Computational intelligence for road pavement condition assessment: a deep learning perspective

Abstract

Pavement defects such as cracks and potholes compromise road safety and demand timely maintenance. Traditional manual inspection is slow and exposes workers to safety risks, whereas automated systems offer a promising alternative. This survey provides a comprehensive review of deep learning methods for road condition assessment. We first examine 2D image-based approaches, tracing their evolution from convolutional neural networks (CNNs) to Transformers. Although these methods are widely adopted, they remain sensitive to lighting conditions and cannot directly capture physical properties such as defect depth. To address these limitations, we review 3D sensing and subsurface diagnostic techniques, which provide essential geometric information for severity assessment. The primary focus of this paper is on evaluation: we summarize key public datasets and evaluation metrics and analyze the persistent gap between algorithmic performance and the practical needs of engineering, emphasizing the importance of assessing the actual utility of models in the field. Finally, we discuss several key challenges and promising research avenues, arguing that future work should prioritize model robustness, reliability, and the integration of these systems into real-world maintenance workflows.

Keywords

Pavement defect detection / Road condition assessment / Deep learning / Transformers / Self-supervised learning / Vision-language models / LiDAR/3D

References

[1] Lim RS, La HM, Shan Z, Sheng W (2011) Developing a crack inspection robot for bridge maintenance. In: 2011 IEEE International Conference on Robotics and Automation, IEEE, pp 6288–6293

[2] Prasanna P, Dana KJ, Gucunski N, Basily BB, La HM, Lim RS, Parvardeh H. Automated crack detection on concrete bridges. IEEE Trans Autom Sci Eng, 2014, 13(2): 591-599

[3] Zou Q, Zhang Z, Li Q, Qi X, Wang Q, Wang S. Deepcrack: learning hierarchical convolutional features for crack detection. IEEE Trans Image Process, 2018, 28(3): 1498-1512

[4] Kim B, Yuvaraj N, Sri Preethaa K, Arun Pandian R. Surface crack detection using deep learning with shallow CNN architecture for enhanced computation. Neural Comput Appl, 2021, 33(15): 9289-9305

[5] Miller JS, Bellinger WY et al (2003) Distress identification manual for the long-term pavement performance program. Tech rep, United States. Department of Transportation. Federal Highway Administration

[6] Gao M, Wang X, Zhu S. Guan P (2020) Detection and segmentation of cement concrete pavement pothole based on image processing technology. Math Probl Eng, 2020, 1: 1360832

[7] Bureau of Infrastructure and Transport Research Economics (2024) Australian infrastructure and transport statistics yearbook 2024: transport safety. https://www.bitre.gov.au/publications/2024/australian-infrastructure-and-transport-statistics-yearbook-2024/transport-safety. Accessed 27 Apr 2026

[8] Wang H, Al-Saadi I, Lu P, Jasim A. Quantifying greenhouse gas emission of asphalt pavement preservation at construction and use stages using life-cycle assessment. Int J Sustain Transp, 2020, 14(1): 25-34

[9] Yu J, Jiang J, Fichera S, Paoletti P, Layzell L, Mehta D, Luo S. Road surface defect detection–from image-based to non-image-based: a survey. IEEE Trans Intell Transp Syst, 2024, 25(9): 10581-10603

[10] Zhuang H, Cheng Y, Zhou M, Yang Z. Deep learning for surface crack detection in civil engineering: a comprehensive review. Measurement, 2025

[11] Fan L, Wang D, Wang J, Li Y, Cao Y, Liu Y, Chen X, Wang Y. Pavement defect detection with deep learning: a comprehensive survey. IEEE Trans Intell Veh, 2023, 9(3): 4292-4311

[12] Fan R, Ozgunalp U, Hosking B, Liu M, Pitas I. Pothole detection based on disparity transformation and road surface modeling. IEEE Trans Image Process, 2019, 29: 897-908

[13] Ohtsu M (2020) Acoustic emission and related non-destructive evaluation techniques in the fracture mechanics of concrete: fundamentals and applications, 2nd ed. Oxford, UK: Woodhead Publishing. https://shop.elsevier.com/books/acoustic-emission-and-related-non-destructive-evaluation-techniques-in-the-fracture-mechanics-of-concrete/ohtsu/978-0-12-822136-5

[14] Graham-Jones J, Summerscales J (2015) Marine applications of advanced fibre-reinforced composites. Amsterdam, The Netherlands: Woodhead Publishing. https://shop.elsevier.com/books/marine-applications-of-advanced-fibre-reinforced-composites/graham-jones/978-1-78242-250-1

[15] Zhao L, Wu Y, Luo X, Yuan Y. Automatic defect detection of pavement diseases. Remote Sensing, 2022, 14(19 4836

[16] Tsai YC, Chatterjee A. Pothole detection and classification using 3D technology and watershed method. J Comput Civ Eng, 2018, 322 04017078

[17] Yang H, Xu X. Intelligent crack extraction based on terrestrial laser scanning measurement. Meas Control, 2020, 533–4): 416-426

[18] Du Y, Zhou Z, Wu Q, Huang H, Xu M, Cao J, Hu G (2020) A pothole detection method based on 3D point cloud segmentation. In: Twelfth International Conference on Digital Image Processing (ICDIP 2020), SPIE, vol 11519, pp 56–64

[19] Yu Y, Li J, Guan H, Wang C (2014) 3D crack skeleton extraction from mobile lidar point clouds. In: 2014 IEEE geoscience and remote sensing symposium, IEEE, pp 914–917

[20] Zhao G, Wang T, Ye J. Anisotropic clustering on surfaces for crack extraction. Mach Vis Appl, 2015, 26(5): 675-688

[21] Amhaz R, Chambon S, Idier J, Baltazart V. Automatic crack detection on two-dimensional pavement images: an algorithm based on minimal path selection. IEEE Trans Intell Transp Syst, 2016, 17(10): 2718-2729

[22] Tian F, Zhao Y, Che X, Zhao Y, Xin D. Concrete crack identification and image mosaic based on image processing. Appl Sci, 2019, 9(22): 4826

[23] Cao X, Li T, Bai J, Wei Z. Identification and classification of surface cracks on concrete members based on image processing. Trait Signal, 2020

[24] Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, Curran Associates, vol 25, pp 1097–1105

[25] Fan J, Bocus MJ, Wang L, Fan R (2021) Deep convolutional neural networks for road crack detection: qualitative and quantitative comparisons. In: 2021 IEEE International Conference on Imaging Systems and Techniques (IST), IEEE, pp 1–6

[26] Cha YJ, Choi W, Suh G, Mahmoudkhani S, Büyüköztürk O. Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types. Comput-Aided Civ Infrastruct Eng, 2018, 33(9): 731-747

[27] Du Y, Pan N, Xu Z, Deng F, Shen Y, Kang H. Pavement distress detection and classification based on YOLO network. Int J Pavement Eng, 2021, 22(13): 1659-1672

[28] Dung CV, et al. . Autonomous concrete crack detection using deep fully convolutional neural network. Autom Constr, 2019, 99: 52-58

[29] Huyan J, Li W, Tighe S, Xu Z, Zhai J. Cracku-net: a novel deep convolutional neural network for pixelwise pavement crack detection. Struct Control Health Monit, 2020, 27(8 e2551

[30] Qu Z, Chen W, Wang SY, Yi TM, Liu L. A crack detection algorithm for concrete pavement based on attention mechanism and multi-features fusion. IEEE Trans Intell Transp Syst, 2021, 238): 11710-11719

[31] Chen T, Cai Z, Zhao X, Chen C, Liang X, Zou T, Wang P. Pavement crack detection and recognition using the architecture of SegNet. J Ind Inf Integr, 2020, 18100144

[32] Liu J, Yang X, Lau S, Wang X, Luo S, Lee VCS, Ding L. Automated pavement crack detection and segmentation based on two-step convolutional neural network. Comput Aided Civ Infrastruct Eng, 2020, 35(11): 1291-1305

