Structural Analysis of Road Potholes Using Deep Neural Networks

Vista sencilla de ítem
dc.creatorRique-Sabogal, Angie-P
dc.creatorGuatame-Medina, Miguel-A
dc.creatorMoreno-Manrique, Cristhian-F
dc.creatorJiménez-López, Fabián-R
dc.creatorJiménez-López, Andrés-F
dc.date2025-06-20
dc.date.accessioned2025-10-01T23:53:15Z
dc.descriptionThe rapid growth of the global population has intensified vehicular traffic, posing a significant challenge to its management. In developing countries such as Colombia, traffic accidents exhibit high mortality rates, largely attributed to road defects, such as cracks and potholes. Given this problem, the objective of this study was to develop an automated system for detecting defects in urban pavements using Convolutional Neural Networks (CNNs) to classify 11 types of road surface failure. The methodology involved creating a dataset from images of defective roads, which was used to train deep neural network models. Two optimizers, SGDM and ADAM, were evaluated using color and grayscale pictures, processed in MATLAB® and validated by civil engineering experts. The results showed that the SGDM optimizer achieved an accuracy of 74.67 % with color images, while ADAM achieved a performance of 52.51 % with grayscale images. These findings demonstrated the potential of CNNs and digital image processing techniques to automate pavement inspection, increasing both efficiency and accuracy in evaluating road infrastructure. Finally, it is concluded that the use of deep neural networks represents a viable alternative for developing intelligent pavement management systems and supports the implementation of data-driven solutions to optimize urban road maintenance.en-US
dc.descriptionEl aumento acelerado de la población mundial ha intensificado el tráfico vehicular, lo que plantea un desafío significativo para su gestión. En países en desarrollo como Colombia, los accidentes de tránsito presentan una alta tasa de mortalidad, atribuida en gran medida a defectos en las carreteras, como grietas y baches. Ante esta problemática, el objetivo de este estudio fue desarrollar un sistema automatizado para la detección de defectos en pavimentos urbanos, utilizando redes neuronales convolucionales (CNN, por sus siglas en inglés) para clasificar 11 tipos de fallas en las vías. La metodología empleada consistió en la creación de una base de datos a partir de imágenes de carreteras con defectos, la cual fue utilizada para entrenar los modelos de redes neuronales profundas. Se evaluaron dos optimizadores, SGDM y ADAM, aplicados sobre imágenes a color y en escala de grises, procesadas en MATLAB® y validadas por expertos en ingeniería civil. Los resultados mostraron que el optimizador SGDM alcanzó una precisión del 74.67 % con imágenes a color, mientras que ADAM obtuvo un desempeño del 52.51 % con imágenes en escala de grises. En general, los hallazgos confirmaron la viabilidad de las CNN y las técnicas de procesamiento digital de imágenes para automatizar el proceso de inspección de pavimentos y mejorar la eficiencia y precisión de la evaluación de la infraestructura vial. Finalmente, se concluye que el uso de redes neuronales profundas constituye una alternativa confiable para el desarrollo de sistemas inteligentes de gestión de pavimentos y respalda la implementación de soluciones basadas en datos para optimizar el mantenimiento de las vías urbanas.es-ES
dc.formatapplication/pdf
dc.formattext/xml
dc.formatapplication/zip
dc.identifierhttps://revistas.itm.edu.co/index.php/tecnologicas/article/view/3266
dc.identifier10.22430/22565337.3266
dc.identifier.urihttps://hdl.handle.net/20.500.12622/7930
dc.languagespa
dc.publisherInstituto Tecnológico Metropolitano (ITM)es-ES
dc.relationhttps://revistas.itm.edu.co/index.php/tecnologicas/article/view/3266/3677
dc.relationhttps://revistas.itm.edu.co/index.php/tecnologicas/article/view/3266/3773
dc.relationhttps://revistas.itm.edu.co/index.php/tecnologicas/article/view/3266/3774
dc.relation/*ref*/J. A. Lupano, La infraestructura de transporte sostenible y su contribución a la igualdad en América Latina y el Caribe, Santiago de Chile, Chile: Comisión Económica para América Latina y el Caribe (CEPAL), 2013. https://hdl.handle.net/11362/35883
dc.relation/*ref*/J. D. Madroñero Urcuqui, and Y. C. Valencia López, “Metodología para la identificación automática del deterioro en pavimento flexible, por medio de fotografías aéreas tomadas desde vehículos no tripulados,” Tesis de grado, Universidad del Valle, Santiago de Cali, Colombia, 2019.
