An Integrated Deep Learning and Fuzzy Logic System for Road Crack Severity Analysis, and Pedestrian Fall Risk Prediction

Chakurkar, Priti; Vora, Deepali

doi:10.22111/ijfs.2025.52137.9268

Document Type : Research Paper

Authors

Priti Chakurkar ¹
Deepali Vora ²

¹ 1. Symbiosis Institute of Technology PUNE, Symbiosis International (Deemed University), Pune, India 2 School of Computer Engineering, Dr.Vishwanath

² Symbiosis Institute of Technology PUNE, Symbiosis International (Deemed University), Pune, India

https://doi.org/10.22111/ijfs.2025.52137.9268

Abstract

Cracks on pedestrian sidewalks and walkways pose a significant safety hazard, increasing the risk of trips, falls, and injuries, particularly for vulnerable groups such as the elderly and children. Traditional crack detection and severity assessment methods are usually manual, time-consuming, and subjective, especially in the Indian context, where road and
sidewalk inspections are still conducted mainly through visual surveys due to cost and infrastructure constraints. This paper proposes an integrated framework of deep learning and fuzzy logic to analyze sidewalk crack severity and predict pedestrian fall risk automatically. A novel crack quantification method using edge detection and adaptive segmentation is proposed to measure crack width accurately. A fine-tuned deep learning model is employed for automating crack
severity prediction, which achieved 95% accuracy and demonstrated robustness to noise, blur, and lighting variations. To estimate fall risk, a fuzzy inference system is developed considering four inputs: crack severity, road condition, weather, and pedestrian age, and a set of expert-defined fuzzy rules is applied to estimate risk levels. The outcomes show the effectiveness of the proposed FIS scheme, which achieved 95% accuracy and outperformed non-fuzzy baseline approaches.

Keywords

Main Subjects

Computer Science

References

[1] L. Ali, H. Al-Jassmi, M. Swavaf, W. Khan, F. Alnajjar, RS-Net: Residual sharp u-net architecture for pavement
crack segmentation and severity assessment, Journal of Big Data, 11(1) (2024), 116. https://doi.org/10.1186/
s40537-024-00981-y

[2] A. Ali, U. Heneash, A. Hussein, M. Eskebi, Predicting pavement condition index using fuzzy logic technique,
Infrastructures, 7(7) (2022), 91. https://doi.org/10.3390/infrastructures7070091

[3] M. Bhardwaj, N. U. Khan, V. Baghel, Road crack detection using pixel classification and intensity-based
distinctive fuzzy c-means clustering, Visual Computer, 41 (2025), 1689-1704. https://doi.org/10.1007/
s00371-024-03470-8

[4] P. S. Chakurkar, D. Vora, S. Patil, K. Kotecha, Automated crack localization for road safety using contextual u-net
with spatial-channel feature integration, MethodsX, 13 (2024), 102796. https://doi.org/10.1016/j.mex.2024.
102796

[5] F. Demir, E. Yalcin, M. Yilmaz, CrackNet: A new deep learning-based strategy for automatic classification of
road cracks after earthquakes, Engineering Science and Technology, an International Journal, 69 (2025), 102128.
https://doi.org/10.1016/j.jestch.2025.102128

[6] L. Deng, A. Zhang, J. Guo, Y. Liu, An integrated method for road crack segmentation and surface feature quantification
under complex backgrounds, Remote Sensing, 15(6) (2023), 1530. https://doi.org/10.3390/rs15061530

[7] F. Elghaish, S. Matarneh, E. Abdellatef, F. Rahimian, M. R. Hosseini, A. F. Kineber, Multi-layers deep learning
model with feature selection for automated detection and classification of highway pavement cracks, Smart and
Sustainable Built Environment, 14(2) (2025), 511-535. https://doi.org/10.1108/SASBE-09-2023-0251

[8] A. Galanis, G. Botzoris, N. Eliou, Pedestrian road safety in relation to urban road type and traffic flow, Transportation
Research Procedia, 24 (2017), 220-227. https://doi.org/10.1016/j.trpro.2017.05.111

[9] H. Gong, L. Liu, H. Liang, Y. Zhou, L. Cong, A state-of-the-art survey of deep learning models for automated
pavement crack segmentation, International Journal of Transportation Science and Technology, 13 (2024), 44-57.
https://doi.org/10.1016/j.ijtst.2023.11.005

[10] J. Ha, D. Kim, M. Kim, Assessing severity of road cracks using deep learning-based segmentation and detection,
Journal of Supercomputing, 78(16) (2022), 17721-17735. https://doi.org/10.1007/s11227-022-04560-x

[11] N. D. Hoang, Q. L. Nguyen, Automatic recognition of asphalt pavement cracks based on image processing and machine learning approaches: A comparative study on classifier performance, Mathematical Problems in Engineering,
2018 (2018), 1-16. https://doi.org/10.1155/2018/6290498

[12] I. Hussain, L. Alam, Adaptive road crack detection and segmentation using Einstein operators and ANFIS for
real-time applications, Journal of Intelligent Systems and Control, 3(4) (2024), 213-226. https://doi.org/10.
56578/jisc030402

[13] D. A. Jehu, J. C. Davis, R. S. Falck, K. J. Bennett, D. Tai, M. F. Souza, B. R. Cavalcante, M. Zhao, T. Liu-
Ambrose, Risk factors for recurrent falls in older adults: A systematic review with meta-analysis, Maturitas, 144
(2021), 23-28. https://doi.org/10.1016/j.maturitas.2020.10.021