[33] Zhang AA, Shang J, Li B, Hui B, Gong H, Li L, Zhan Y, Ai C, Niu H, Chu X, et al. . Intelligent pavement condition survey: overview of current researches and practices. Journal of road engineering, 2024, 4(3): 257-281

[34] Zhu G, Liu J, Fan Z, Yuan D, Ma P, Wang M, Sheng W, Wang KC. A lightweight encoder-decoder network for automatic pavement crack detection. Comput Aided Civ Infrastruct Eng, 2024, 39(12): 1743-1765

[35] Ma N, Song Z, Hu Q, Liu CW, Han Y, Zhang Y, Fan R, Xie L (2025) Vehicular road crack detection with deep learning: a new online benchmark for comprehensive evaluation of existing algorithms. Preprint at https://arxiv.org/abs/2503.18082

[36] Li J, Zhang Y, Yun P, Zhou G, Chen Q, Fan R. Roadformer: duplex transformer for rgb-normal semantic road scene parsing. IEEE Trans Intell Veh, 2024, 9(7): 5163-5172

[37] Liu H, Miao X, Mertz C, Xu C, Kong H (2021) Crackformer: transformer network for fine-grained crack detection. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 3783–3792

[38] Li P, Zhou B, Wang C, Hu G, Yan Y, Guo R, Xia H. CNN-based pavement defects detection using grey and depth images. Autom Constr, 2024, 158 105192

[39] Jing J, Yang X, Ding L, Wang H, Guan J, Hou Y, El-Badawy SM. Self-adaptive 2D3D image fusion for automated pixel-level pavement crack detection. Autom Constr, 2024, 168 105756

[40] Ma N, Fan R, Xie L. Up-cracknet: unsupervised pixel-wise road crack detection via adversarial image restoration. IEEE Trans Intell Transp Syst, 2024, 25(10): 13926-13936

[41] Liu X, Wu K, Cai X, Huang W (2024) Semi-supervised semantic segmentation using cross-consistency training for pavement crack detection. Road Mater Pavement Des 25(6):1368–1380

[42] Zhang H, Qian Z, Tan Y, Xie Y, Li M. Investigation of pavement crack detection based on deep learning method using weakly supervised instance segmentation framework. Constr Build Mater, 2022, 358 129117

[43] Jongwiriyanurak N, Zeng Z, Goo JM, Wang X, Ilyankou I, Sriroongvikrai K, Christie N, Wang M, Chen H, Haworth J (2024) V-roast: visual road assessment. Can vlm be a road safety assessor using the irap standard? Preprint at https://arxiv.org/abs/2408.10872

[44] Zhang Y, Liu C. Vision-enhanced multi-modal learning framework for non-destructive pavement damage detection. Autom Constr, 2025, 177 106389

[45] Zan C, Du S, Ikenaga T (2025) Clip-guided cross-modal feature fusion based few-shot learning for nighttime pavement defect detection. In: 2025 19th International Conference on Machine Vision and Applications (MVA), IEEE, pp 1–5

[46] Federal Highway Administration (2023) Successful practices for quality management of pavement surface condition data collection and analysis. Tech Rep FHWA-RC-23-0002, Federal Highway Administration

[47] Federal Highway Administration (2023) Unmanned aircraft systems (UAS) for highway construction and maintenance: a field use guide. Tech Rep FHWA-HIF-23-012, Federal Highway Administration

[48] Chang GK, Sankaranarayanan S, Gilliland A (2024) NDT and ICT for asphalt pavement construction: Techbrief (PMTP/IC/DPS/VETA). Tech Rep FHWA-HIF-24-031, Federal Highway Administration. https://rosap.ntl.bts.gov/view/dot/78767. Accessed 20 Jan 2026

[49] American Association of State Highway and Transportation Officials (2022) Standard practice for continuous thermal profile of asphalt mixture during construction. AASHTO R110-22, Washington, DC, USA. https://store.accuristech.com/standards/aashto-r-110-22. Accessed 20 Jan 2026

[50] ASTM International (2022) Standard test method for measuring the p-wave speed and the thickness of concrete plates using the impact-echo method. ASTM C1383-15(2022). https://www.astm.org/c1383-15r22.html. Accessed 20 Jan 2026

[51] Edmund Optics (2024) Successful light polarization techniques. Edmund Optics Knowledge Center. https://www.edmundoptics.com/knowledge-center/application-notes/illumination/successful-light-polarization-techniques/. Accessed 20 Jan 2026

[52] Abdellatif M, Peel H, Cohn AG, Fuentes R. Pavement crack detection from hyperspectral images using a novel asphalt crack index. Remote Sens, 2020, 12(18): 3084

[53] Sattar S, Li S, Chapman M. Road surface monitoring using smartphone sensors: a review. Sensors, 2018, 18(11): 3845

[54] Eriksson J, Girod L, Hull B, Newton R, Madden S, Balakrishnan H (2008) The pothole patrol: using a mobile sensor network for road surface monitoring. In: Proceedings of MobiSys 2008, pp 29–39. https://nms.csail.mit.edu/papers/p2-mobisys-2008.pdf. Accessed 12 Oct 2025

[55] Olsen MJ (2013) Guidelines for the use of mobile LIDAR in transportation applications. NCHRP Rep 748. Washington, DC, USA: Transportation Research Board. https://highways.fhwa.dot.gov/safety/data-analysis-tools/rsdp/rsdp-tools/national-cooperative-highway-research-program-nchrp-5

[56] US Geological Survey (2024) Lidar Base Specification 2024 Rev. A. https://www.usgs.gov/media/files/lidar-base-specification-2024-rev-a. Accessed 28 Jan 2026

[57] American Society for Photogrammetry and Remote Sensing (2019) Las specification, version 1.4–R15. https://www.asprs.org/wp-content/uploads/2019/07/LAS_1_4_r15.pdf. Accessed 18 Dec 2025

[58] Pavemetrics Systems Inc (2021) LCMS-2D / LCMS-3D whitepaper. White paper. https://www.pavemetrics.com/downloads/lcms-2d-3d-whitepaper/. Accessed 28 Jan 2026

[59] International Organization for Standardization (2002) Characterization of pavement texture by use of surface profiles - Part 3: Specification and classification of profilometers, ISO 13473-3:2002. International Organization for Standardization, Geneva. https://www.iso.org/standard/29426.html

[60] ASTM International (2023) Standard practice for calculating pavement macrotexture mean profile depth. ASTM E1845-23. https://www.astm.org/e1845-23.html. Accessed 28 Jan 2026

[61] Fan R, Liu Y, Yang X, Bocus MJ, Dahnoun N, Tancock S (2018) Real-time stereo vision for road surface 3-d reconstruction. In: 2018 IEEE International Conference on Imaging Systems and Techniques (IST), IEEE, pp 1–6

[62] Basler AG (2023) Time-of-flight versus stereo vision – who scores where? Technical article. https://www.baslerweb.com/en/learning/time-of-flight-stereovision/. Accessed 10 Jan 2026

[63] Zhang Y, Chen C, Wu Q, Lu Q, Zhang S, Zhang G, Yang Y. A Kinect-based approach for 3d pavement surface reconstruction and cracking recognition. IEEE Trans Intell Transp Syst, 2018, 19(12): 3935-3946

[64] American Association of State Highway and Transportation Officials (2018) AASHTO R 37-04 (2018) Standard practice for application of ground penetrating radar (GPR) to highways. American Association of State Highway and Transportation Officials, Washington. https://store.transportation.org. Accessed 28 Jan 2026

[65] ASTM International (2022) Standard test method for evaluating asphalt-covered concrete bridge decks using ground penetrating radar, ASTM D6087–22. Standard. https://doi.org/10.1520/D6087-22

[66] Texas Department of Transportation (2024) Seismic evaluation tools (PSPA/DSPA) — TxDOT pavement evaluation manual. Technical manual. https://www.txdot.gov/. Accessed 20 Jan 2026

