Un modelo de clasificación del estado del pavimento a partir de imágenes, tomas video y señales de GNSS
| dc.contributor.advisor | Fernández Gómez, Wilmar Darío | |
| dc.contributor.author | Espinel Gómez, Diego Fernando | |
| dc.contributor.orcid | Fernández Gómez, Wilmar Darío [0000-0001-6339-8050] | |
| dc.creator.email | espineldago@gmail.com | |
| dc.creator.id | 20192195003 | |
| dc.date.accessioned | 2026-05-15T18:00:29Z | |
| dc.date.available | 2026-05-15T18:00:29Z | |
| dc.date.created | 2026-05-05 | |
| dc.description | Los sistemas de mapeo móvil se utilizan ampliamente para la observación urbana. Mediante la integración de dispositivos electrónicos con diversos sensores (incluidos ópticos y térmicos), técnicas de visión artificial, algoritmos de IA y sistemas de posicionamiento GNSS, se pueden recopilar datos de los corredores viales urbanos. Esta investigación presenta una revisión de los métodos convencionales de mapeo móvil y propone un enfoque avanzado de visión artificial que aprovecha la IA para mejorar la precisión del mapeo. Se examinan críticamente las limitaciones y los desafíos de los métodos tradicionales, como los sistemas LIDAR montados en vehículos. El estudio destaca cómo la integración de la IA, en particular los algoritmos de aprendizaje profundo, ha mejorado significativamente la interpretación de datos y los procesos de toma de decisiones en la gestión de la infraestructura vial. Se realizó un experimento en la red vial de Bogotá utilizando un sistema de mapeo móvil equipado con sensores de video y dispositivos GNSS en un vehículo especialmente adaptado. Esta configuración facilitó la recopilación de grandes conjuntos de datos, que posteriormente se procesaron utilizando el algoritmo de IA YOLO para detectar y clasificar eficazmente las condiciones del pavimento. Los resultados del experimento subrayan la eficacia de combinar la tecnología de mapeo móvil, la programación y los algoritmos de IA para crear mapas detallados e identificar objetos clave en el entorno urbano. Se analizan las aplicaciones prácticas de esta tecnología, centrándose en la creación de mapas urbanos detallados según las directrices técnicas de las agencias viales responsables. Asimismo, se aborda la identificación de zonas de congestión vehicular y la evaluación del estado de la red vial. El uso de estos sistemas integrados de hardware y software proporciona una solución rápida y rentable para el estudio del estado de los corredores viales, tanto urbanos como rurales. | |
| dc.description.abstract | Mobile mapping systems are widely used for urban observation. By integrating electronic devices with various sensors (including optical and thermal), computer vision techniques, AI algorithms, and GNSS positioning systems, data from urban road corridors can be collected. This research presents a review of conventional mobile mapping methods and proposes an advanced computer vision approach that leverages AI to improve mapping accuracy. The limitations and challenges of traditional methods, such as vehicle-mounted LIDAR systems, are critically examined. The study highlights how AI integration, particularly deep learning algorithms, has significantly enhanced data interpretation and decision-making processes in road infrastructure management. An experiment was conducted on Bogotá's road network using a mobile mapping system equipped with video sensors and GNSS devices in a specially adapted vehicle. This setup facilitated the collection of large datasets, which were subsequently processed using the YOLO AI algorithm to effectively detect and classify road pavement conditions. The experiment's results underscore the effectiveness of combining mobile mapping technology, programming, and AI algorithms to create detailed maps and identify key objects in the urban environment. Practical applications of this technology are discussed, focusing on creating detailed urban maps under the technical guidelines of responsible road agencies. Additionally, the identification of traffic congestion zones and the evaluation of the road network's condition are addressed. The use of these integrated hardware and software systems provides a fast and cost-effective solution for studying the state of both urban and rural road corridors. | |
