AERIAL PHOTOGRAMMETRY FOR THE IDENTIFICATION OF FAULTS IN FLEXIBLE PAVEMENTS
Keywords:
UAV photogrammetry, flexible pavements, pavement distress, remote sensing, image classificationAbstract
DOI: https://doi.org/10.46296/ig.v9i17.0337
Abstract
Pavement condition assessment is a fundamental task for road infrastructure management. Traditionally, this process is carried out through field visual inspections, which involve high costs, significant time requirements, and safety risks for technical personnel. In this context, this study aims to identify and classify failures in flexible pavements using aerial photogrammetry techniques based on unmanned aerial vehicles (UAVs). The methodology included aerial image acquisition, orthomosaic generation, digital image processing, and supervised classification to detect different types of pavement distress. The results were compared with the traditional visual inspection method based on the Pavement Condition Index (PCI). The results allowed the identification of several types of pavement distress, including cracks, patches, potholes, and weathering, reaching a kappa index of 0.81. However, the comparison between visual inspection and photogrammetric classification showed an overall accuracy of 58%. Cracks and patches achieved the highest accuracy levels, while other failures were more difficult to distinguish due to spectral similarities and environmental factors. The study concludes that UAV-based photogrammetry represents a promising alternative for pavement monitoring, especially for preliminary assessments and large-scale surveys. Nevertheless.
Keywords: UAV photogrammetry, flexible pavements, pavement distress, remote sensing, image classification.
Downloads
References
Braun, A. (2020, octubre). SAR-based landcover classification with Sentinel-1 GRD products. https://step.esa.int/docs/tutorials/S1TBX%20Landcover%20classification%20with%20Sentinel-1%20GRD.pdf
CORDILLERA LA VIUDA – [Tesis de grado, Universidad Privada del Norte]. https://repositorio.upn.edu.pe/bitstream/handle/11537/35622/TESIS%20-NILO- FIORELLA_PDF_TOTAL.pdf?sequence=1&isAllowed=y
Cornejo, E., & Valle, A. (2018). Metodología para el uso de imágnenes de sistemas de aeronaves pilotadas a distancia (RPAS) para la evaluación de la condición del pavimento en la carretera tramo Huancayo—Izcuchaca km 162+000 al km 163+000 [Tesis de grado, Ricardo Palma]. https://repositorio.urp.edu.pe/handle/20.500.14138/3411
Cui, L., Qi, Z., Chen, Z., Meng, F., & Shi, Y. (2015). Pavement Distress Detection Using Random Decision Forests. En C. Zhang, W. Huang, Y. Shi, P. S. Yu, Y. Zhu, Y. Tian,
Falcon, K., & Ramon, N. (2023). APLICACIÓN DE LA FOTOGRAMETRÍA CON RPA, PARA ANALIZAR LA CALIDAD DEL PAVIMENTO FLEXIBLE EN LA CARRETERA LIMACANTA - HUALLAY, TRAMO LAGUNA 7 COLORES - FANTASMA CORDILLERA LA VIUDA – [Tesis de grado, Universidad Privada del Norte]. https://repositorio.upn.edu.pe/bitstream/handle/11537/35622/TESIS%20-NILO-FIORELLA_PDF_TOTAL.pdf?sequence=1&isAllowed=y
Hoffman, M., & Del Águila, P. (1985, octubre). Estudios de evaluación estructural de pavimentos basados en la interpretación de curvas de deflexiones (ensayos no destructivos). https://www.academia.edu/6082128/ESTUDIOS_DE_EVALUACION_ESTRUCTURAL_DE_PAVIMENTOS_BASADOS_EN_LA_INTERPRETACION_DE_CURVAS_DE_DEFLEXIONES_ENSAYOS_NO_DESTRUCTIVOS
Maeda, H., Sekimoto, Y., Seto, T., Kashiyama, T., & Omata, H. (2018). Road damage detection using deep neural networks with images captured through a smartphone. arXiv. https://doi.org/10.48550/arXiv.1801.09454
Ministerio de Obras Públicas y Comunicaciones. (1990). IDENTIFICACIÓN DE FALLAS EN PAVIMENTOS Y TÉCNICAS DE REPARACIÓN (p. 212) [Catálogo]. Departamento de administración y evaluación de pavimentos. https://www.mopc.gob.do/media/2335/sistema-identifici%C3%B3n-fallas.pdf
Montejo Fonseca, A. (1998). Ingeniería de pavimentos para carreteras (2a ed). Universidad Católica de Colombia.