dc.relation/*ref*/J. F. Olarte Bustinza, and C. M. Soto Mallqui, “inspección de seguridad vial y propuesta de mejora en la intersección cuádruple de las avenidas el sol, tullumayo, pardo paseo de los héroes y la alameda pachacuteq, ubicadas en el centro histórico de la ciudad del cusco,” Tesis de grado, Pontificia Universidad Católica del Perú, Lima, Perú, 2023. http://hdl.handle.net/20.500.12404/26106
dc.relation/*ref*/S. M. Martinez Niño, and G. A. Rojas Sánchez, “Inventario Vial y Alternativas de Intervención para el Tramo Vial que une los Municipios de Lourdes hasta Sardinata Desde el K10+00 al K17+00, Departamento de Norte de Santander,” Tesis de grado, Universidad Francisco de Paula Santander, Cucutá, Colombia, 2023. https://repositorio.ufps.edu.co/handle/ufps/6916
dc.relation/*ref*/X. Chen, C. Liu, L. Chen, X. Zhu,Y. Zhang, and C. Wang, “A Pavement Crack Detection and Evaluation Framework for a UAV Inspection System Based on Deep Learning,” Appl. Sci., vol. 14, no. 3, p. 1157, Feb. 2024. https://doi.org/10.3390/app14031157
dc.relation/*ref*/D. Arya et al., “Deep learning-based road damage detection and classification for multiple countries,” Automat. Constr., vol. 132, p. 103935, Dec. 2021. https://doi.org/10.1016/j.autcon.2021.103935
dc.relation/*ref*/M. Anis Benallal, and M. Si Tayeb, “An image-based convolutional neural network system for road defects detection,” IAES Int. J. Artif. Intell., vol. 12, no. 2, pp. 577–584, Jun. 2023. http://doi.org/10.11591/ijai.v12.i2.pp577-584
dc.relation/*ref*/M. Mythili, D. Janani, D. S. Madhumitha, V. Mangala Madhumita, and R. Nandhini, “A Framework for Precise Road Damage Detection Using Deep Learning,” in 2nd International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA), Namakkal, India, 2024, pp. 1–5. http://dx.doi.org/10.1109/aimla59606.2024.10531516
dc.relation/*ref*/X. Yang et al., “Research and applications of artificial neural network in pavement engineering: A state-of-the-art review,” J. Traffic Transp. Engin., vol. 8, no. 6, pp. 1000–1021, Dec. 2021. https://doi.org/10.1016/j.jtte.2021.03.005
dc.relation/*ref*/A. Ashraf, A. Sophian, A. Akramin shafie, T. Surya Gunawan, and N. Nadia Ismail, “Machine learning-based pavement crack detection, classification, and characterization: a review,” Bul. Electr. Eng. Inform., vol. 12, no. 6, pp. 3601–3619, Dec. 2023. https://doi.org/10.11591/eei.v12i6.5345
dc.relation/*ref*/J.-W. Baek, and K. Chung, “Pothole classification model using edge detection in road image,” Appl. Sci., vol. 10, no. 19, p. 6662, Oct. 2020. https://doi.org/10.3390/app10196662
dc.relation/*ref*/N. Ma et al., “Computer vision for road imaging and pothole detection: a state-of-the-art review of systems and algorithms,” Transp. Saf. Environ., vol. 4, no. 4, pp. 1–16, Dec. 2022. https://doi.org/10.1093/tse/tdac026
dc.relation/*ref*/L. Manoni, S. Orcioni, and M. Conti, “Recent Advancements in Deep Learning Techniques for Road Condition Monitoring: A Comprehensive Review,” IEEE Acc., vol. 12, pp. 154271–154293, Oct. 2024. https://doi.org/10.1109/ACCESS.2024.3481649
dc.relation/*ref*/J. Li, T. Liu, X. Wang, and J. Yu, “Automated asphalt pavement damage rate detection based on optimized GA-CNN,” Automat. Constr., vol. 136, p. 104180, Apr. 2022. https://doi.org/10.1016/j.autcon.2022.104180