[67] Federal Aviation Administration (2021) Portable seismic property analyzer (PSPA). https://www.airporttech.tc.faa.gov/Airport-Pavement/Evaluation-Management/Nondestructive-Testing-Technology/NDT-Technology/Portable-Seismic-Pavement-Analyzer. Accessed 20 Jan 2026

[68] ASTM International (2018) Standard test method for measuring the longitudinal profile of traveled surfaces with an accelerometer-established inertial profiling reference, ASTM E950/E950M-09(2018). Standard. https://www.astm.org/e0950_e0950m-09r18.html. Accessed 20 Jan 2026

[69] ASTM International (2021) Standard practice for computing international roughness index of roads from longitudinal profile measurements, ASTM E1926-08(2021). https://www.astm.org/e1926-08r21.html. Accessed 20 Jan 2026

[70] Sayers MW, Gillespie TD, Queiroz CAV (1986) The international road roughness experiment: establishing correlation and a calibration standard for measurements. Technical Paper 45, World Bank, Washington, DC. https://documents.worldbank.org/en/publication/documents-reports/documentdetail/326081468740204115. Accessed 20 Jan 2026

[71] Sayers MW, Gillespie TD, Queiroz CAV (1986) The international road roughness experiment: a basis for establishing a standard scale for road roughness measurements. Transportation Research Record (1084):76–85. https://onlinepubs.trb.org/Onlinepubs/trr/1986/1084/1084-010.pdf. Accessed 20 Jan 2026

[72] American Association of State Highway and Transportation Officials (2020) AASHTO R 32-20: Standard recommended practice for calibrating the load cell and deflection sensors for a falling weight deflectometer. Standard, Washington, DC. https://store.accuristech.com/standards/aashto-r-32-20. Accessed 20 Jan 2026

[73] ASTM International (2020) Standard test method for deflections with a falling-weight-type impulse load device, ASTM D4694-09(2020).https://www.astm.org/d4694-09r20.html. Accessed 20 Jan 2026

[74] ASTM International (2020) Standard guide for calculating in situ equivalent elastic moduli of pavement materials using layered elastic theory, ASTM D5858-96(2020). Standard. https://www.astm.org/d5858-96r20.html. Accessed 20 Jan 2026

[75] Federal Highway Administration (2017) 23 CFR Part 490 Subpart C: national performance management measures for assessing pavement condition. Office of the Federal Register, National Archives and Records Administration. https://www.ecfr.gov/current/title-23/chapter-I/subchapter-E/part-490/subpart-C. Accessed 20 Jan 2026

[76] Federal Highway Administration (2024) Highway performance monitoring system (HPMS) field manual. Tech Rep No. FHWA-2023-0014-0003. https://downloads.regulations.gov/FHWA-2023-0014-0003/attachment_1.pdf. Accessed 20 Jan 2026

[77] Grogg M, Van T, Rozycki R, Vaughn R, Roff T, Clarke J, Beatty W, Buck J, Christenson A, Chang C (2018) Computation procedure for the pavement condition measures. Tech Rep No. FHWA-HIF-18-022. https://www.fhwa.dot.gov/tpm/guidance/hif18022.pdf. Accessed 20 Jan 2026

[78] ASTM International (2023) Standard practice for roads and parking lots pavement condition index surveys, ASTM D6433-23. https://www.astm.org/d6433-23.html. Accessed 20 Jan 2026

[79] ASTM International (2023) Standard test method for measuring rut-depth of pavement surfaces using a straightedge, ASTM E1703/E1703M-10(2023). https://www.astm.org/e1703_e1703m-10r23.html. Accessed 20 Jan 2026

[80] Federal Highway Administration (2014) Distress identification manual for the long-term pavement performance program (fifth revised edition). Tech Rep No. FHWA-HRT-13-092, Federal Highway Administration, Office of Infrastructure Research and Development. https://highways.dot.gov/sites/fhwa.dot.gov/files/docs/research/long-term-pavement-performance/products/1401/distress-identification-manual-13092.pdf. Accessed 20 Jan 2026

[81] Heath AC, Roesler JR, Harvey JT. Modeling longitudinal, corner and transverse cracking in jointed concrete pavements. Int J Pavement Eng, 2003, 4(1): 51-58

[82] Swarna S, Tech M, Hossain K (2018) Effect of interface bonds on pavement performance. In: Proceedings of the 2018 TAC Conference, Saskatoon, Saskatchewan. Transportation Association of Canada (TAC), Ottawa, Ontario

[83] Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Commun ACM, 2017, 60(6): 84-90

[84] Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. Preprint at https://arxiv.org/abs/1409.1556

[85] He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR, pp 770–778. https://doi.org/10.1109/CVPR.2016.90

[86] Su QF, Zhou Z, Zhu M, Wang H, Ye J (2020) Concrete crack detection based on EfficientNet-B0 with transfer learning. IEEE Access

[87] Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: in Proc Adv Neural Inf Process Syst, pp 91–99

[88] Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: in Proc IEEE Conf Comput Vis Pattern Recognit, pp 779–788

[89] Lin TY, Goyal P, Girshick R, He K, Dollár P (2018) Focal loss for dense object detection. Preprint at https://arxiv.org/abs/1708.02002

[90] Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Proc MICCAI, Springer, pp 234–241. https://doi.org/10.1007/978-3-319-24574-4_28

[91] Chen LC, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proc ECCV, pp 801–818. Preprint at https://arxiv.org/abs/1802.02611

[92] He K, Gkioxari G, Dollár P, Girshick R (2017) Mask R-CNN. In: Proceedings of the IEEE international conference on computer vision, pp 2961–2969

[93] Tang W, Huang S, Zhang X, Huangfu L (2022) Pict: a slim weakly supervised vision transformer for pavement distress classification. Preprint at https://arxiv.org/abs/2209.10074

[94] Chen Y, Zhou R, Yang X, Guo Z, Zhang J, Ouyang S, Huang J, Wang L, Xu G. A fast inference vision transformer for automatic pavement image classification and its visual interpretation method. Remote Sens, 2022, 14(8 1877

[95] Huang WQ, Feng L, He YL. Ltpln: automatic pavement distress detection. PLoS One, 2024, 1910 e0309,172

[96] Wu W, Zhu F, Li Z, Li X, Li X, Wang J. Optimized deep learning model with integrated spectrum focus transformer for pavement distress recognition and classification. Sci Rep, 2025, 15 3803

[97] Zhang S, Wang K, Liu Z, Huang M, Huang S. The fine feature extraction and attention re-embedding model based on the Swin Transformer for pavement damage classification. Algorithms, 2025, 186): 369

[98] Luo H, Li J, Cai L, Wu M. STrans-YOLOX: fusing Swin Transformer and YOLOX for automatic pavement crack detection. Appl Sci, 2023, 13(3): 1999

[99] Zhao Y, Lv W, Xu S, Wei J, Wang G, Dang Q, Liu Y, Chen J (2024) DETRs beat YOLOs on real-time object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 16965–16974. https://doi.org/10.1109/CVPR52733.2024.01605

[100] Zuo C, Huang N, Yuan C, Li Y. Pavement-DETR: a high-precision real-time detection transformer for pavement defect detection. Sensors, 2025, 25(8 2426

[101] Sun Z, Zhai J, Pei L, Li W, Zhao K. Automatic pavement crack detection transformer based on convolutional and sequential feature fusion. Sensors, 2023, 237): 3772

[102] Chen S, Feng Z, Xiao G, Chen X, Gao C, Zhao M, Yu H. Pavement crack detection based on the improved swin-unet model. Buildings, 2024

[103] Yu M, Wu D, Rao W, Cheng L, Li R, Li Y (2022) Automated road crack detection method based on visual transformer with multi-head cross-attention. In: 2022 IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC), pp 328–332. https://doi.org/10.1109/SDPC55702.2022.9915808

