 2025
  ident: 10.1016/j.procs.2025.08.266_bib20
  article-title: Semi-supervised crack detection using segment anything model and deep transfer learning
  publication-title: Automation in Construction
  doi: 10.1016/j.autcon.2024.105899
– volume: 14
  issue: 9
  year: 2023
  ident: 10.1016/j.procs.2025.08.266_bib1
  article-title: Real-time road surface damage detection framework based on mask r-cnn model
  publication-title: International Journal of Advanced Computer Science and Applications
  doi: 10.14569/IJACSA.2023.0140979
– volume: 408
  start-page: 133582
  year: 2023
  ident: 10.1016/j.procs.2025.08.266_bib14
  article-title: Automated detection and segmentation of cracks in concrete surfaces using joined segmentation and classification deep neural network
  publication-title: Construction and Building Materials
  doi: 10.1016/j.conbuildmat.2023.133582
– ident: 10.1016/j.procs.2025.08.266_bib15
  doi: 10.1177/03611981251322484
– volume: 141
  start-page: 104436
  year: 2022
  ident: 10.1016/j.procs.2025.08.266_bib10
  article-title: Multi-scale feature fusion network for pixel-level pavement distress detection
  publication-title: Automation in Construction
  doi: 10.1016/j.autcon.2022.104436
– ident: 10.1016/j.procs.2025.08.266_bib18
  doi: 10.1109/TITS.2024.3405995
SSID ssj0000388917
Score 2.3426754
Snippet Road surface integrity is critical for ensuring vehicular safety and reducing maintenance costs, yet traditional visual inspections are laborious and subject...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 131
SubjectTerms 2D U-Net
Deep learning
Pixel-wise segmentation
Road damage
semantic segmentation
Title Real-Time Pixel-Wise Segmentation of Road Surface Damage Using a 2D U-Net Architecture
URI https://dx.doi.org/10.1016/j.procs.2025.08.266
Volume 269
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1877-0509
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000388917
  issn: 1877-0509
  databaseCode: M~E
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF5FLQcuUF6ivLQHbmElZ22v18dCQZxCVQr0Zu2Tpm2cynWrpJX62zv7cGLRCAESF8vetbPWzJeZ2fE8EHorhLKgaAyhclSSrFCMCMoTYlKtksIqRnXim00U4zE_PCz3BoPrLhfm8rSoaz6fl2f_ldUwBsx2qbN_we7lj8IAnAPT4Qhsh-MfMX4fTD_iMjuGe5O5OSU_JucGRMLPacwy8vbh_kyAoXnRWAH_610xdZE7IXpADCnsCsnYtMOd3keGvhHrkwsAVz4e3bWEGEY9uvLYXh2JBbw48M-f974YAQJlN_denBwtWphfIvTLVDSzONcumpNuKvolQvZycJPdSZXxkpUXBXHFZoLiWTMWxTENrVuiQB1FHWHiVblW7AcPxLFTOsrVYKe5q8tK2S9Ftr3a_upWdYuC8QfbR5eet0kL2Fe5uM-blYPOlckpfcfm5Wt2Vat8fOCdtdZbNj1r5WALPYjbDLwT4PEIDUz9GD3sWnjgKNGfoO9LtOAVWnAfLXhmsUMLjmjBAS3YowULTHexRwvuo-Up-vbp48GHzyS22iAKDGZGLM-ttKkWMlPaZAWzbKSpUqlMMqltlueGMQlEoibX1ihgktFaMCPhljyR6TO0Uc9q8xxhKcBmhbsyatJMpFxwPhKpZrxQKTU03UbvOjJVZ6GiStWFGh5XnqqVo2qV8Aqouo1YR8oqgjkYexUw_3cPvvjXB1-i--4q-NleoY22uTCv0T112U7OmzceJLci9IjY
linkProvider ISSN International Centre
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=Real-Time+Pixel-Wise+Segmentation+of+Road+Surface+Damage+Using+a+2D+U-Net+Architecture&rft.jtitle=Procedia+computer+science&rft.au=Olzhayev%2C+Olzhas&rft.au=Kulambayev%2C+Bakhytzhan&rft.au=Omarov%2C+Batyrkhan&rft.date=2025&rft.pub=Elsevier+B.V&rft.issn=1877-0509&rft.eissn=1877-0509&rft.volume=269&rft.spage=131&rft.epage=139&rft_id=info:doi/10.1016%2Fj.procs.2025.08.266&rft.externalDocID=S1877050925026110
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1877-0509&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1877-0509&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1877-0509&client=summon