Análisis comparativo de modelos yolo para la detección de defectos en infraestructura vehicular

Duber Martínez Torres; Jairo Antonio  Muñoz Arango

doi:10.22490/ECBTI.8803

Vol. 4 No. 2 (2023)

Published 2025-02-26

license

Artículos

Comparative analysis of yolo models for defect detection in vehicular infrastructure

DOI: https://doi.org/10.22490/ECBTI.8803

Duber Martínez Torres Universidad Nacional Abierta y a Distancia

Jairo Antonio Muñoz Arango Universidad Nacional Abierta y a Distancia

PDF (Spanish)

Abstract
References

YOLOv11 model with some of its earlier versions in the specific task of detecting road defects. The UDTIRI dataset, consisting of 1,000 labeled images, was used, and the lightweight versions of each model were evaluated under the same experimental conditions. The results show that YOLOv11 achieves a better balance between precision, recall, and efficiency. This study highlights the importance of future research to assess models with a larger number of parameters and to explore the impact of techniques such as data preprocessing and hyperparameter tuning, aiming to enhance defect detection and optimize the application of these models for monitoring road infrastructure.

keywords: Defect detection, YOLO models, Deep learning

Ayman, H., & Fakhr, M. W. (2023). Recent computer vision applications for pavement distress and condition assessment. Automation in Construction, 146, 104664.

Guo, S., Li, J., Feng, Y., Zhou, D., Zhang, D., Chen, C., ... & Fan, R. (2024). UDTIRI: An online open-source intelligent road inspection benchmark suite. IEEE Transactions on Intelligent Transportation Systems.

Jeong, D., & Kim, J. (2022). Road Damage Detection using YOLO with Image Tiling about Multi-source Images. Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022. https://doi.org/10.1109/BigData55660.2022.10020282

Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 779–788.

Ultralytics. (n.d.). YOLOv11 models. Ultralytics Documentation. https://docs.ultralytics.com/models/yolo11/

Wan, F., Sun, C., He, H., Lei, G., Xu, L., & Xiao, T. (2022). YOLO-LRDD: a lightweight method for road damage detection based on improved YOLOv5s. Eurasip Journal on Advances in Signal Processing, 2022(1). https://doi.org/10.1186/s13634-022-00931-x

license

How to Cite

Martínez Torres, D., & Muñoz Arango, J. A. (2025). Comparative analysis of yolo models for defect detection in vehicular infrastructure. Documentos De Trabajo ECBTI, 4(2). https://doi.org/10.22490/ECBTI.8803

Download Citation

Almétricas

Metrics

File downloads