Artificial intelligence techniques have advanced significantly in recent years and can be applied across various fields of knowledge. In civil engineering, such techniques as machine learning and computer vision have proven useful in pavement inspection and evaluation—processes that are traditionally carried out manually in the field, demanding considerable time and effort from inspectors. To address the limitations of manual inspections, numerous studies have aimed to automate this process by employing algorithms capable of recognizing and classifying surface distress. However, few studies address these algorithms’ ability to determine the severity level of pavement distress, a crucial piece of information for planning maintenance and rehabilitation activities. Therefore, the aim of this study is to conduct a systematic literature review, using the systematic search flow method, of research that employed machine learning techniques to automatically or semi-automatically determine the severity levels of pavement distresses. A search conducted in two databases (Scopus and Web of Science) yielded a total of 283 articles. After applying a defined filtering process, 28 studies were identified as meeting the established scope. A review of these articles revealed that machine learning is an effective method for distress recognition and severity classification. Nonetheless, owing to the limited exploration of this topic in the current literature, further investigation and detailed analysis of specific elements are necessary in future studies.
JuR. Y.CaiW.Fracture Detection in Pediatric Wrist Trauma X-Ray Images Using YOLOv8 Algorithm. Scientific Reports, Vol. 13, No. 1, 2023, pp. 1–14.
2.
DangF.ChenD.LuY.LiZ.YOLOWeeds: A Novel Benchmark of YOLO Object Detectors for Multi-Class Weed Detection in Cotton Production Systems. Computers and Electronics in Agriculture, Vol. 205, 2023, p. 107655.
3.
CorballyR.MalekjafarianA.A Deep-Learning Framework for Classifying the Type, Location, and Severity of Bridge Damage Using Drive-by Measurements. Computer-Aided Civil and Infrastructure Engineering, Vol. 39, No. 6, 2024, pp. 852–871.
4.
SousaA. D. P.SousaG. C. L.MauésL. M. F.Using Digital Image Processing and Unmanned Aerial Vehicle (UAV) for Identifying Ceramic Cladding Detachment in Building Facades. Ambiente Construído, Vol. 22, No. 2, 2022, pp. 199–213.
5.
de SouzaÁ. M.da Silva SoaresJ. V.de SousaA. D. P.de SousaG. C. L.da SilvaL. M.Detection of Potholes in Asphalt Pavements Using YOLOv4 Architecture. International Journal of Pavement Research and Technology, 2024. https://doi.org/10.1007/s42947-024-00474-4.
6.
JakubecM.LieskovskáE.BučkoB.ZábovskáK.Comparison of CNN-Based Models for Pothole Detection in Real-World Adverse Conditions: Overview and Evaluation. Applied Sciences, Vol. 13, No. 9, 2023, pp. 1–25.
7.
BučkoB.LieskovskáE.ZábovskáK.ZábovskýM.Computer Vision Based Pothole Detection Under Challenging Conditions. Sensors, Vol. 22, No. 22, 2022, pp. 1–18.
8.
GoodaS. K.ChinthamuN.SelvanS. T.RajakumareswaranV.ParamasivamG. B.Automatic Detection of Road Cracks using EfficientNet with Residual U-Net-based Segmentation and YOLOv5-based Detection. International Journal on Recent and Innovation Trends in Computing and Communication, Vol. 11, No. 4, 2023, pp. 84–91.
9.
ChenD. R.ChiuW. M.Deep-Learning-Based Road Crack Detection Frameworks for Dashcam-Captured Images Under Different Illumination Conditions. Soft Computing, Vol. 27, No. 19, 2023, pp. 14337–14360.
10.
YaoH.FanY.WeiX.LiuY.CaoD.YouZ.Research and Optimization of YOLO-Based Method for Automatic Pavement Defect Detection. Electronic Research Archive, Vol. 32, No. 3, 2024, pp. 1708–1730.
11.
YiC.LiuJ.TaoH.XiaoH.GuanH.An Efficient Method of Pavement Distress Detection Based on Improved YOLOv7. Measurement Science and Technology, Vol. 34, No. 11, 2023, pp. 1–15.
12.
GopalakrishnanK.Deep Learning in Data-Driven Pavement Image Analysis and Automated Distress Detection: A Review. Data, Vol. 3, No. 3, 2018, p. 28.
13.
AliL.AlnajjarF.KhanW.SerhaniM. A.AlJassmiH.Bibliometric Analysis and Review of Deep Learning-Based Crack Detection Literature Published between 2010 and 2022. Buildings, Vol. 12, No. 4, 2022, p. 432.