[104] Guo F, Qian Y, Liu J, Yu H. Pavement crack detection based on transformer network. Autom Constr, 2023, 145 104646

[105] Guo F, Liu J, Xie Q, Yu H. A two-stage framework for pixel-level pavement surface crack detection. Eng Appl Artif Intell, 2024, 133(108 312

[106] Liu H, Yang J, et al. . Crackformer network for pavement crack segmentation. IEEE Trans Intell Transp Syst, 2023, 249): 9240-9252

[107] Liang F, Li Q, Yu H, Wang W. Crackclip: adapting vision-language models for weakly supervised crack segmentation. Entropy, 2025, 27(2): 127

[108] Li Q, Arnab A, Yang Y, Dehghani M, Hassani A, Gritsenko A, Wang X, Zhai X, Lučić M, Houlsby N (2022) Language-driven semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), LSeg

[109] Liang F, Li Q, Yu H, Wang W et al (2023) Open-vocabulary semantic segmentation with mask-adapted clip. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, oVSeg

[110] Ge K, Wang C, Guo Y, Tang Y, Hu Z, Chen H. Fine-tuning vision foundation model for crack segmentation in civil infrastructures. Constr Build Mater, 2024, 431 136573

[111] Yoon H, Kim S. Open-vocabulary crack object detection through attribute-guided similarity probing. Appl Sci, 2025, 15(19 10350

[112] Minderer M, Gritsenko A, Stone A, Neumann M, Weissenborn D, Dosovitskiy A, Mahendran A, Arnab A, Dehghani M, Shen Z et al (2022) Simple open-vocabulary object detection. In: European conference on computer vision, Springer, pp 728–755

[113] Liu S, Zeng Z, Ren T, Li F, Zhang H, Yang J, Li C, Yang J, Su H, Zhu J, Zhang L (2023) Grounding dino: marrying dino with grounded pre-training for open-set object detection. Preprint at https://arxiv.org/abs/2303.05499

[114] Kirillov A, Mintun E, Ravi N, Mao H, Rolland C, Gustafson L, Xiao T, Whitehead S, Berg AC, Lo WY et al (2023) Segment anything. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 4015–4026

[115] Xu S et al (2025) Zero-shot pavement monitoring with large language models. Preprint at https://arxiv.org/abs/2504.06785

[116] Zhou K, Yang J, Loy CC, Liu Z. Learning to prompt for vision-language models. Int J Comput Vision, 2022, 1309): 2337-2348

[117] Gao P, Geng S, Jiang R, Yuan N, Hsieh TY, Qiao Y (2022) Tip-adapter: training-free adaption of clip for few-shot classification. In: Computer Vision – ECCV 2022

[118] Ding H, Du Y, Xia Z. Urban road anomaly monitoring using vision-language models for enhanced safety management. Appl Sci, 2025, 15(5 2517

[119] Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J, Krueger G, Sutskever I (2021) Learning transferable visual models from natural language supervision. Preprint at https://arxiv.org/abs/2103.00020

[120] Chen C, et al. . Pavement crack detection and classification based on fusion feature of lbp and pca with svm. Int J Pavement Eng, 2022, 239): 3274-3283

[121] Shi Y, et al. . Automatic road crack detection using random structured forests. IEEE Trans Intell Transp Syst, 2016, 17(12): 3434-3445

[122] Cord A, Chambon S. Automatic road defect detection by textural pattern recognition based on AdaBoost. Comput-Aided Civ Infrastruct Eng, 2012, 27(4): 244-259

[123] Chen Z, Gao Y, Yu Z, et al. . Review of image classification algorithms based on convolutional neural networks. Remote Sensing, 2021, 13(24): 4712

[124] Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 1251–1258

[125] Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: CVPR, pp 7132–7141. https://doi.org/10.1109/CVPR.2018.00745

[126] Yang Q, Shi W, Chen J, Lin W. Deep convolution neural network-based transfer learning method for civil infrastructure crack detection. Autom Constr, 2020, 116 103199

[127] Rajadurai R, Kang ST. Automated vision-based crack detection on concrete surfaces using deep learning. Appl Sci (Basel), 2021, 11(11 5229

[128] Matarneh S, Elghaish F, Edwards DJ, Rahimian FP, Abdellatef E, Ejohwomu O. Automatic crack classification on asphalt pavement surfaces using convolutional neural networks and transfer learning. J Inf Technol Constr, 2024, 29: 1239-1256

[129] Bukhsh ZA, Jansen N, Saeed A. Damage detection using in-domain and cross-domain transfer learning. Neural Comput Appl, 2021, 3324): 16921-16936

[130] Gao Y, Mosalam KM. Peer hub ImageNet: a large-scale multiattribute benchmark data set of structural images. J Struct Eng, 2020, 146(10 04020198

[131] Shin HK, Ahn YH, Lee SH, Kim HY. Automatic concrete damage recognition using multi-level attention convolutional neural network. Materials (Basel), 2020, 1323 5549

[132] Qi Z, Liu D, Zhang J, Chen J. Micro-concrete crack detection of underwater structures based on convolutional neural network. Mach Vis Appl, 2022, 335): 74

[133] Ali I, et al. . The classification and localization of crack using lightweight convolutional neural networks. Eng Struct, 2022, 260: 114180

[134] Ali L, Alnajjar F, Al Jassmi H, Gocho M, Khan W, Serhani MA. Performance evaluation of deep CNN-based crack detection and localization techniques for concrete structures. Sensors (Basel), 2021, 21(5 1688

[135] Ali L, Al Jassmi H, Khan W, Alnajjar F. Crack45k: integration of vision transformer with tubularity flow field (TUFF) and sliding-window approach for crack-segmentation in pavement structures. Buildings, 2023, 131 55

[136] Bai Y, Sezen H, Yilmaz A. Detecting cracks and spalling automatically in extreme events by end-to-end deep learning frameworks. ISPRS Ann Photogramm Remote Sens Spat Inf Sci, 2021, V-2-2021: 161-168

[137] Taha H, El-Habrouk H, Bekheet W, El-Naghi S, Torki M. Pixel-level pavement crack segmentation using UAV remote sensing images based on the ConvNeXt-UperNet. Alex Eng J, 2025

[138] Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. Preprint at https://arxiv.org/abs/1704.04861

[139] Hou X, Zhang Z, Li W et al (2021) MobileCrack: an adaptive lightweight CNN model for pavement crack image classification. J Transp Eng B Pavements

[140] Liu Z, Mao H, Wu CY, Feichtenhofer C, Darrell T, Xie S (2022) A convnet for the 2020s. CVPR pp 11976–11986. https://doi.org/10.1109/CVPR52688.2022.01167

[141] Song C, Zhang W, Li H et al (2025) Automatic crack defect detection via multiscale feature aggregation and adaptive fusion with multiple-dimension attention. Autom Constr

[142] Vishwakarma R, Vennelakanti R (2021) CNN model & tuning for global road damage detection. In: IEEE Big Data Cup 2020. Preprint at https://arxiv.org/abs/2103.09512

[143] Cai Z, Vasconcelos N (2018) Cascade R-CNN: delving into high quality object detection. In: Proc IEEE Conf Comput Vis Pattern Recognit, pp 6154–6162

[144] Song L, Wang X. Faster region convolutional neural network for automated pavement distress detection. Road Mater Pavement Des, 2021, 221): 23-41

[145] Shen T, Nie M (2020) Pavement damage detection based on cascade R-CNN. In: Proceedings of the 4th International Conference on Computer Science and Application Engineering (CSAE), ACM, pp 1–5

[146] Fu R, Cao M, Novak D, Qian X, Alkayem NF (2023) Extended efficient convolutional neural network for concrete crack detection with illustrated merits. Autom Constr 156:105098. Elsevier

[147] Marin B, Brown KE, Erden MS (2021) Automated masonry crack detection with Faster R-CNN. In: 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE). IEEE. https://doi.org/10.1109/CASE49439.2021.9551683