dc.relation/*ref*/B. Bučko, E. Lieskovská, K. Zábovská, and M. Zábovský, “Computer Vision Based Pothole Detection under Challenging Condition,” Sensors, vol. 22, no. 22, p. 8878, Nov. 2022. https://doi.org/10.3390/s22228878
dc.relation/*ref*/Y. Sang, Q. Yu, Y. Fang, V. Vo, and R. Wix, “Smartphone-Based IRI Estimation for Pavement Roughness Monitoring A Data-Driven Approach,” IEEE Internet Things J., vol. 11, no. 11, pp. 19708-19720, Jun. 2024. https://ieeexplore.ieee.org/document/10444016
dc.relation/*ref*/K. Zhao, S. Xu, J. Loney, A. Visentin, and Z. Li, “Road pavement health monitoring system using smartphone sensing with a two-stage machine learning model,” Automat. Constr., vol. 167, p. 105664, Nov. 2024. https://doi.org/10.1016/j.autcon.2024.105664
dc.relation/*ref*/M. Staniek, “Road pavement condition diagnostics using smartphone-based data crowdsourcing in smart cities,” J. Traffic Transp. Eng., vol. 8, no. 4, pp. 554–567, Aug. 2021. https://doi.org/10.1016/j.jtte.2020.09.004
dc.relation/*ref*/S. Matarneh, F. Elghaish, D. J. Edwards, F. Pour Rahimian, E. Abdellatef, and O. Ejohwomu, “Automatic Crack Classification on Asphalt Pavement Surfaces using Convolutional Neural Networks and Transfer Learning,” J. Informat. Technol. Constr., vol. 29, pp. 1239–1256, Dec. 2024. https://doi.org/10.36680/j.itcon.2024.055
dc.relation/*ref*/G. Ochoa-Ruiz, A. A. Angulo-Murillo, A. Ochoa-Zezzatti, L. M. Aguilar-Lobo, J. A. Vega-Fernández, and S. Natraj, “An Asphalt Damage Dataset and Detection System Based on Retinanet for Road Conditions Assessment,” Appl. Sci., vol. 10, no. 11, p. 3974, Jun. 2020. https://doi.org/10.3390/app10113974
dc.relation/*ref*/F. Jalili, S. Morsal Ghavami, and H. Afsharnia, “An Artificial Neural Network approach to assess road roughness using smartphone-based crowdsourcing data,” Eng. Appl. Artif. Intell., vol. 138, no. Part A, p. 109308, Dec. 2024. https://doi.org/10.1016/j.engappai.2024.109308
dc.relation/*ref*/A. M. Al-Sabaeei, M. I. Souliman, and A. Jagadeesh, “Smartphone applications for pavement condition monitoring: A review,” Constr. Build. Mater., vol. 410, p. 134207, Jan. 2024. https://doi.org/10.1016/j.conbuildmat.2023.134207
dc.relation/*ref*/L. Tello-Cifuentes, M. Aguirre-Sánchez, J. P. Díaz-Díaz, and F. Hernández, “Evaluación de daños en pavimento flexible usando fotogrametría terrestre y redes neuronales,” TecnoL., vol. 24, no. 50, p. e1686, Jan. 2021. https://doi.org/10.22430/22565337.1686
dc.relation/*ref*/W. Song, G. Jia, H. Zhu, D. Jia, and L. Gao, “Automated Pavement Crack Damage Detection Using Deep Multiscale Convolutional Features,” J. Adv. Transport., vol. 2020, p. 6412562, Jan. 2020. https://doi.org/10.1155/2020/6412562
dc.relation/*ref*/Y. Safyari, M. Mahdianpari, and H. Shiri, “A Review of Vision-Based Pothole Detection Methods Using Computer Vision and Machine Learning,” Sensors, vol. 24, no. 17, p. 5652, Aug. 2024. https://doi.org/10.3390/s24175652
dc.relation/*ref*/C.-C. Hsieh, H.-W. Jia, W.-H. Huang, and M.-H. Hsih, “Deep Learning-Based Road Pavement Inspection by Integrating Visual Information and IMU,” Information, vol. 15, no. 4, p. 239, Apr. 2024. https://doi.org/10.3390/info15040239