14.
SholevarN.GolrooA.EsfahaniS. R.Machine Learning Techniques for Pavement Condition Evaluation. Automation in Construction, Vol. 136, 2022, p. 104190.
15.
FerenhofH. A.FernandesR. F.Demystifying the Literature Review as Basis for Scientific Writing: SSF Method. Revista ACB: Biblioteconomia em St Catarina, Florianópolis, Vol. 21, No. 3, 2016, pp. 550–563.
16.
RanyalE.SadhuA.JainK.Enhancing Pavement Health Assessment: An Attention-Based Approach for Accurate Crack Detection, Measurement, and Mapping. Expert Systems with Applications, Vol. 247, 2024, p. 123314.
17.
PerakaN. S. P.BiligiriK. P.KalidindiS. N.Development of a Multi-Distress Detection System for Asphalt Pavements: Transfer Learning-Based Approach. Transportation Research Record: Journal of the Transportation Research Board, 2021. 2675: 538–553.
18.
LiZ.TorbaghanM. E.ZhangT.QinX.LiW.LiY.ZhangJ.An Automated 3D Crack Severity Assessment Using Surface Data for Improving Flexible Pavement Maintenance Strategies. IEEE Transactions on Intelligent Transportation Systems, Vol. 25, No. 9, 2024, pp. 12490–12503.
19.
TsaiY. C. (J.)ZhaoY.Pop-StefanovB.ChatterjeeA.Automatically Detect and Classify Asphalt Pavement Raveling Severity Using 3D Technology and Machine Learning. International Journal of Pavement Research and Technology, Vol. 14, No. 4, 2021, pp. 487–495.
20.
ValipourP. S.GolrooA.KheiratiA.FahmaniM.AmaniM. J.Automatic Pavement Distress Severity Detection Using Deep Learning. Road Materials and Pavement Design, Vol. 25, No. 8, 2023, pp. 1830–1846.
21.
HsiehY. A.TsaiY. (J.). Automated Asphalt Pavement Raveling Detection and Classification Using Convolutional Neural Network and Macrotexture Analysis. Transportation Research Record: Journal of the Transportation Research Board, 2021. 2675:984–994.
22.
HoangN.-D.TranV. D.TranX. L.Image Processing-Based Classification of Pavement Fatigue Severity Using Extremely Randomized Trees, Deep Neural Network, and Convolutional Neural Network. International Journal of Pavement Engineering, Vol. 24, No. 1, 2023., pp.–1-24. https://doi.org/10.1080/10298436.2023.2201902.
23.
HsiehY.-A.YangZ.TsaiY.-C. J.Convolutional Neural Network for Automated Classification of Jointed Plain Concrete Pavement Conditions. Computer-Aided Civil and Infrastructure Engineering, Vol. 36, No. 11, 2021, pp. 1382–1397.
24.
GaneshanD.SharifM. S.ApeagyeiA.Road Deterioration Detection: A Machine Learning-Based System for Automated Pavement Crack Identification and Analysis. Proc., 2023 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2023, Sakheer, Bahrain, Institute of Electrical and Electronics Engineers, New York, 2023, p. 188–194.
25.
RobertsR.GiancontieriG.InzerilloL.Di MinoG.Towards Low-Cost Pavement Condition Health Monitoring and Analysis Using Deep Learning. Applied Sciences, Vol. 10, No. 1, 2020, p. 319.
26.
RanyalE.SadhuA.JainK.Automated Pothole Condition Assessment in Pavement Using Photogrammetry-Assisted Convolutional Neural Network. International Journal of Pavement Engineering, Vol. 24, No. 1, 2023, p. 2183401.
27.
TranT. S.TranV. P.LeeH. J.FloresJ. M.LeV. P.A Two-Step Sequential Automated Crack Detection and Severity Classification Process for Asphalt Pavements. International Journal of Pavement Engineering, Vol. 23, No. 6, 2020, pp. 2019–2033.
28.
HoangN.-D.TranV.-D.Comparison of Histogram-Based Gradient Boosting Classification Machine, Random Forest, and Deep Convolutional Neural Network for Pavement Raveling Severity Classification. Automation in Construction, Vol. 148, 2023, p. 104767.
29.