| dc.format.mimetype | ||
| dc.identifier.uri | http://hdl.handle.net/11349/101424 | |
| dc.language.iso | spa | |
| dc.publisher | Universidad Distrital Francisco José de Caldas | |
| dc.relation.references | Benavides López, J. A., & Barrera Vera, J. A. (2020). Evaluación de los sistemas de mapeo móvil (MMS) en la documentación gráfica del tholo de El Romeral (Conjunto Arqueológico Dólmenes de Antequera). Arqueología de la Arquitectura, 17, e095. https://doi.org/10.3989/arq.arqt.2020.004 | |
| dc.relation.references | Grešla, O., & Jašek, P. (2023). Measuring road structures using a mobile mapping system. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLVIII-5/W2, 43–48. https://doi.org/10.5194/isprs-archives-XLVIII-5-W2-2023- 43-2023 | |
| dc.relation.references | Ibragimov, E., Kim, Y., Lee, J. H., Cho, J., & Lee, J.-J. (2024). Automated pavement condition index assessment with deep learning and image analysis: An end-to-end approach. Sensors, 24(7), 2333. https://doi.org/10.3390/s24072333 | |
| dc.relation.references | Meta AI. (2023, April 5). Segment Anything: The first foundation model for image segmentation. Meta AI Blog. https://ai.facebook.com/blog/segment-anything-foundation-model-imagesegmentation/ | |
| dc.relation.references | Ministerio de Transporte & Instituto Nacional de Vías (INVÍAS). (2022). Metodología para la determinación y calificación del estado de la red vial. Instituto Nacional de Vías. https://www.invias.gov.co/index.php/normativa/politicas-y-lineamientos/servicios-alciudadano/proyectos-invias/red-nacional-de-carreteras/14618-metodologia-para-ladeterminacion-y-calificacion-del-estado-de-la-red-vial/file | |
| dc.relation.references | Naciones Unidas en Colombia. (s. f.). Objetivos de Desarrollo Sostenible (ODS). Recuperado de https://colombia.un.org/es/sdgs | |
| dc.relation.references | Nasrallah, A. A., Abdelfatah, M. A., Attia, M. I. E., & et al. (2024). Positioning and detection of rigid pavement cracks using GNSS data and image processing. Earth Science Informatics, 17, 1799-1807. https://doi.org/10.1007/s12145-024-01228-3 | |
| dc.relation.references | Pajuelo Zavala, G. L. (2021). Análisis comparativo del sistema de mapeo móvil inercial y los equipos GNSS/GPS utilizados en el inventario vial de rutas vecinales de la provincia de Cusco [Tesis de grado, Universidad Nacional Mayor de San Marcos]. Repositorio ALICIA – CONCYTEC. https://hdl.handle.net/20.500.12672/16427 | |
| dc.relation.references | PIARC (World Road Association). (2020). The use of big data for road condition monitoring: literature review and practical guidance. PIARC Technical Committee Reports. https://www.piarc.org/en/order-library/40731-enThe%20Use%20of%20Big%20Data%20for%20Road%20Condition%20Monitoring%20- %20Literature%20Review | |
| dc.relation.references | Qureshi, W. S., Power, D., Ullah, I., Mulry, B., Feighan, K., McKeever, S., & O’Sullivan, D. (2023). Deep learning framework for intelligent pavement condition rating: A direct classification approach for regional and local roads. Automation in Construction, 153, 104945. https://doi.org/10.1016/j.autcon.2023.104945 | |
| dc.relation.references | Sairam, N., Nagarajan, S., & Ornitz, S. (2016). Development of mobile mapping system for 3D road asset inventory. Sensors, 16(3), 367. https://doi.org/10.3390/s16030367 | |
| dc.relation.references | Sanabria Echeverry, D. Y., Porras Díaz, H., & Ortíz Ferreira, J. A. (2018). Tendencia mundial en tecnologías de sistemas de mapeo móvil implementadas con láser. Avances Investigación en Ingeniería, 15(1), 204–230. https://doi.org/10.18041/1794-4953/avances.1.1361 | |
| dc.relation.references | Zheng, L., Xiao, J., Wang, Y., Wu, W., Chen, Z., Yuan, D., & Jiang, W. (2024). Deep learningbased intelligent detection of pavement distress. Automation in Construction, 168, 105772. https://doi.org/10.1016/j.autcon.2024.105772 | |