[148] Park SS, Tran VT, Lee DE. Application of various YOLO models for computer vision-based real-time pothole detection. Appl Sci, 2021, 11(23 11229

[149] Teng S, Liu Z, Chen G, Cheng L. Concrete crack detection based on well-known feature extractor model and the yolo_v2 network. Appl Sci, 2021, 112 813

[150] Du FJ, Jiao SJ. Improvement of lightweight convolutional neural network model based on YOLO algorithm and its research in pavement defect detection. Sensors, 2022, 229): 3537

[151] Wang D, Liu Z, Gu X, Wu W, Chen Y, Wang L. Automatic detection of pothole distress in asphalt pavement using improved convolutional neural networks. Remote Sens, 2022

[152] Wu P, Liu A, Fu J, Ye X, Zhao Y (2022) Autonomous surface crack identification of concrete structures based on an improved one-stage object detection algorithm. Eng Struct 272:114962. Elsevier

[153] Yang Z, Li L, Luo W. Pdnet: improved yolov5 nondeformable disease detection network for asphalt pavement. Comput Intell Neurosci, 2022

[154] Du FJ, Jiao SJ. Improvement of lightweight convolutional neural network model based on YOLO algorithm and its research in pavement defect detection. Sensors, 2022

[155] Chu Y, Xiang X, Wang Y, Huang B (2022) Pavement disease detection through improved yolov5s neural network. Comput Intell Neurosci 2022

[156] Guo K, He C, Yang M, Wang S (2022) A pavement distresses identification method optimized for yolov5s. Sci Rep 12(1)

[157] Xiang W, Wang H, Xu Y, Zhao Y, Zhang L, Duan Y (2023) Road disease detection algorithm based on yolov5s-dsg. J Real-Time Image Process 20(3)

[158] Wu L, Duan Z, Liang C. Research on asphalt pavement disease detection based on improved yolov5s. J Sensors, 2023, 2023 1–12, article ID 2069044

[159] Liu W (2016) Ssd: single shot multibox detector. In: Proc 14th Eur Conf Comput Vis, pp 21–37

[160] Yan K, Zhang Z. Automated asphalt highway pavement crack detection based on deformable Single Shot MultiBox Detector under a complex environment. IEEE Access, 2021, 9: 150925-150938

[161] Yan K, Zhang Z. Automated asphalt highway pavement crack detection and localization in complex environment. IEEE Access, 2021, 9: 150925-150938

[162] Ochoa-Ruiz G, Angulo-Murillo AA, Ochoa-Zezzatti A, Aguilar-Lobo LM, Vega-Fernández JA, Natraj S. An asphalt damage dataset and detection system based on RetinaNet for road conditions assessment. Appl Sci, 2020, 10(11 3974

[163] Tran VP, Tran TS, Lee HJ, Kim KD, Baek J, Nguyen TT. One stage detector (RetinaNet)-based crack detection for asphalt pavements considering pavement distresses and surface objects. J Civ Struct Health Monit, 2021, 11: 205-222

[164] Jiang Y, Pang D, Li C. A deep learning approach for detection and classification of concrete damage using YOLO-v3. Autom Constr, 2021, 128 103785

[165] Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, pp 3431–3440. https://doi.org/10.1109/CVPR.2015.7298965

[166] Mei Q, Gül M, Azim MR. Densely connected deep neural network considering connectivity of pixels for automatic crack detection. Autom Constr, 2020, 110 103018

[167] Choi W, Cha YJ. Sddnet: real-time crack segmentation. IEEE Trans Ind Electron, 2020, 679): 8016-8025

[168] Zhang H, Liu J, Hu G. FCN attention enhancing asphalt pavement crack detection through attention mechanisms and fully convolutional networks. Sci Rep, 2025, 15 25257

[169] Yu G, Dong J, Wang Y, Zhou X. Ruc-net: a residual-Unet-based convolutional neural network for pixel-level pavement crack segmentation. Sensors (Basel), 2022, 23(1): 53

[170] Han C, Ma T, Huyan J, Huang X, Zhang Y. Crackw-net: a novel pavement crack image segmentation convolutional neural network. IEEE Trans Intell Transp Syst, 2022, 23(11): 22135-22144

[171] Zhang et al (2023) Asymmetric dual-decoder-U-net for pavement crack semantic segmentation. Adv Eng Inform. https://doi.org/10.1016/j.sc.2023.003989

[172] Al-maqtari O, Peng B, Al-Huda Z, Al-Malahi A, Maqtary N. Lightweight yet effective: a modular approach to crack segmentation. IEEE Trans Intell Veh, 2024

[173] Zim AH, Iqbal A, Al-Huda Z, Malik A, Kuribayashi M (2025) Efficientcracknet: a lightweight model for crack segmentation. In: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), IEEE, pp 6279–6289

[174] Tse KW, Pi R, Yang W, Yu X, Wen CY. Advancing UAV-based inspection system: the USSA-net segmentation approach to crack quantification. IEEE Trans Instrum Meas, 2024, 73: 1-14

[175] Sun X, Xie Y, Jiang L, Cao Y, Liu B. DMA-net: Deeplab with multi-scale attention for pavement crack segmentation. IEEE Trans Intell Transp Syst, 2022, 23(10): 18392-18403

[176] Xu Q et al (2022) Pixel-level pavement crack detection using enhanced high-resolution semantic dataset. Int J Pavement Eng 23(14). https://doi.org/10.1080/10298436.2021.1985491

[177] Ji A, Xue X, Wang Y, Luo X, Xue W. An integrated approach to automatic pixel-level crack detection and quantification of asphalt pavement. Autom Constr, 2020, 114 103176

[178] Badrinarayanan V, Kendall A, Cipolla R. Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell, 2017, 39(12): 2481-2495

[179] Badrinarayanan V, Kendall A, Cipolla R (2016) Segnet: a deep convolutional encoder-decoder architecture for image segmentation. Preprint at https://arxiv.org/abs/1511.00561

[180] Li H, et al. . Gating attention convolutional networks with dense connection for pixel-level pavement crack detection (segnet-based). Multimedia Syst, 2022

[181] Chen X et al (2024) A two-stage framework for pixel-level pavement surface crack detection and segmentation. Eng Appl Artif Intell. https://doi.org/10.1016/j.engappai.2024.110867

[182] Zhang J, Yang X, Wang W, Brilakis I, Davletshina D, Wang H, Cao M. Automatic segmentation of airport pavement damage by AM-Mask R-CNN algorithm. Eng Rep, 2023, 5(8 e12628

[183] Yan Z, et al. . Crack detection and comparison study based on Faster R-CNN and Mask R-CNN. Sensors (Basel), 2022, 223 1215

[184] Kulambayev B, Olzhayev O. A Mask R-CNN algorithm for automated segmentation of asphalt road cracks. Procedia Comput Sci, 2025, 269: 39-48

[185] Yu G, Zhou X. An improved YOLOv5 crack detection method combined with a Bottleneck Transformer. Mathematics (Basel), 2023, 1110 2377

[186] Jiang TY, Liu ZY, Zhang GZ. YOLOv5s-road: road surface defect detection under engineering environments based on CNN-Transformer and adaptively spatial feature fusion. Measurement, 2025, 242 115990

[187] Xiang X, Wang Z, Qiao Y. An improved YOLOv5 crack detection method combined with Transformer. IEEE Sens J, 2022, 2214): 14328-14335

[188] Zhao G, Zhang W, Sun R, Wei T. Road crack detection based on improved RT-DETR. SIViP, 2025, 19: 583

[189] Chen J, Lu Y, Yu Q, Luo X, Adeli E, Wang Y, Lu L, Yuille A, Zhou Y (2021) Transunet: Transformers make strong encoders for medical image segmentation. Preprint at https://arxiv.org/abs/2102.04306

[190] Shamsabadi EA, Xu C, Rao AS, Nguyen T, Ngo T, da Costa DD. Vision transformer-based autonomous crack detection on asphalt and concrete surfaces. Autom Constr, 2022, 140 104316