Morales, J. (2004). Técnicas de rehabilitación de pavimentos de concreto utilizando sobrecapas de refuerzo [Tesis de grado, Universidad de Piura]. https://pirhua.udep.edu.pe/backend/api/core/bitstreams/939ab42a-fd28-41f9-b6a2-5aaad4e3a5d6/content
P. Zhang, & J. He (Eds.), Data Science (pp. 95-102). Springer International Publishing.
Pachón, I. (2016). Evaluación de la condición de envejecimiento en pavimentos flexibles mediante técnicas de Espectroradiometría y clasificación en imágenes multiespectrales [Tesis de maestria, Universidad Distrital Francisco José de Caldas]. https://repository.udistrital.edu.co/bitstream/handle/11349/2776/Pach%c3%b3nCend alesIndiraPaola2016.pdf?sequence=1&isAllowed=y
Pan, Y., Zhang, X., Cervone, G., & Yang, L. (2018). Detection of asphalt pavement potholes and cracks based on UAV multispectral imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(10), 3701–3712. https://doi.org/10.1109/JSTARS.2018.2865528
Peng, C., Yang, M., Zheng, Q., Zhang, J., Wang, D., Yan, R., Wang, J., & Li, B. (2020). A triple-thresholds pavement crack detection method leveraging random structured forest. Construction and Building Materials, 263, 120080. https://doi.org/10.1016/j.conbuildmat.2020.120080
Peña, M., & Zárate, B. (2020). Empleo de VANT para determinar fallas superficiales en pavimentos flexibles. 17(2). https://revistas.unilibre.edu.co/index.php/avances/article/view/6626
Ramírez, L. (2019). Sistema de clasificación de severidad de daños en pavimentos flexibles para determinar poibles intervenciones [Grado, EIA]. https://core.ac.uk/download/pdf/232126784.pdf
Ruiz, L. (s. f.). Aplicación de filtros morfológicos en imágenes (p. 11). Universidad Politecnica de Valencia. Recuperado 24 de mayo de 2024, de https://riunet.upv.es/bitstream/handle/10251/145903/Ruiz%20-%20Aplicaci%C3%B3n%20de%20filtros%20morfol%C3%B3gicos%20en%20im%C3%A1genes.pdf?sequence=1
Sylvester Inkoom, A. B., John Sobanjo, & Niu, X. (2019). Prediction of the crack condition of highway pavements using machine learning models. Structure and Infrastructure Engineering, 15(7), 940-953. https://doi.org/10.1080/15732479.2019.1581230
Tello, L., Aguirre, M., Díaz, J. P., & Hernández, F. (2021). Evaluación de daños en pavimento flexible usando fotogrametría terrestre y redes neuronales. TecnoLógicas, 24(50). https://revistas.itm.edu.co/index.php/tecnologicas/article/view/1686/1811
Vargas, C. (2018). Análisis comparativo de la inspección visual de un pavimento flexible, por los métodos tradicional y por sensores remotos en un kilómetro de la calle séptima en el municipio de Cajica Cundinamarca [Tesis de grado, Universidad Militar Nueva Granada]. https://repository.unimilitar.edu.co/handle/10654/20509
Vasconcelos, R., Fonseca, A., Batista, G., Vinícius, V., Azevedo, B., & Sousa, A. (2021). Mapeamento de manifestações patológicas em pavimento asfáltico por meio de uso de drones. 61-72. https://revistaalconpat.org/index.php/RA/article/view/521
Zhang, L., Xu, W., Zhu, L., Yuan, X., & Zhang, C. (2019). Study on Pavement Defect Detection Based on Image Processing Utilizing UAV. Journal of Physics: Conference Series, 1168, 042011. https://doi.org/10.1088/1742-6596/1168/4/042011
Zhang, L., Yang, F., Zhang, Y. D., & Zhu, Y. J. (2021). Road crack detection using deep convolutional neural network. IEEE Access, 9, 11382–11394. https://doi.org/10.1109/ACCESS.2021.3051324
Zhu, J., Zhong, J., Ma, T., Huang, X., Zhang, W., & Zhou, Y. (2022). Pavement distress detection using convolutional neural networks with images captured via UAV. Automation in Construction, 133, 103991. https://doi.org/10.1016/j.autcon.2021.103991
Zhu, Z., German, S., & Brilakis, I. (2022). Visual inspection of asphalt pavement using UAV images: A deep learning approach. Automation in Construction, 135, 104111. https://doi.org/10.1016/j.autcon.2022.104111
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Scientific Journal INGENIAR: Engineering, Technology and Research
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