dc.relation/*ref*/F. Liu, J. Liu, and L. Wang, “Asphalt pavement fatigue crack severity classification by infrared thermography and deep learning,” Automat. Constr., vol. 143, p. 104575, Nov. 2022. https://doi.org/10.1016/j.autcon.2022.104575
dc.relation/*ref*/H. Garita-Durán, J. Philipp Stöcker, and M. Kaliske, “Deep learning-based system for automated damage detection and quantification in concrete pavement,” Results Eng., vol. 25, p. 104546, Mar. 2025. https://doi.org/10.1016/j.rineng.2025.104546
dc.relation/*ref*/Y. Zhang, and L. Zhang, “Detection of Pavement Cracks by Deep Learning Models of Transformer and UNet,” IEEE Trans. Intell. Transp. Syst., vol. 25, no. 11, pp. 15791–15808, Nov. 2024. https://doi.org/10.1109/TITS.2024.3420763
dc.relation/*ref*/W. Guo, L. Zhong, D. Zhang, and Q. Li, “Pavement Crack Detection using Fractal Dimension and Semi-Supervised Learning,” Fractal Fract., vol. 8, no. 8, p. 468, Aug. 2024. https://doi.org/10.3390/fractalfract8080468
dc.relation/*ref*/J. Nnamdi Opara, A. B. Bo Thein, S. Izumi, H. Yasuhara, and P.-J. Chun, “Defect Detection on Asphalt Pavement by Deep Learning,” Int. J. GEOMATE, vol. 21, no. 83, pp. 87–94, Jul. 2021. https://doi.org/10.21660/2021.83.6153
dc.relation/*ref*/W. Cao, Q. Liu, and Z. He, “Review of Pavement Defect Detection Methods,” IEEE Acc., vol. 8, no. 1, pp. 14531–14544, Jan. 2020. https://doi.org/10.1109/aCCESS.2020.2966881
dc.relation/*ref*/R. Tao, R. Peng, Y. Jin, F. Gong, and B. Li, “Automatic Detection of Asphalt Pavement Crack Width Based on Machine Vision,” IEEE Trans. Intell. Transport. Syst., vol. 26, no. 1, pp. 484–496, Jan. 2025. https://doi.org/10.1109/TITS.2024.3492731
dc.relation/*ref*/S. Matarneh, F. Elghaish, F. Pour Rahimian, E. Abdellatef, and S. Abrishami, “Evaluation and optimisation of pre-trained CNN models for asphalt pavement crack detection and classification,” Automat. Constr., vol. 160, p. 105297, Apr. 2024. https://doi.org/10.1016/j.autcon.2024.105297
dc.relation/*ref*/A. Rasheed Rababaah, “A Deep Learning based Process Model for Crack Detection in Pavement Structures,” in 9th International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India, 2022, pp. 1–6. https://doi.org/10.23919/INDIACom54597.2022.9763286
dc.relation/*ref*/J. Lan, H. Wang, Z. Zhu, and Q. Zhang, “Computer Vision Based Pothole Road Detection and Recognition,” in 2024 5th Int. Conf. Comp. Vision, Image Deep Learn., (CVIDL), Zhuhai, China, 2024, pp. 505–509. https://doi.org/10.1109/CVIDL62147.2024.10603934
dc.relation/*ref*/D. Shu et al., “Research on Methods of Pavement Distress Detection using Convolutional Neural Network based on Highway Rapid Inspection Images,” in 2024 9th Int. Conf. Signal Image Process. (ICSIP), Nanjing, China, 2024, pp. 623–627. https://doi.org/10.1109/ICSIP61881.2024.10671436
dc.relation/*ref*/E. Ranyal, A. Sadhu, and K. Jain, “Road Condition Monitoring using Smart Sensing and Artificial Intelligence: A Review,” Sensors, vol. 22, no. 8, p. 3044, Apr. 2022. https://doi.org/10.3390/s22083044
dc.relation/*ref*/M. Zeeshan, S. M. Adnan, W. Ahmad, and F. Zeeshan Khan, “Structural Crack Detection and Classification using Deep Convolutional Neural Network,” Pakistan J. Eng. Technol., vol. 4, no. 4, pp. 50–56, Dec. 2021. https://doi.org/10.51846/vol4iss4pp50-56
dc.relation/*ref*/H. Jing, X. Zhang, and Z. Zhang, “Research on Automatic Identification of Asphalt Payment Defects Based on Deep Learning,” in 2024 7th Int. Conf. Adv. Algor. Contr. Eng. (ICAACE), Shanghai, China, 2024, pp. 1407–1412, https://doi.org/10.1109/ICAACE61206.2024.10548739
dc.relation/*ref*/A. As Sami, S. Sakib, K. Deb, and I. H. Sarker, “Improved YOLOv5-Based Real-Time Road Pavement Damage Detection in Road Infrastructure Management,” Algorithms, vol. 16, no. 9, p. 452, Sep. 2023. https://doi.org/10.3390/a16090452
dc.relation/*ref*/P. Li et al., “CNN-based pavement defects detection using grey and depth images,” Automat. Constr., vol. 158, p. 105192, Feb. 2024. https://doi.org/10.1016/j.autcon.2023.105192
dc.relation/*ref*/T. Zhang, D. Wang, and Y. Lu, “ECSNet: An Accelerated Real-Time Image Segmentation CNN Architecture for Pavement Crack Detection,” IEEE Trans. Intell. Transport. Syst., vol. 24, no. 12, pp. 15105–15112, Dec. 2023. https://doi.org/10.1109/TITS.2023.3300312
dc.relation/*ref*/D. Li, Z. Duan, X. Hu, D. Zhang, and Y. Zhang, “Automated classification and detection of multiple pavement distress images based on deep learning,” J. Traffic Transport. Eng., vol. 10, no. 2, pp. 276–290, Apr. 2023. https://doi.org/10.1016/j.jtte.2021.04.008
dc.relation/*ref*/H. Chu et al., “Deep Learning Method to Detect the Road Cracks and Potholes for Smart Cities,” Comput., Mater. Continua, vol. 75, no. 1, pp. 1863–1881, Feb. 2023. https://doi.org/10.32604/cmc.2023.035287
dc.relation/*ref*/R. Kothai, N. Prabakaran, Y. V. Srinivasa, L. Reddy Cenkeramaddi, and V. Kakani, “Pavement Distress Detection, Classification, and Analysis Using Machine Learning Algorithms: A Survey,” IEEE Acc., vol. 12, pp. 126943–126960, Sep. 2024. https://doi.org/10.1109/ACCESS.2024.3455093
dc.relation/*ref*/
dc.rightsDerechos de autor 2025 TecnoLógicases-ES
dc.rightshttps://creativecommons.org/licenses/by-nc-sa/4.0es-ES
dc.sourceTecnoLógicas; Vol. 28 No. 63 (2025); e3266en-US
dc.sourceTecnoLógicas; Vol. 28 Núm. 63 (2025); e3266es-ES
dc.source2256-5337
dc.source0123-7799
dc.subjectinfraestructura viales-ES
dc.subjectmantenimiento predictivoes-ES
dc.subjectmodelos de aprendizaje profundoes-ES
dc.subjectoptimización de algoritmoses-ES
dc.subjectprocesamiento digital de imágeneses-ES
dc.subjectroad infrastructureen-US
dc.subjectpredictive maintenanceen-US
dc.subjectdeep learning modelsen-US
dc.subjectalgorithm optimizationen-US
dc.subjectdigital image processingen-US
dc.titleStructural Analysis of Road Potholes Using Deep Neural Networksen-US
dc.titleAnálisis estructural de baches viales mediante redes neuronales profundases-ES
dc.typeinfo:eu-repo/semantics/article
dc.typeinfo:eu-repo/semantics/publishedVersion
dc.typeResearch Papersen-US
dc.typeArtículos de investigaciónes-ES

Archivos

Bloque original

Mostrando 1 - 3 de 3
Miniatura
Nombre:
3266_MPU_VF_v2.pdf
Tamaño:
653.06 KB
Formato:
Adobe Portable Document Format
Descargar
Miniatura
Nombre:
344281872004.xml
Tamaño:
107.86 KB
Formato:
Extensible Markup Language
Descargar
Miniatura
Nombre:
344281872004.epub
Tamaño:
2.13 MB
Formato:
Electronic publishing
Descargar

Colecciones

Revista TecnoLógicas - Cosecha Portal de Revistas