[191] Fang J, et al. . External attention based TransUNet and label expansion strategy for crack detection. IEEE Trans Intell Transp Syst, 2022, 23(10): 19054-19063

[192] Xu Y, Xia Y, Zhao Q, Yang K, Li Q. A road crack segmentation method based on transformer and multi-scale feature fusion. Electronics Basel, 2024

[193] Ma M, Yang L, Liu Y, Yu H. A transformer-based network with feature complementary fusion for crack defect detection. IEEE Trans Intell Transp Syst, 2024, 25(11): 16989-17006

[194] Zhou Z, Zhang J, Gong C. Hybrid semantic segmentation for tunnel lining cracks based on Swin Transformer and convolutional neural network. Comput Aided Civ Infrastruct Eng, 2023, 38(17): 2491-2510

[195] Xu Z, et al. . Pavement crack detection from CCD images with a locally enhanced transformer network. Int J Appl Earth Obs Geoinf, 2022, 110102825

[196] Xu Z, Guan H, Kang J, Lei X, Ma L, Yu Y, Chen Y, Li J. Pavement crack detection from CCD images with a locally enhanced transformer network. Int J Appl Earth Obs Geoinf, 2022, 110102825

[197] Bai S, Yang L, Liu Y, Yu H. Dmf-net: a dual-encoding multi-scale fusion network for pavement crack detection. IEEE Trans Intell Transp Syst, 2023, 25(6): 5981-5996

[198] Chen Z, Shamsabadi EA, Jiang S, Shen L, Dias-da Costa D. An average pooling designed transformer for robust crack segmentation. Autom Constr, 2024, 162 105367

[199] Shan J, Huang Y, Jiang W. Dcuformer: enhancing pavement crack segmentation in complex environments with dual-cross/upsampling attention. Expert Syst Appl, 2025, 264 125891

[200] Wang C, Liu H, An X, Gong Z, Deng F. Swincrack: pavement crack detection using convolutional swin-transformer network. Digit Signal Process, 2024, 145 104297

[201] Chen Z, Zou Y, González VA, Ingham J, Wotherspoon LM (2025) Bridge inspection using a multi-modal vision language model. In: Proceedings of the 6th International Conference on Civil and Building Engineering Informatics, vol 8, p 11

[202] Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W (2021) Lora: low-rank adaptation of large language models. Preprint at https://arxiv.org/abs/2106.09685

[203] Akçay S, Atapour-Abarghouei A, Breckon TP. Ganomaly: semi-supervised anomaly detection via adversarial training. Pattern Recogn Lett, 2019, 125: 349-356

[204] Yu N, Meng X, Zhang D, Hu S, Lang C (2020) Unsupervised pixel-level road defect detection via adversarial image-to-frequency transform. In: Proc. IEEE Intelligent Vehicles Symposium (IV), pp 972–979. https://doi.org/10.1109/IV47402.2020.9304587

[205] Fan R, Liu M. Road damage detection based on unsupervised disparity map segmentation. IEEE Trans Intell Transp Syst, 2020, 21(11): 4906-4911

[206] Duan Y, Gu Y, Li X (2023) Unsupervised crack image binarization via image-to-image translation with GANs. Sci Iran

[207] Yu D, Chen X, Liu H et al (2023) Multi-source domain adaptation and domain alignment with outlier relocation for road defect segmentation. In: Proc IEEE Int Conf Robot Autom (ICRA) Workshops

[208] Alzuhairi N, Al-Zuky AA, Al-Raweshidy MA. Road segmentation in high-resolution orthophotos using deep convolutional autoencoder. Remote Sens, 2017, 9(6): 590

[209] Mubashshira S, Azam MM, Ahsan SMM (2020) An unsupervised approach for road surface crack detection. In: 2020 IEEE Region 10 Symposium (TENSYMP), pp 1596–1599. IEEE

[210] Shamsolmoali P, K MHR et al (2019) Adversarial spatial pyramid networks for road detection. IEEE Geosci Remote Sens Lett 16(11):1815–1819. https://doi.org/10.1109/LGRS.2019.2900539

[211] Wang Z, Su Y. Semi-supervised semantic segmentation network for surface crack detection. Autom Constr, 2021, 128 103786

[212] Ouali Y, Hudelot C, Tami M (2020) Semi-supervised semantic segmentation with cross-consistency training. In: Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR), pp 12674–12684. https://doi.org/10.1109/CVPR42600.2020.01269

[213] Liu X, Wu K, Cai X, Huang W (2024) Semi-supervised semantic segmentation using cross-consistency training for pavement crack detection. Road Mater Pavement Des 25(6):1368–1380. Taylor & Francis

[214] Zhou B, Khosla A, Lapedriza À, Oliva A, Torralba A (2016) Learning deep features for discriminative localization. In: Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR), pp 2921–2929. https://doi.org/10.1109/CVPR.2016.319

[215] Krähenbühl P, Koltun V (2011) Efficient inference in fully connected CRFs with Gaussian edge potentials. In: Advances in Neural Information Processing Systems (NeurIPS), pp 109–117

[216] König R, Chen Q, Peters O, Hampel U, Säwert U, Bayer C. Weakly-supervised surface crack segmentation by generating pseudo-labels using localization with a classifier and thresholding. IEEE Trans Intell Transp Syst, 2022, 23(11): 20825-20836

[217] Dong Z, Wang J, Cui B, Wang D, Wang X. Patch-based weakly supervised semantic segmentation network for crack detection. Constr Build Mater, 2020, 258 120291

[218] Tang W, Huang S, Zhao Q, Li R, Huangfu L. An iteratively optimized patch label inference network for automatic pavement distress detection. IEEE Trans Intell Transp Syst, 2021, 22(6): 3352-3363

[219] Al-Huda H, El-Khazali RA, Al-Qutayri M. Weakly supervised pavement crack semantic segmentation based on multi-scale class activation maps. Appl Intell, 2023, 53(5): 5562-5577

[220] Pizer SM, Amburn EP, Austin JD, Cromartie R, Geselowitz A, Greer T, ter Haar Romeny B, Zimmerman JB, Zuiderveld K (1990) Adaptive histogram equalization and its variations (CLAHE). In: Proc SPIE, Visualization in Biomedical Computing, pp 337–345. https://doi.org/10.1109/VBC.1990.109340

[221] Dorafshan S, Thomas RJ, Maguire M. Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete. Constr Build Mater, 2018, 186: 1031-1045

[222] Zhang X, Rajan D, Story B (2019) Concrete crack detection using context-aware deep semantic segmentation network. Comput-Aided Civ Infrastruct Eng 34(11):951–971. https://doi.org/10.1111/mice.12477

[223] Fan R, Bocus MJ, Zhu Y, Jiao J, Wang L, Ma F, Liu M, et al. . Pavement crack detection based on capillary tension and shadow removal. IEEE Trans Intell Transp Syst, 2020, 22(9): 5550-5560

[224] Shi Y, Cui L, Qi Z, Meng F, Chen Z. Automatic road crack detection using random structured forests. IEEE Trans Intell Transp Syst, 2016, 17(12): 3434-3445

[225] Cubero-Fernandez A, Rodriguez-Lozano F, Villatoro-Villar R, Arias-García J, García-Fernández J. Data augmentation for imbalanced pavement crack datasets in deep learning. Sensors (Basel), 2021, 21(186162

[226] Laurent J, Talbot M, Doucet M (2008) A road surface crack detection and measurement system based on 3D laser profiling. In: 7th symposium on pavement surface characteristics: SURF 2008, pp 1–11

[227] Mathavan S, Kamal K, Rahman M. A review of three-dimensional imaging technologies for pavement distress detection and measurements. IEEE Trans Intell Transp Syst, 2015, 165): 2353-2362

[228] Wang KC, Li JQ (2021) A review of 3D point cloud applied to pavement engineering. J Traffic Transp Eng 8(2):177–193