| dc.relation.references | Chen, X., Ma, H., Wan, J., Li, B., & Xia, T. (2020). Multi-view 3D object detection network for autonomous driving. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1907–1915). | |
| dc.relation.references | El-Sheimy, N., Valeo, C., & Habib, A. (2005). Digital terrain modeling: Acquisition, manipulation, and applications. Artech House. | |
| dc.relation.references | García, P., Hernández, R., & López, D. (2022). Aplicaciones de inteligencia artificial en el mapeo móvil. Revista Colombiana de Ingeniería, 58(4), 233–245. | |
| dc.relation.references | González, J., & Rodríguez, M. (2021). Limitaciones de los métodos tradicionales de mapeo móvil. Revista de Ingeniería Urbana, 45(3), 123–135. | |
| dc.relation.references | Huang, G., Liu, Z., van der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2261–2269). | |
| dc.relation.references | Levinson, J., Montemerlo, M., & Thrun, S. (2011). Map-based precision vehicle localization in urban environments. In Robotics: Science and Systems. | |
| dc.relation.references | Liu, Z., Huang, G., & Wang, S. (2018). Advances in high-resolution sensors for mobile mapping systems. Journal of Spatial Science, 63(2), 207–221. | |
| dc.relation.references | Pérez, L., González, M., & Rodríguez, J. (2019). Challenges and opportunities in mobile mapping systems for urban infrastructure. International Journal of Urban Planning, 23(2), 145–162. | |
| dc.relation.references | Pérez, L., Sánchez, A., & Torres, F. (2019). Desafíos en el uso de GPS y LIDAR para el mapeo móvil. Journal of Urban Mapping, 34(2), 89–102. | |
| dc.relation.references | Redmon, J., & Farhadi, A. (2017). YOLO9000: Better, faster, stronger. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 7263–7271). | |
| dc.relation.references | Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, realtime object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 779–788). | |
| dc.relation.references | Schwarz, K. P., Chapman, M. A., Cannon, M. E., & Gong, P. (2010). An integrated INS/GPS approach to the georeferencing of remotely sensed data. Photogrammetric Engineering & Remote Sensing, 58(3), 323–328. | |
| dc.relation.references | Wang, Y., Zhang, L., & Zhang, Y. (2019). A comprehensive review on the integration of GNSS and vision systems. IEEE Transactions on Intelligent Transportation Systems, 20(3), 1012– 1025. | |
| dc.relation.references | Wu, Y., Huang, C., & Chan, K. (2018). Road pavement distress detection using deep learning. IEEE Transactions on Intelligent Transportation Systems, 19(2), 330–340. | |
| dc.relation.references | Xu, Z., Zhao, W., & Li, H. (2019). Interdisciplinary collaboration in the development of smart infrastructure systems. Journal of Civil Engineering and Management. | |
| dc.relation.references | Yang, L., Zhang, W., & Wu, Q. (2021). Thermal imaging for pavement condition assessment: A review. Journal of Infrastructure Systems. | |
| dc.relation.references | Zhang, X., Zhang, L., & Li, Y. (2020). Convolutional neural networks for pavement distress detection: A comparative study. Computers, Environment and Urban Systems. | |
| dc.relation.references | Bierhoff, J., Smith, A., & Doe, J. (2021). Geospatial data visualization with React. Springer. Chen, X., Zhang, Y., Liu, W., & Wang, J. (2022). Deep learning-based road infrastructure condition monitoring: A review. IEEE Transactions on Intelligent Transportation Systems, 23(4), 1234–1248. | |
| dc.relation.references | Geetha, A. S. (2025). YOLOv4: A breakthrough in real-time object detection. | |
| dc.relation.references | Géron, A. (2023). Hands-on full-stack web development with Python and Django. Packt Publishing. | |
| dc.relation.references | González, J., Ramírez, L., & Torres, M. (2020). Evaluación del impacto del deterioro vial en la seguridad vehicular. Revista de Ingeniería Civil, 45(2), 99–112. | |
| dc.relation.references | Jones, R., White, P., & Black, L. (2020). Efficient API development with Falcon. O’Reilly Media. | |