PerakaN. S. P.BiligiriK. P.KalidindiS. N.Framework for Pothole Detection, Quantification, and Maintenance System (PDQMS) for Smart Cities. Proceedings of the 9th International Conference on Maintenance and Rehabilitation of Pavements—Mairepav9 (RaabC., ed.), Lecture Notes in Civil Engineering. Springer, Cham, 2020, pp. 913–922.
30.
HassanM. U.SteinnesO. M. H.GustafssonE. G.LøkenS.HameedI. A.Predictive Maintenance of Norwegian Road Network Using Deep Learning Models. Sensors, Vol. 23, No. 6, 2023, p. 2935.
31.
SongW.JiaG.JiaD.ZhuH.Automatic Pavement Crack Detection and Classification Using Multiscale Feature Attention Network. IEEE Access, Vol. 7, 2019, pp. 171001–171012.
32.
GuoN.YouL.LongZ.LvS.DiabA.Computationally-Affordable Unsupervised Machine Learning Algorithm to Identify the Level of Distress Severity in Pavement Functional Performance. IEEE Transactions on Intelligent Transportation Systems, Vol. 24, No. 7, 2023, pp. 7342–7356.
33.
El-WakeelA. S.LiJ.NoureldinA.HassaneinH. S.ZorbaN.Towards a Practical Crowdsensing System for Road Surface Conditions Monitoring. IEEE Internet of Things Journal, Vol. 5, No. 6, 2018, 4672–4685.
34.
AlqethamiS.AlghamdiS.AlsubaitT.AlhakamiH.RoadNet: Efficient Model to Detect and Classify Road Damages. Applied Sciences, Vol. 12, No. 22, 2022, pp. 1–15.
35.
ChacraD. B. A.ZelekJ. S.Fully Automated Road Defect Detection Using Street View Images. Proc., 2017 14th Conference on Computer and Robot Vision, CRV 2017, Edmonton, AB, Canada, Institute of Electrical and Electronics Engineers, Piscataway, NJ, 2017, pp. 353–360.
36.
RanjbarS.NejadF. M.ZakeriH.An Image-Based System for Asphalt Pavement Bleeding Inspection. International Journal of Pavement Engineering, Vol. 23, No. 12, 2022, pp. 4080–4096.
37.
OliveiraH.CorreiaP. L.Automatic Road Crack Detection and Characterization. IEEE Transactions on Intelligent Transportation Systems, Vol. 14, No. 1, 2013, pp. 155–168.
38.
LiuF.LiuJ.WangL.Asphalt Pavement Fatigue Crack Severity Classification by Infrared Thermography and Deep Learning. Automation in Construction, Vol. 143, 2022, p. 104575.
39.
YuX.SalariE.Pavement Pothole Detection and Severity Measurement Using Laser Imaging. Proc., 2011 IEEE International Conference on Electro Information Technology, Mankato, MN, IEEE, New York, 2011, pp. 1–5.
40.
TranV. P.TranT. S.LeeH. J.KimK. D.BaekJ.NguyenT. T.One Stage Detector (RetinaNet)-Based Crack Detection for Asphalt Pavements Considering Pavement Distresses and Surface Objects. Journal of Civil Structural Health Monitoring, Vol. 11, No. 1, 2021, pp. 205–222.
41.
SalariE.BaoG.Pavement Distress Detection and Severity Analysis. Proc., SPIE - The International Society for Optical Engineering, San Francisco, CA, 2011.
42.
IbrahimA.ZukriN. A. Z. M.IsmailB. N.OsmanM. K.YusofN. A. M.IdrisM.RabianA. H.BahriI.Flexible Pavement Crack’s Severity Identification and Classification using Deep Convolution Neural Network. Journal of Mechanical Engineering, Vol. 18, No. 2, 2021, pp. 193–201.
43.
MoussaG.HussainK.A New Technique for Automatic Detection and Parameters Estimation of Pavement Crack. Proc., IMETI 2011 - 4th International Multi-Conference on Engineering and Technological Innovation, Orlando, FL, International Institute of Informatics and Systemics, Winter Garden, FL, 2011, p. 11–16.
44.
DNIT. Manual de projeto geométrico de rodovias rurais. DNIT, Rio de Janeiro, 1999.
45.
Arévalo PáezE. M.Índice de condição do pavimento (ICP) para aplicação em sistemas de gerência de pavimentos urbanos. Dissertação. Escola de Engenharia de São Carlos, 2015.
46.
DanieleskiM. L.Proposta de metodologia para avaliação superficial de pavimentos urbanos: aplicação à rede viária de Porto Alegre. Dissertação. Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, 2004.