[229] Sun T, Chen Y, Liao Q, Chen R, Chen H, Cao Z. Self-adaptive 2d–3d image fusion for automated pixel-level pavement crack segmentation (csf-cracknet). Adv Eng Inform, 2024, 62 102851

[230] Graham B, Engelcke M, van der Maaten L (2018) 3D semantic segmentation with submanifold sparse convolutional networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 4555–4564. https://doi.org/10.1109/CVPR.2018.00479

[231] Choy C, Gwak J, Savarese S (2019) 4D spatio-temporal ConvNets: Minkowski convolutional neural networks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 3075–3084. https://doi.org/10.1109/CVPR.2019.00319

[232] Zhu X, Zhou H, Wang T, Hong F, Ma Y, Li W, Li H, Lin D (2021) Cylindrical and asymmetrical 3D convolution networks for LiDAR segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 9939–9948. https://doi.org/10.1109/CVPR46437.2021.00981

[233] Wu B, Wang P, Bänzigar MD, Shen XS, Keutzer K (2018) Squeezeseg: convolutional neural nets with recurrent CRF for real-time road-object segmentation from 3D LiDAR point cloud. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp 1887–1894. https://doi.org/10.1109/ICRA.2018.8462926

[234] Milioto A, Vizzo I, Behley J, Stachniss C (2019) Rangenet++: fast and accurate LiDAR semantic segmentation. In: 2019 IEEE/RSJ international conference on intelligent robots and systems (IROS), IEEE, pp 4213–4220

[235] Zhang AA, Wang KCP, Ai C, Li Y, Liu Y, Li P, Wang C, Zhang E, Li JQ. Automated pixel-level pavement crack detection on 3D asphalt surfaces using a deep-learning network. Comput Aided Civ Infrastruct Eng, 2017, 32(10): 805-819

[236] Zhang AA, Wang KCP, Liu Y, Wang C, Zhang E, Li Q, Li P, Li JQ. Deep learning-based fully automated pavement crack detection on 3D asphalt surfaces with an improved CrackNet. J Comput Civ Eng, 2018, 32(5 04018041

[237] Zhang AA, Wang KCP, Fei Y, Liu Y, Wang C, Zhang E, Li Q, Li P, Li JQ. Pixel-level cracking detection on 3D asphalt pavement images using a deep-learning network. IEEE Trans Intell Transp Syst, 2020, 211): 273-284

[238] Zhang AA, Wang KCP, Liu Y, Wang C, Fei Y, Li JQ, Zhang E, Li P. Automated pixel-level pavement crack detection on 3D asphalt surfaces with a recurrent neural network. Comput Aided Civ Infrastruct Eng, 2019, 34(3): 213-229

[239] Qi CR, Su H, Mo K, Guibas LJ (2017) Pointnet: Deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 652–660

[240] Qi CR, Yi L, Su H, Guibas LJ (2017) Pointnet++: deep hierarchical feature learning on point sets in a metric space. Adv Neural Inform Process Syst 30

[241] Feng M, Yu L, Zhou Y, Zhao S, Gu S, Li S, Pu J, Liu H. CrackGCN: semi-supervised pavement crack detection from mobile laser scanning point clouds via deep graph convolution network. IEEE Trans Intell Transp Syst, 2022, 23(8): 12570-12583

[242] Ma L, Feng M, Wang C, Xu W, Liu H. Saliency-based dilated graph convolutional network for pavement crack detection from mobile laser scanning point clouds. Int J Appl Earth Obs Geoinf, 2022, 108 102784

[243] Zhao H, Jiang L, Jia J, Torr PHS, Koltun V (2021) Point transformer. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp 16259–16268

[244] Feng M, Ma L, Wang C, Xu W, Liu H. Scl-gcn: hierarchical contrastive learning graph convolutional network for pavement crack detection from mobile laser scanning point clouds. Int J Appl Earth Obs Geoinf, 2023, 118 103248

[245] Nilnoree S, Mizutani T. An innovative framework for incorporating iPhone Lidar point cloud in digitized documentation of road operations. Results Eng, 2025

[246] Fan R, Bocus MJ, Zhu Y, Shah M, Hadi SA. Road pothole detection from rgb imagery using deep convolutional neural networks and transfer learning. IEEE Trans Image Process, 2019, 29: 897-908

[247] Tseng TY, Lyu H, Li J, Berrio JS, Shan M, Worrall S (2025) M2s-road: multi-modal semantic segmentation for road damage using camera and LiDAR data. Preprint at https://arxiv.org/abs/2504.10123

[248] Wang Z, Zang D, Li Y, Gong B, Yang X, Zhang Y, Tian Z, Hao Q. Recent advances in multimodal 3d object detection. IEEE Trans Intell Veh, 2023, 8(3): 2197-2216

[249] Crampen D, Blankenbach J. Data enrichment for semantic segmentation of point clouds for the generation of geometric-semantic road models. Front Built Environ, 2025, 11 1607375

[250] Gupta S, Girshick R, Arbelaez P, Malik J (2014) Learning rich features from RGB-D images for object detection and semantic segmentation. In: European Conference on Computer Vision (ECCV), Springer, pp 345–360. https://doi.org/10.1007/978-3-319-10584-0_23

[251] Vora S, Lang AH, Helou B, Beijbom O (2020) Pointpainting: sequential fusion for 3D object detection. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 4603–4611. https://doi.org/10.1109/CVPR42600.2020.00466

[252] Wang Z, Li B, Fan T, He M, Wu W, Ouyang W, Feng X, Qiao Y (2021) Pointaugmenting: cross-modal augmentation for 3D object detection. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 11794–11803. https://doi.org/10.1109/CVPR46437.2021.01163

[253] Xu D, Anguelov D, Jain A (2018) Pointfusion: deep sensor fusion for 3D bounding box estimation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 244–253. https://doi.org/10.1109/CVPR.2018.00033

[254] Wang C, Xu D, Zhu Y, Martín-Martín R, Lu C, Savarese S, Fei-Fei L (2019) Densefusion: 6D object pose estimation by iterative dense fusion. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 3343–3352. https://doi.org/10.1109/CVPR.2019.00346

[255] Wu Q, Zhang P, Niu X, Peng K, He L. Road pothole extraction and safety evaluation by the integration of point cloud and images. Adv Eng Inform, 2019, 42 100936

[256] Benmhahe Y, Ezzamouri H, Laachir AA, Moubtassime M, Abbou SO, Chehouani H. Identification of longitudinal and transversal cracks in pavements using 2D/3D model feature map fusion. Measurement, 2024, 226 115449

[257] Huang J, Liu W, Sun X. Road crack detection using 2D/3D data fusion based on Dempster–Shafer theory. Comput-Aided Civ Infrastruct Eng, 2013, 28(9): 671-686

[258] Zhong J, Kong D, Wei Y, Pan B. Yolov8 and point cloud fusion for enhanced road pothole detection and quantification. Sci Rep, 2025, 15 11260

[259] Liu Y, Wang Z et al (2024) Road surface defect detection—from image-based to non-image-based: a survey. Preprint at https://arxiv.org/abs/2409.20118

[260] Elamin A, El-Rabbany A. Uav-based image and lidar fusion for pavement crack segmentation. Sensors Basel, 2023, 23(23 9315

[261] Marsh B, Wu R. Crack segmentation in roads using synthetic data and rgb-d data fusion. Comput Vis Image Underst, 2025, 260 104452

[262] Federal Highway Administration. Highway performance monitoring system (hpms) field manual, 2023, Federal Highway Administration, Technical report

[263] Sharma M, Al-Hammadi M, Mork H, Klein-Paste A (2025) Combined dataset for subjective panel rating, international roughness index and images for road damage detection of low volume road in norway. Dataset. https://doi.org/10.18710/EHMQU7

[264] Federal Highway Administration (2018) LTPP InfoPave brochure. Technical Report No. FHWA-HRT-18-011, Federal Highway Administration, Washington, DC. https://www.fhwa.dot.gov/publications/research/infrastructure/pavements/ltpp/18011/18011.pdf

