eISSN: 3087-4068 editor@aimjournals.com
All Journals
Submit your article

International Research Journal of Advanced Engineering and Technology

Open Access Peer Review International
Open Access

A Multi-Scale Deep Learning Framework For Quantitative Assessment Of Road Marking Degradation Using Mobile Laser Scanning Reflectance Imagery

DOI
pdf
Pham Van Minh 1 , Daria Ivanova 1 ,
4 Faculty of Computer Science and Engineering, Ho Chi Minh City University of Technology, Ho Chi Minh City, Vietnam
4 Department of Civil Engineering, Peter the Great St. Petersburg Polytechnic University, St. Petersburg, Russia

Abstract

Purpose: Reliable and quantitative assessment of road marking degradation is paramount for traffic safety and the operational robustness of autonomous vehicle (AV) systems, which rely heavily on visual contrast. Traditional inspection methods are slow, subjective, and fail to provide the high-resolution, continuous data required for modern maintenance planning. This study addresses this gap by proposing a novel deep learning framework for the precise quantification of road marking wear from Mobile Laser Scanning (MLS) reflectance imagery.

Methods: We introduce the Percentage of Residual Marking (PRM)-Enhanced Detector (PRMED), an end-to-end deep learning model based on an EfficientNet backbone integrated with a Feature Pyramid Network. Crucially, the architecture incorporates a dedicated PRM Regression Head that directly predicts the continuous wear percentage (0.0 to 1.0) for each detected marking instance, bypassing the computational complexity and error propagation of a sequential segmentation-then-calculation pipeline. The model was trained and validated on a synthesized dataset derived from MLS data, which accurately represents a full spectrum of real-world degradation states.

Results: The PRMED model achieved a high detection accuracy, registering an $mAP@0.5$ of 0.94 and significantly outperforming a two-stage segmentation baseline in quantitative wear assessment. Specifically, the model demonstrated a Mean Absolute Error (MAE) for PRM prediction of only 1.85%, which is critical for establishing objective maintenance thresholds. Inference speed was confirmed to be suitable for real-time mobile deployment.

Conclusion: The proposed multi-scale, end-to-end deep learning framework provides a robust, efficient, and objective solution for road marking wear assessment. The continuous PRM metric offers a crucial data point for infrastructure managers to optimize maintenance schedules and, more importantly, to ensure the consistent functional integrity of perception systems in autonomous vehicles.

Keywords

Deep Learning, Road Marking Wear, Mobile Laser Scanning, Percentage of Residual Marking (PRM),