| dc.relation.references | Lu, K., Zhao, F., Xu, X., & Zhang, Y. (2023). An object detection algorithm combining selfattention and YOLOv4 in traffic scene. PLOS ONE, 18(5). | |
| dc.relation.references | Matsumoto, R. (2019). High-performance web APIs with Falcon. Python Software Foundation Journal, 12(2), 45–58. | |
| dc.relation.references | Momjian, B. (2022). PostgreSQL: Introduction and concepts. Addison-Wesley. | |
| dc.relation.references | Oyeniran, O., Adewusi, A., Adeleke, A. G., & Akwawa, L. (2024). Microservices architecture in cloud-native applications: Design patterns and scalability. Computer Science & IT Research Journal, 5(9), 2107–2124. | |
| dc.relation.references | Pivoto, D., Waquil, P. D., Talamini, E., Finocchio, C. P. S., & Corte, V. F. D. (2020). Scientific developments and technical challenges in smart and sustainable cities research. Journal of Cleaner Production, 276, 124034. | |
| dc.relation.references | Shin, H., Kim, D., & Park, J. (2023). Scalable microservices architecture for real-time road infrastructure monitoring. International Journal of Software Engineering, 32(1), 45–67. | |
| dc.relation.references | Silva, R., Pereira, F., & Oliveira, J. (2021). Challenges in urban road maintenance and automated inspection methods. Transportation Research Procedia, 54, 200–212. | |
| dc.relation.references | Wang, Y., Guan, Y., Liu, H., Jin, L., Li, X., Guo, B., & Zhang, Z. (2023). VV-YOLO: A vehicle view object detection model based on improved YOLOv4. Sensors, 23(7), 3385. | |
| dc.relation.references | Yepuri, V. K., Polamarasetty, V. K., Donthi, S., & Gondi, A. K. R. (2023). Containerization of a polyglot microservice application using Docker and Kubernetes. | |
| dc.relation.references | Zhang, Y., & Zhang, L. (2023). Detection of pavement cracks by deep learning models of transformer and UNet. | |
| dc.relation.references | Ziar, A., Ulfat, S., Serat, Z., & Armal, M. A. (2023). Cost-effectiveness analysis of design methods for rigid and flexible pavement: A case study of urban road. Archives of Advanced Engineering Science, 2(3), 134–141. | |
| dc.relation.references | Banco Interamericano de Desarrollo. (2025). Pavimentados. https://knowledge.iadb.org/en/codedevelopment/open-source-solutions/pavimentados | |
| dc.relation.references | Binagekar, K., & Pai, A. (2024). Real-time structural crack detection in buildings using YOLOv3 and autonomous unmanned aerial systems. International Journal of System Assurance Engineering and Management, 15(5), 1874-1887. https://doi.org/10.1007/s13198-023-02192-9 | |
| dc.relation.references | Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2023). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv:2004.10934. | |
| dc.relation.references | Chen, Z., Li, Y., & Chen, M. (2023). Siamese neural networks for visual similarity and defect detection. Pattern Recognition Letters, 168, 47–56. | |
| dc.relation.references | García-Peña, C., Navarro, M., & Uribe, S. (2023). Automated asset mapping with GNSS and mobile video data. Remote Sensing, 15(6), 1543. | |
| dc.relation.references | Gupta, R., Soni, R., & Patel, M. (2023). Annotation tools for deep learning: A comparative study of open-source platforms. International Journal of Computer Vision and Image Processing. | |
| dc.relation.references | Jiang, Y. (2024). Road damage detection and classification using deep neural networks. Discover Applied Sciences, 6, 421. https://doi.org/10.1007/s42452-024-06129-0 | |
| dc.relation.references | Jocher, G., Chaurasia, A., Qiu, J., & Stoken, A. (2025). YOLO by Ultralytics [Repositorio GitHub]. https://github.com/ultralytics/ultralytics | |
| dc.relation.references | Kang, S., Jeong, H., & Lee, J. (2023). Efficient image sampling for smart road assessment. IEEE Access, 11, 95432–95445. | |
| dc.relation.references | Li, S., Zhu, Z., Sun, H., Ning, X., Dai, G., & Hu, Y. (2024). Toward high-accuracy and real-time two-stage small object detection on FPGA. IEEE Transactions on Circuits and Systems for Video Technology, 34(9), 8053–8066. https://doi.org/10.1109/TCSVT.2024.3385121 | |