[14] M. Kara¸sahin, S. Terzi, Performance model for asphalt concrete pavement based on the fuzzy logic approach,
Transport, 29(1) (2014), 18-27. https://doi.org/10.3846/16484142.2014.893926

[15] R. Kumar, S. Tung, Automated detection and severity assessment of asphalt pavement distress using YOLOv8: A
deep learning approach, International Journal of Pavement Research and Technology, (2025). https://doi.org/
10.1007/s42947-025-00584-7

[16] C. Liu, C. S. Tang, B. Shi, W. B. Suo, Automatic quantification of crack patterns by image processing, Computational
and Geosciences, 57 (2013), 77-80. https://doi.org/10.1016/j.cageo.2013.04.008

[17] W. Liu, C. Zhang, H. Ma, Y. Li, Distance transform-based skeleton extraction and its applications in sensor
networks, IEEE Transactions on Parallel and Distributed Systems, 24(9) (2013), 1763-1772. https://doi.org/
10.1109/TPDS.2012.300

[18] S. Mathavan, V. Kanapathippillai, A. Kumar, C. Chandrakumar, K. Kamal, M. Rahman, M. Stonecliffe-Jones,
Detection of pavement cracks using tiled fuzzy Hough transform, Journal of Electronic Imaging, 26(5) (2017).
https://doi.org/10.1117/1.JEI.26.5.053008

[19] H. Oliveira, P. L. Correia, Automatic road crack detection and characterization, IEEE Transactions on Intelligent
Transportation Systems, 14(1) (2013), 155-168. https://doi.org/10.1109/TITS.2012.2208630

[20] S. Qiu, W. Wang, S. Wang, K. C. P. Wang, Methodology for accurate AASHTO PP67-10-based cracking quantification
using 1-mm 3D pavement images, Journal of Computing in Civil Engineering, 31(2) (2017), 04016056.
https://doi.org/10.1061/(ASCE)CP.1943-5487.0000627

[21] N. M. Ralevic, M. Delic, L. Nedovic, Aggregation of fuzzy metrics and its application in image segmentation, Iranian
Journal of Fuzzy Systems, 19(3) (2022), 19-37. https://doi.org/10.22111/ijfs.2022.6941

[22] S. Ranjbar, F. Moghadas Nejad, H. Zakeri, Image-based severity analysis of asphalt pavement bleeding using a
metaheuristic-boosted fuzzy classifier, Automation in Construction, 166 (2024), 105655. https://doi.org/10.
1016/j.autcon.2024.105655

[23] A. G. Rundle, R. P. Crowe, H. E.Wang, A. X. Lo, A methodology for the public health surveillance and epidemiologic
analysis of outdoor falls that require an emergency medical services response, Injury Epidemiology, 10(1) (2023),
4. https://doi.org/10.1186/s40621-023-00414-z

[24] F. Saeed, M. Rahman, M. Mahmood, A fuzzy inference system for predicting pavement surface damage due to
combined action of traffic loading and water, International Journal of Pavement Engineering, 23(2) (2020), 261-
269. https://doi.org/10.1080/10298436.2020.1742333

[25] W. Song, G. Jia, D. Jia, H. Zhu, Automatic pavement crack detection and classification using multiscale feature
attention network, IEEE Access, 7 (2019), 171001-171012. https://doi.org/10.1109/ACCESS.2019.2956191

[26] J. Swanenburg, E. D. de Bruin, D. Uebelhart, T. Mulder, Falls prediction in elderly people: A 1-year prospective
study, Gait and Posture, 31(3) (2010), 317-321. https://doi.org/10.1016/j.gaitpost.2009.11.013

[27] L. Wang, Q. Feng, J. Yan, Pavement crack detection based on depth-supervision FRRN model, Measurement and
Control, 58(8) (2024), 1078-1088. https://doi.org/10.1177/00202940241292189

[28] Q. Yang, Y. Deng, Evaluation of cracking in asphalt pavement with stabilized base course based on statistical pattern
recognition, International Journal of Pavement Engineering, 20(4) (2017), 417-424. https://doi.org/10.1080/
10298436.2017.1299528

[29] X. Yang, H. Li, Y. Yu, X. Luo, T. Huang, X. Yang, Automatic pixel-level crack detection and measurement
using fully convolutional network, Computer-Aided Civil and Infrastructure Engineering, 33(12) (2018), 1090-
1109. https://doi.org/10.1111/mice.12412

[30] M. Yilmaz, et al., Automatic segmentation of asphalt cracks on highways after large-scale and severe earthquakes
using deep learning-based approaches, IEEE Access, 13 (2025), 22820-22830. https://doi.org/10.1109/ACCESS.
2025.3536554

[31] J. Yuan, Q. Ren, C. Jia, J. Zhang, J. Fu, M. Li, Automated pixel-level crack detection and quantification using
deep convolutional neural networks for structural condition assessment, Structures, 59 (2024), 105780. https:
//doi.org/10.1016/j.istruc.2023.105780

An Integrated Deep Learning and Fuzzy Logic System for Road Crack Severity Analysis, and Pedestrian Fall Risk Prediction

References

References

Volume 22, Issue 6November and December 2025Pages 103-123

Volume 22, Issue 6
November and December 2025
Pages 103-123