References

📄 Tual M, Muzet V, Foucher P, Heinkelé C, Charbonnier P. Using deep learning for the dynamic evaluation of road marking features from laser imaging. In: Proceedings of the 4th international conference on image proceeding and vision engineering, pp. 23–31 (2024). https://doi.org/10.5220/0000177300003720
📄 Revilloud M, Gruyer D, Pollard E. Generator of road marking textures and associated ground truth applied to the evaluation of road marking detection. In: 2012 15th international IEEE conference on intelligent transportation systems, pp. 933–938 (2012). https://doi.org/10.1109/ITSC.2012.6338773 . IEEE
📄 Parate, H., Madala, P., & Waikar, A. (2025). Equity and efficiency in TxDOT infrastructure funding: A per capita and spatial investment analysis. Journal of Information Systems Engineering and Management, 10(55s). https://www.jisem-journal.com/
📄 Tan M, Le Q. EfficientNetv2: Smaller models and faster training. In: International conference on machine learning, pp 10096–10106 (2021). PMLR
📄 El Krine A, Girard J, Redondin M, Heinkelé C, Stresser A, Muzet V. Road marking characterization for ADAS machine vision reliability. In: ESREL 2021 31st European safety and reliability conference proceedings, pp. 2030–2037 (2021)
📄 EN 1436: Road marking materials - Road marking performance for road users and test methods. European standard, CEN (2018)
📄 Babic D, Fiolić M, Zilioniene D. Evaluation of static and dynamic method for measuring retroreflection of road markings. Gradevinar. 2017;69(10):907–14. https://doi.org/10.14256/JCE.2010.2017.
📄 CS 126: Inspection and assessment of road markings and road studs. Dmrb, Highways England: Guildford, UK; Transport Scotland: Edinburgh, UK; Llywodraeth Cymru Welsh Government: Cardiff (2022)
📄 Sai Nikhil Donthi. (2025). Improvised Failure Detection for Centrifugal Pumps Using Delta and Python: How Effectively Iot Sensors Data Can Be Processed and Stored for Monitoring to Avoid Latency in Reporting. Frontiers in Emerging Computer Science and Information Technology, 2(10), 24–37. https://doi.org/10.64917/fecsit/Volume02Issue10-03
📄 Lee S, Cho BH. Evaluating Pavement lane markings in metropolitan road networks with a vehicle-mounted retroreflectometer and AI-based image processing techniques. Remote Sens. 2023;15(7):1812. https://doi.org/10.3390/rs15071812.
📄 Mesenberg H-H. Ztv m 02: Die neuen zusätzlichen technischen vertragsbedingungen und richtlinien für markierungen auf straßen. BAST: German regulation; 2003.
📄 NF EN 1824: Road marking materials - road trials. French standard, CEN (May 2020)
📄 Dumont E. Evaluation du degré d’usure des marquages routiers par traitement d’images. Research report (in French): LCPC; 2001.
📄 Zhang Y, Hancheng G. Assessment of presence conditions of pavement markings with image processing. Trans Res Rec J Trans Res Board. 2012;2272:94–102. https://doi.org/10.3141/2272-11.
📄 ASTM: Standard test method for measurement of retroreflective pavement marking materials with CEN-prescribed geometry using a portable retroreflectometer. In: E1710-05, (2005)
📄 Laurent J, Hébert J.F, Lefebvre D, Savard Y. 3D laser road profiling for the automated measurement of road surface conditions and geometry. 17th international road federation world meeting, vol. 2, p. 30 (2014)
📄 Reiterer A, Dambacher M, Maindorfer I, Höfler H, Ebersbach D, Frey C, Scheller S, Klose D. Straßenzustandsüberwachung in sub-millimeter. In: Photogrammetrie, Laserscanning, Optische 3D-Messtechnik, Beiträge der Oldenburger 3D-Tage, pp. 78–85. Herbert Wichmann Verlag, Karlsruhe, Germany (2013). In German
📄 Zhang Y, Lu Z, Zhang X, Xue J-H, Liao Q. Deep learning in lane marking detection: A survey. IEEE Trans Intell Transp Syst. 2022;23(7):5976–92. https://doi.org/10.1109/TITS.2021.3070111.
📄 Zhang D, Xu X, Lin H, Gui R, Cao M, He L. Automatic road-marking detection and measurement from laser-scanning 3D profile data. Autom Constr. 2019;108:102957. https://doi.org/10.1016/j.autcon.2019.102957.
📄 Bar Hillel A, Lerner R, Levi D, Raz G. Recent progress in road and lane detection: a survey. Mach Vis Appl. 2014;25(3):727–45.
📄 Lulla, K., Chandra, R., & Ranjan, K. (2025). Factory-grade diagnostic automation for GeForce and data centre GPUs. International Journal of Engineering, Science and Information Technology, 5(3), 537–544. https://doi.org/10.52088/ijesty.v5i3.1089
📄 Otsu N. A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern. 1979;9(1):62–6.
📄 Veit T, Tarel J-P, Nicolle P, Charbonnier P. Evaluation of road marking feature extraction. In: 11th international IEEE conference on intelligent transportation systems, pp. 174–181 (2008)
📄 Em PP, Hossen J, Fitrian I, Wong EK. Vision-based lane departure warning framework. Heliyon. 2019;5(8):02169.
📄 Tarel J-P, Ieng S-S, Charbonnier P. Using robust estimation algorithms for tracking explicit curves. In: 7th European conference on computer vision (ECCV), pp. 492–407 (2002)
📄 Liang D, Guo Y-C, Zhang S-K, Mu T-J, Huang X. Lane detection: A survey with new results. J Comput Sci Technol. 2020;35(3):493–505. https://doi.org/10.1007/s11390-020-0476-4.
📄 Perlin K. An image synthesizer. In: Proceedings of the 12th annual conference on computer graphics and interactive techniques. SIGGRAPH ’85, pp. 287–296. Association for Computing Machinery, New York, NY, USA (1985)
📄 Soilán M, González-Aguilera D, del-Campo-Sánchez A, Hernández-López D, Del Pozo S. Road marking degradation analysis using 3D point cloud data acquired with a low-cost Mobile Mapping System. Autom Constr 2022;141:104446 https://doi.org/10.1016/j.autcon.2022.104446
📄 Wu J, Liu W, Maruyama Y. Street view image-based road marking inspection system using computer vision and deep learning techniques. Sensors. 2024;24(23): https://doi.org/10.3390/s24237724.
📄 Vokhidov H, Hong HG, Kang JK, Hoang TM, Park KR. Recognition of damaged arrow-road markings by visible light camera sensor based on convolutional neural network. Sensors 2016;16(12) https://doi.org/10.3390/s16122160
📄 Iparraguirre O, Iturbe-Olleta N, Brazalez A, Borro D. Road marking damage detection based on deep learning for infrastructure evaluation in emerging autonomous driving. IEEE Trans Intell Transp Syst. 2022;23(11):22378–85.
📄 Chen R-C, Chao W-K, Manongga WE, Sub-r-pa C., Instance segmentation of road marking signs using YOLO models. J Adv Inform Technol. 2024;15(10) https://doi.org/10.12720/jait.15.10.1131-1137
📄 Wei C, Li S, Wu K, Zhang Z, Wang Y. Damage inspection for road markings based on images with hierarchical semantic segmentation strategy and dynamic homography estimation. Autom Constr. 2021;131:103876. https://doi.org/10.1016/j.autcon.2021.103876.
📄 Kong W, Zhong T, Mai X, Zhang S, Chen M, Lv G. Automatic detection and assessment of pavement marking defects with street view imagery at the city scale. Remote Sens. 2022;14(16) https://doi.org/10.3390/rs14164037.
📄 Wen C, Sun X, Li J, Wang C, Guo Y, Habib A. A deep learning framework for road marking extraction, classification and completion from mobile laser scanning point clouds. ISPRS J Photog Remote Sens. 2019;147:178–92. https://doi.org/10.1016/j.isprsjprs.2018.10.007.
📄 Tan M, Pang R, Le QV. EfficientDet: Scalable and Efficient Object Detection. In: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR) (2020)
📄 Wang J, Liao X, Wang Y, Zeng X, Ren X, Yue H, et al. M-sksnet: Multi-scale spatial kernel selection for image segmentation of damaged road markings. Remote Sens. 2024;16(9) https://doi.org/10.3390/rs16091476.
📄 Wang J, Zeng X, Wang Y, Ren X, Wang D, Qu W, et al. A multi-level adaptive lightweight net for damaged road marking detection based on knowledge distillation. Remote Sens. 2024;16(14) https://doi.org/10.3390/rs16142593.
📄 He K, Gkioxari Dollár P, Girshick RA. Mask R-CNN. In: IEEE international conference on computer vision (ICCV), pp. 2980–2988 (2017)
📄 Kurita T, Otsu N, Abdelmalek N. Maximum likelihood thresholding based on population mixture models. Pattern Recogn. 1992;25(10):1231–40.
📄 Xu S, Wang J, Wu P, Shou W, Wang X, Chen M. Vision-based pavement marking detection and condition assessment-a case study. Appl Sci. 2021;11(7) https://doi.org/10.3390/app11073152.
📄 Jessurun N, Paradis O, Roberts A, Asadizanjani N. Component detection and evaluation framework CDEF): A semantic annotation tool. Microsc Microanal. 2020;26(S2):1470–4.
📄 Lin T-Y, Dollár P, Girshick R, He K, Hariharan B, Belongie S. Feature pyramid networks for object detection. In: IEEE conference on computer vision and pattern recognition, pp. 2117–2125 (2017)
📄 Lin T-Y, Goyal P, Girshick R, He K, Dollár P. Focal loss for dense object detection. In: IEEE international conference on computer vision, pp. 2980–2988 (2017)
📄 Loshchilov I, Hutter F. Decoupled weight decay regularization. In: 7th international conference on learning representations, ICLR 2019. OpenReview.net, New Orleans USA (2019)
📄 Journal Officiel de la République Française: Instruction ministérielle sur la sécurité routière. 7ème PARTIE : Marques sur chaussée. in French (2021). https://equipementsdelaroute.cerema.fr/versions-consolidees-des-9-parties-de-l-a528.html
📄 Kumar Enugala, V. (2025). Quantum Sensors for Micro-Corrosion Detection. International Journal of Computational and Experimental Science and Engineering, 11(3). https://doi.org/10.22399/ijcesen.3481

Most read articles by the same author(s)