Identification of failures in flexible pavement using Machine Learning, Cajamarca 2022

Dagoberto G.L.K.J.; del Rosario Q.M.L.K.; Jaime R.C.Y.; Zarela Q.P.V.; Augusto M.Z.C. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2023)

Resumen

For many years, fault detection in flexible pavements has been carried out using traditional methods such as PCI, VIZIR, and visual observation. However, recent technologies such as artificial intelligence (AI) have been developed due to their efficiency and accuracy, using deep learning techniques related to image processing to achieve object detection and analysis. The objective of the research is to use AI through the Yolov5 software to detect and analyze faults in the pavement of the Southern Bypass, in the stretch between Óvalo Musical (Jr. Atahualpa) and Avenida Industrial. The study has an applicative and experimental scope and design, with a non-probabilistic sample based on the two most common types of faults in flexible pavements: alligator cracking and fissures.

Instituciones: Universidad Privada del Norte