Detección inteligente de baches y estimación de su profundidad con aprendizaje profundo para la conservación de carreteras
Article Sidebar
Publicado
mar 19, 2025
##plugins.pubIds.doi.readerDisplayName##
https://doi.org/10.30878/ces.v32n0a37
Main Article Content
Mario Alberto Roman Garay
http://orcid.org/0000-0002-4328-4651
Carlos Alberto Hernández Beltran
http://orcid.org/0000-0002-5317-2506
Luis Alberto Morales Rosales
http://orcid.org/0000-0002-4753-9375
Hector Rodriguez Rangel
http://orcid.org/0000-0003-4999-3472
Miguel Antonio Villa Camacho
http://orcid.org/0009-0003-2086-9619
Jorge Luis Soto Audelo
http://orcid.org/0009-0004-6704-6756
Peter Lepej
http://orcid.org/0000-0002-7693-1966
http://orcid.org/0000-0002-4328-4651
Carlos Alberto Hernández Beltran
http://orcid.org/0000-0002-5317-2506
Luis Alberto Morales Rosales
http://orcid.org/0000-0002-4753-9375
Hector Rodriguez Rangel
http://orcid.org/0000-0003-4999-3472
Miguel Antonio Villa Camacho
http://orcid.org/0009-0003-2086-9619
Jorge Luis Soto Audelo
http://orcid.org/0009-0004-6704-6756
Peter Lepej
http://orcid.org/0000-0002-7693-1966
Resumen
Se aborda la detección inteligente de baches y la estimación precisa de su profundidad a partir de técnicas de aprendizaje profundo para la conservación de carreteras en entornos urbanos. Para ello, se emplea una cámara de profundidad y la red convolucional YOLOv8, entrenada con 273 imágenes, con la que se obtiene mAP de 84.7%, precisión de 85.7% y recall de 76.3%. Los resultados demuestran un error promedio de 5 mm en la estimación de profundidad. En este sentido, se ofrece una herramienta que apoya la gestión de infraestructura vial al proporcionar un inventario de la profundidad de los baches que facilite la planificación de tareas de mantenimiento. El deterioro de las carreteras, visible en forma de baches, conlleva altos costos de reparación y aumenta el riesgo de accidentes.
Article Details
Como citar
ROMAN GARAY, Mario Alberto et al.
Detección inteligente de baches y estimación de su profundidad con aprendizaje profundo para la conservación de carreteras.
CIENCIA ergo-sum, [S.l.], v. 32, mar. 2025.
ISSN 2395-8782.
Disponible en: <https://cienciaergosum.uaemex.mx/article/view/22933>. Fecha de acceso: 20 jul. 2026
doi: https://doi.org/10.30878/ces.v32n0a37.
Sección
Ciencias exactas y aplicadas
Esta obra está bajo licencia internacional Creative Commons Reconocimiento-NoComercial-SinObrasDerivadas 4.0.
Citas
Cui, Y., Chen, R., Chu, W., Chen, L., Tian, D., Li, Y., & Cao, D. (2021). Deep learning for image and point
cloud fusion in autonomous driving: A review. IEEE Transactions on Intelligent Transportation Systems, 23 (2), 722-739.
De Blasiis, M. R., Di Benedetto, A., & Fiani, M. (2020). Mobile laser scanning data for the evaluation of
pavement surface distress. Remote Sensing, 12 (6), 942.
Roboflow. (2022). (Version 1.0) [Software]. https://roboflow.com.computer vision.
Elamin, A., & El-Rabbany, A. (2023). UAV-Based Image and LiDAR Fusion for Pavement Crack Segmentation. Sensors, 23(23), 9315.
Fischler, M. A., & Bolles, R. C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6), 381-395.
Guan, J., Yang, X., Ding, L., Cheng, X., Lee, V. C., & Jin, C. (2021). Automated pixel-level pavement distress detection based on stereo vision and deep learning. Automation in Construction, 129, 103788.
Han, H., Deng, H., Dong, Q., Gu, X., Zhang, T., & Wang, Y. (2021). An advanced Otsu method integrated with edge detection and decision tree for crack detection in highway transportation infrastructure. Advances in Materials Science and Engineering, 2021(1), 9205509.
Jocher, G., Chaurasia, A., & Qiu, J. (2023). YOLO by Ultralytics (Version 8.0.0) [Computer software]. https://github.com/ultralytics/ultralytics
Kang, B. H., & Choi, S. I. (2017, July). Pothole detection system using 2D LiDAR and camera. In 2017 ninth international conference on ubiquitous and future networks (ICUFN) (pp. 744-746). IEEE.
Ma, D., Fang, H., Xue, B., Wang, F., Msekh, M. A., & Chan, C. L. (2020). Intelligent detection model based on a fully convolutional neural network for pavement cracks. CMES-Computer Modeling in Engineering & Sciences, 123 (3).
Mednis, A., Strazdins, G., Zviedris, R., Kanonirs, G., & Selavo, L. (2011, June). Real time pothole detection using android smartphones with accelerometers. In 2011 International conference on distributed computing in sensor systems and workshops (DCOSS) (pp. 1-6). IEEE.