| dc.relation.references | Lin, X., Wang, J., & Zhao, H. (2024). Improving object detection performance using hybrid data augmentation and YOLOv8. Journal of Artificial Intelligence Research. | |
| dc.relation.references | Liu, H., Zhang, Y., & Chen, W. (2024). YOLOv8-DGS: An improved crack detection algorithm based on depthwise separable convolution. PLOS ONE. https://doi.org/10.1371/journal.pone.0324512 | |
| dc.relation.references | Meimetis, D., Daramouskas, I., Patrinopoulou, N., Lappas, V., & Kostopoulos, V. (2025). Comparative analysis of object detection models for edge devices in UAV swarms. Machines, 13(8), 684. https://doi.org/10.3390/machines13080684 | |
| dc.relation.references | Narlan, A., & Widiyanto, A. (2023). Automated pavement defect detection using YOLOv8 object detection algorithm. International Journal of Applied Artificial Intelligence, 2(1), 12–22. | |
| dc.relation.references | Redmon, J., & Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv:1804.02767. | |
| dc.relation.references | Souza, M., Ramírez, J., & Villalobos, P. (2025). Defect detection using YOLOv8 for determining the condition of asphalt pavements. Revista ALCONPAT, 15(1), 1–12. https://doi.org/10.21041/ra.v15i1.781 | |
| dc.relation.references | Wang, H., Liu, T., & Chen, L. (2024). Real-time applications of lightweight object detection models in smart cities. Sensors, 24(3), 1105. | |
| dc.relation.references | Wang, X., Sun, J., & Li, Z. (2024). Improved YOLOv8s model for real-time pavement defect detection. Scientific Reports, 14(1), 1–14. https://doi.org/10.1038/s41598-024-67953-3 | |
| dc.relation.references | Yurdakul, S., & Tasdemir, S. (2025). Improved YOLOv8-seg model with RGB-D data for pavement crack detection. arXiv:2505.04207. | |
| dc.relation.references | Zhang, L., He, J., & Wu, Q. (2024). MS-YOLOv8: A multi-scale attention enhanced YOLOv8 for road defect detection. Sensors, 24(14), 4569. https://doi.org/10.3390/s24144569 | |
| dc.relation.references | Zhang, M., Xu, K., & Ren, Y. (2023). Spatial association of urban features using PostGIS. GeoInformatica, 27(2), 201–219. | |
| dc.relation.references | Zhang, Y., Huang, W., & Li, Z. (2023). Data quality in object detection: A comprehensive review. IEEE Transactions on Pattern Analysis and Machine Intelligence. | |
| dc.relation.references | Zhu, Y., Wang, L., & Huang, R. (2024). Visual validation techniques in automated road inspection. Computer Vision and Image Understanding, 230, 103832. | |
| dc.relation.references | Zuo, H., Liang, K., & Tang, S. (2025). Crack segmentation and mechanical dimension measurement using an improved YOLOv8 with attention mechanisms. arXiv:2504.13208. | |
| dc.rights.acceso | Restringido (Solo Referencia) | |
| dc.rights.accessrights | RestrictedAccess | |
| dc.subject | Mapeo móvil | |
| dc.subject | Inteligencia artificial | |
| dc.subject | Estado del pavimento | |
| dc.subject | Detección de daños en el pavimento | |
| dc.subject | YOLO | |
| dc.subject.keyword | Mobile Mapping | |
| dc.subject.keyword | Artificial Intelligence | |
| dc.subject.keyword | Pavement condition | |
| dc.subject.keyword | Pavement distresses detection | |
| dc.subject.keyword | YOLO | |
| dc.subject.lemb | Maestría en Ciencias de la Información y las Comunicaciones -- Tesis y disertacones académicas | |
| dc.subject.lemb | Pavimentos — Evaluación del estado | |
| dc.subject.lemb | Procesamiento digital de imágenes — Aplicaciones en ingeniería | |
| dc.subject.lemb | Infraestructura vial — Monitoreo y control | |
| dc.title | Un modelo de clasificación del estado del pavimento a partir de imágenes, tomas video y señales de GNSS | |
| dc.title.titleenglish | A pavement condition classification model based on images, video recordings, and GNSS signals | |
| dc.type | masterThesis | |
| dc.type.coar | http://purl.org/coar/resource_type/c_bdcc | |
| dc.type.degree | Investigación-Innovación | |
| dc.type.driver | info:eu-repo/semantics/masterThesis |
Archivos
Bloque de licencias
1 - 1 de 1
Cargando...
- Nombre:
- license.txt
- Tamaño:
- 7 KB
- Formato:
- Item-specific license agreed upon to submission
- Descripción: