Application of artificial intelligence and object detection to determine failures in flexible pavements

According to the Association of Traffic Accident Victims (AVIACTRAN), on average there are 10 potholes per kilometer of flexible pavement in the city of Lima.This is due to the lack of timely road maintenance by government authorities, as they do not have a system that allows them to identify in real time the different pavement defects to make decisions.To address this problem, this paper proposes the use of the Cascade Trainer GUI algorithm and Python programming to determine defects in flexible pavements.The proposal consists of training the algorithm with images of different pavement defects using mobile phone cameras or drones for data collection and evaluation of the condition of the pavement.The implementation of the model provides a saving of 60% in the detection time of functional defects of the pavement compared to the traditional method.The methodology detects 5 types of defects (crocodile cracking, edge cracking, block cracking, potholes and wear) with an accuracy of 70%.This innovative approach offers an efficient and fast solution for management road infrastructure in urban and rural environments.