Peralta-López, J. E., Morales-Viscaya, J. A., Lázaro-Mata, D., Villaseñor-Aguilar, M. J., Prado-Olivarez, J., Pérez-Pinal, F. J., ... & Barranco-Gutiérrez, A. I. (2023). Speed bump and pothole detection using deep neural network with images captured through zed camera. Applied Sciences, 13(14), 8349.
Ranganathan, D. G. (2021). A study to find facts behind preprocessing on deep learning algorithms. Journal of Innovative Image Processing, 3(1), 66-74.
SICT (Secretaría de Infraestructura, Comunicaciones y Transporte). (2023). CSV. CONSERVACIÓN. CAR. Carreteras. EVALUACIÓN. Evaluación de pavimentos. 008. Determinación de los Deterioros Superficiales de los Pavimentos (DET). M·CSV·CAR·1·03·008/23. Gobierno de México. https://es.scribd.com/document/715449972/M-CSV-CAR-1-03-008-23#page=1
Wu, H., Yao, L., Xu, Z., Li, Y., Ao, X., Chen, Q. ..., & Meng, B. (2019). Road pothole extraction and safety evaluation by integration of point cloud and images derived from mobile mapping sensors. Advanced Engineering Informatics, 42, 100936.
Xu, W., Tang, Z., Zhou, J., & Ding, J. (2013, September). Pavement crack detection based on saliency and statistical features. In 2013 IEEE international conference on image processing (pp. 4093-4097). IEEE.
cloud fusion in autonomous driving: A review. IEEE Transactions on Intelligent Transportation Systems, 23 (2), 722-739.
De Blasiis, M. R., Di Benedetto, A., & Fiani, M. (2020). Mobile laser scanning data for the evaluation of
pavement surface distress. Remote Sensing, 12 (6), 942.
Roboflow. (2022). (Version 1.0) [Software]. https://roboflow.com.computer vision.
Elamin, A., & El-Rabbany, A. (2023). UAV-Based Image and LiDAR Fusion for Pavement Crack Segmentation. Sensors, 23(23), 9315.
Fischler, M. A., & Bolles, R. C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6), 381-395.
Guan, J., Yang, X., Ding, L., Cheng, X., Lee, V. C., & Jin, C. (2021). Automated pixel-level pavement distress detection based on stereo vision and deep learning. Automation in Construction, 129, 103788.
Han, H., Deng, H., Dong, Q., Gu, X., Zhang, T., & Wang, Y. (2021). An advanced Otsu method integrated with edge detection and decision tree for crack detection in highway transportation infrastructure. Advances in Materials Science and Engineering, 2021(1), 9205509.
Jocher, G., Chaurasia, A., & Qiu, J. (2023). YOLO by Ultralytics (Version 8.0.0) [Computer software]. https://github.com/ultralytics/ultralytics
Kang, B. H., & Choi, S. I. (2017, July). Pothole detection system using 2D LiDAR and camera. In 2017 ninth international conference on ubiquitous and future networks (ICUFN) (pp. 744-746). IEEE.
Ma, D., Fang, H., Xue, B., Wang, F., Msekh, M. A., & Chan, C. L. (2020). Intelligent detection model based on a fully convolutional neural network for pavement cracks. CMES-Computer Modeling in Engineering & Sciences, 123 (3).
Mednis, A., Strazdins, G., Zviedris, R., Kanonirs, G., & Selavo, L. (2011, June). Real time pothole detection using android smartphones with accelerometers. In 2011 International conference on distributed computing in sensor systems and workshops (DCOSS) (pp. 1-6). IEEE.
Peralta-López, J. E., Morales-Viscaya, J. A., Lázaro-Mata, D., Villaseñor-Aguilar, M. J., Prado-Olivarez, J., Pérez-Pinal, F. J., ... & Barranco-Gutiérrez, A. I. (2023). Speed bump and pothole detection using deep neural network with images captured through zed camera. Applied Sciences, 13(14), 8349.
Ranganathan, D. G. (2021). A study to find facts behind preprocessing on deep learning algorithms. Journal of Innovative Image Processing, 3(1), 66-74.
SICT (Secretaría de Infraestructura, Comunicaciones y Transporte). (2023). CSV. CONSERVACIÓN. CAR. Carreteras. EVALUACIÓN. Evaluación de pavimentos. 008. Determinación de los Deterioros Superficiales de los Pavimentos (DET). M·CSV·CAR·1·03·008/23. Gobierno de México. https://es.scribd.com/document/715449972/M-CSV-CAR-1-03-008-23#page=1
Wu, H., Yao, L., Xu, Z., Li, Y., Ao, X., Chen, Q. ..., & Meng, B. (2019). Road pothole extraction and safety evaluation by integration of point cloud and images derived from mobile mapping sensors. Advanced Engineering Informatics, 42, 100936.
Xu, W., Tang, Z., Zhou, J., & Ding, J. (2013, September). Pavement crack detection based on saliency and statistical features. In 2013 IEEE international conference on image processing (pp. 4093-4097). IEEE.