47.
BernucciL. B.GorettiL. M.MottadaCerattiJ. A. P.SoaresJ. B.Pavimentação asfaltica: Formação para engenheiros. PETROBRAS: ABEDA, Rio de Janeiro, 2022, p. 750.
48.
ChangX.ZhangR.XiaoY.ChenX.ZhangX.LiuG.Mapping of Publications on Asphalt Pavement and Bitumen Materials: A Bibliometric Review. Construction and Building Materials, Vol. 234, 2020, p. 117370.
49.
ASTM D6433. Standard Practice for Roads and Parking Lots Pavement Condition Index Surveys. ASTM International, West Conshohocken, PA, 2024.
50.
DorafshanS.ThomasR. J.MaguireM.SDNET2018: An Annotated Image Dataset for Non-Contact Concrete Crack Detection Using Deep Convolutional Neural Networks. Data in Brief, Vol. 21, 2018, pp. 1664–1668.
51.
FanR.OzgunalpU.HoskingB.LiuM.PitasI.Pothole Detection Based on Disparity Transformation and Road Surface Modeling. IEEE Transactions on Image Processing, Vol. 29, No. 1, 2020, pp. 897–908.
52.
AryaD.MaedaH.GhoshS. K.ToshniwalD.MrazA.KashiyamaT.SekimotoY.Deep Learning-Based Road Damage Detection and Classification for Multiple Countries. Automation in Construction, Vol. 132, 2021, p. 103935.
53.
MulyantoA.Fitri SariR.MuisA.HarwahyuR.Vision-Based Automated Pavement Distress Inspection: A Review. IEEE Access, Vol. 13, 2025, pp. 115474–115502.
54.
RuizR. D. B.Lordsleem JuniorA. C.Sousa NetoA. F.FernandesB. J. T.Processamento digital de imagens para detecção automática de fissuras em revestimentos cerâmicos de edifícios. Ambiente Construído, Vol. 21, No. 1, 2021, pp. 139–147.
55.
MittalP.SinghR.SharmaA.Deep Learning-Based Object Detection in Low-Altitude UAV Datasets: A Survey. Image and Vision Computing, Vol. 104, 2020, p. 104046.
56.
MillerJ. S.BellingerW. Y. Distress Identification Manual for the Long-Term Pavement Performance Program, Fifth Revised Edition. Publication FHWA-HRT-13-092. FHWA, U.S. Department of Transportation, 2014.
57.
NaiduG.ZuvaT.SibandaE. M.A Review of Evaluation Metrics in Machine Learning Algorithms. In Artificial Intelligence Application in Networks and Systems (SilhavyR.SilhavyP., eds.), Springer International Publishing, Cham, 2023, pp. 15–25.
58.
JafariF.MoradiK.ShafieeQ.Shallow Learning vs. Deep Learning in Engineering Applications. In Shallow Learning vs Deep Learning: A Pratical Guide for Machine Learning (ErtugrulO. F.GuerreroJ. M.YilmazM., eds.), Springer, Cham, 2024, pp. 29–76.
59.
XuY.ZhouY.SekulaP.DingL.Machine Learning in Construction: From shallow to Deep Learning. Developments in the Built Environment, Vol. 6, 2021, p. 100045.
60.
DongQ.ChenX.DongS.ZhangJ.Classification of Pavement Climatic Regions Through Unsupervised and Supervised Machine Learnings. Journal of Infrastructure Preservation and Resilience, Vol. 2, No. 1, 2021, p. 5.
61.
AlomM. Z.TahaT. M.YakopcicC.WestbergS.SidikeP.NasrinM. S.HasanM.Van EssenB. C.AwwalA. A. S.AsariV. K.A State-of-the-Art Survey on Deep Learning Theory and Architectures. Electronics, Vol. 8, No. 3, 2019, p. 292.
62.
LecunY.BengioY.HintonG.Deep Learning. Nature, Vol. 521, No. 7553, 2015, pp. 436–444.
63.
WuH.LiuQ.LiuX.A Review on Deep Learning Approaches to Image Classification and Object Segmentation. Computers, Materials & Continua, Vol. 60, No. 2, 2019, pp. 575–597.
64.
KangJ.TariqS.OhH.WooS. S.A Survey of Deep Learning-Based Object Detection Methods and Datasets for Overhead Imagery. IEEE Access, Vol. 10, 2022, pp. 20118–20134.