[265] Federal Highway Administration (2006) LTPP directive D-44: distress survey photographs. Technical Report, Federal Highway Administration, Washington, DC. https://infopave.fhwa.dot.gov/InfoPave_Repository/Reports/B10/B10_20/D-44.pdf

[266] Owor NJ, Du H, Daud A, Aboah A, Adu-Gyamfi Y (2023) Image2pci – a multitask learning framework for estimating pavement condition indices directly from images. Preprint at https://arxiv.org/abs/2310.08538

[267] Government of Alberta (2015) International roughness index and rut data. Open Government dataset. https://open.canada.ca/data/en/dataset/5161dfca-bca9-4e11-bfe4-683ef3c8aad7. Accessed 28 Apr 2026

[268] Ontario Ministry of Transportation (2023) Pavement condition for provincial highways. Ontario Data Catalogue dataset. https://data.ontario.ca/dataset/pavement-condition-for-provincial-highways. Accessed 28 Apr 2026

[269] San Francisco Public Works (2026) Streets data–pavement condition index (PCI) scores. DataSF dataset. https://data.sfgov.org/City-Infrastructure/Streets-Data-Pavement-Condition-Index-PCI-Scores/5aye-4rtt. Accessed 28 Apr 2026

[270] Data.Gov (2025) Pavement condition index. Data.gov dataset catalog entry. Montgomery County, Maryland. https://catalog.data.gov/dataset/pavement-condition-index-2019. Accessed 28 Apr 2026

[271] Cheng B, Girshick R, Dollár P, Berg AC, Kirillov A (2021) Boundary IOU: Improving object-centric image segmentation evaluation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 15334–15342

[272] Shit S, Paetzold JC, Ezhov I, Sekuboyina A, Unger A, Zhylka A, Pluim JPW, Bauer U, Menze BH (2021) CLDICE – a novel topology-preserving loss function for tubular structure segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 16555–16564.https://doi.org/10.1109/CVPR46437.2021.01629

[273] Zhou Z, Siddiquee MMR, Tajbakhsh N, Liang J. Unet++: redesigning skip connections to exploit multiscale features in image segmentation. IEEE Trans Med Imaging, 2020, 396): 1856-1867

[274] Yuan Y, Chen X, Wang J (2020) Object-contextual representations for semantic segmentation. In: Proc ECCV, pp 173–190. https://doi.org/10.1007/978-3-030-58548-8_11

[275] Oktay O, Schlemper J, Folgoc LL et al (2018) Attention U-Net: learning where to look for the pancreas. Preprint at https://arxiv.org/abs/1804.03999

[276] Goo JR et al (2025) Hybrid-segmentor: high-resolution and efficient pavement crack segmentation. Automation in Construction (In press). TechRxiv. https://doi.org/10.36227/techrxiv.170775714.48894818. arXiv:2409.02866

[277] Tao H, Liu B, Cui J, Zhang H (2023) A convolutional-transformer network for crack segmentation with boundary awareness. In: Proc IEEE ICIP, pp 86–90. https://doi.org/10.1109/ICIP49359.2023.10349671

[278] Zou Q, Zhang Z, Li Q, Qi X, Wang Q, Wang S. Deepcrack: learning hierarchical convolutional features for crack detection. IEEE Trans Image Process, 2019, 28(3): 1498-1512

[279] Chen X, Shi Y, Pang J. Secrackseg: a high-accuracy crack segmentation network based on proposed unet with sam2 s-adapter and edge-aware attention. Sensors Basel, 2025, 25(9 2642

[280] Xie E, Wang W, Yu Z, Anandkumar A, Alvarez JM, Luo P (2021) SegFormer: simple and efficient design for semantic segmentation with transformers. Preprint at https://arxiv.org/abs/2105.15203

[281] Yeom SU, Klitzing J (2025) U-MixFormer: UNet-like transformer with mix-attention for efficient semantic segmentation. In: Proc IEEE/CVF Winter Conf Appl Comput Vis (WACV), pp 7710–7719. https://doi.org/10.1109/WACV61041.2025.00750

[282] Guo M, Lu C, Hou Q, Liu Z, Cheng M, Hu S (2022) SegNeXt: rethinking convolutional attention design for semantic segmentation. In: 36th Conference on Neural Information Processing Systems (NeurIPS 2022). https://proceedings.neurips.cc/paper_files/paper/2022/file/08050f40fff41616ccfc3080e60a301a-Paper-Conference.pdf

[283] Cheng B, Misra I, Girdhar R, Kirillov A (2022) Masked-attention mask transformer for universal image segmentation. In: Proc CVPR. https://doi.org/10.1109/CVPR52688.2022.01964

[284] Shan J, Huang Y, Jiang W (2024) DCUFormer: enhancing pavement crack segmentation in complex scenarios by dual-branch connected U-Former. Expert Syst Appl 264:125891. https://doi.org/10.1016/j.eswa.2024.125891

[285] Yan H, Wu M, Zhang C (2024) Multi-scale representations by varying window attention for semantic segmentation (vwformer). Preprint at https://arxiv.org/abs/2404.16573

[286] Yu C, Wang J, Peng C, Gao C, Yu G, Sang N (2018) Bisenet: bilateral segmentation network for real-time semantic segmentation. In: ECCV. https://openaccess.thecvf.com/content_ECCV_2018/papers/Changqian_Yu_BiSeNet_Bilateral_Segmentation_ECCV_2018_paper.pdf

[287] Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: Proc CVPR, pp 2881–2890. https://doi.org/10.1109/CVPR.2017.660

[288] Wang Y, Zhou Q, Liu J, Xiong J, Gao G, Wu X, Latecki LJ (2019) Lednet: a lightweight encoder-decoder network for real-time semantic segmentation. In: 2019 IEEE International Conference on Image Processing (ICIP), IEEE, pp 1860–1864. https://doi.org/10.1109/ICIP.2019.8803154. Accessed 20 Apr 2026

[289] Zhang T, Wang D, Lu Y. Ecsnet: an accelerated real-time image segmentation CNN architecture for pavement crack detection. IEEE Trans Intell Transp Syst, 2023, 2412): 15105-15112

[290] Li H, Yue Z, Liu J, Wang Y, Cai H, Cui K, Chen X. Sccdnet: a pixel-level crack segmentation network. Applied Sciences, 2021, 11(11 5074

[291] Xu N, He L, Li Q. Crack-att net: crack detection based on improved u-net with parallel attention. Multimed Tools Appl, 2023, 8227): 42465-42484

[292] Manjunatha P, Masri SF, Nakano A, Wellford LC. Crackdenselinknet: a deep convolutional neural network for semantic segmentation of cracks on concrete surface images. Struct Health Monit, 2024, 23(2): 796-817

[293] Tabernik D, Šuc M, Skočaj D. Automated detection and segmentation of cracks in concrete surfaces using joined segmentation and classification deep neural network. Constr Build Mater, 2023, 408 133582

[294] Lu Z, She C, Wang W, Huang Q. Lm-net: a light-weight and multi-scale network for medical image segmentation. Comput Biol Med, 2024, 168 107717

[295] Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proc ICCV, pp 10012–10022. https://doi.org/10.1109/ICCV48922.2021.00986

[296] Xu Z, Wu D, Yu C, Chu X, Sang N, Gao C. Sctnet: single-branch CNN with Transformer semantic information for real-time segmentation. Proc AAAI Conf Artif Intell, 2024, 38: 6378-6386

[297] Wang Z, et al. . Adaptive frequency transformer for efficient semantic segmentation. IEEE Access, 2023

[298] Chen J et al (2022) Refined crack detection via LECSFormer for autonomous road inspection vehicles. IEEE Trans Intell Veh 8(3):2049–2061. https://doi.org/10.1109/TIV.2022.3204583

RIGHTS & PERMISSIONS

The Author(s)