This paper discusses the latest YOLOv5 series detection model for pavement crack detection and is to find out an effective training and detection method. As a result, those models have become possible for pavement crack detection.
Object detection based on the deep learning model has achieved good results in many fields. In the face of many types of pavement cracks, it is difficult to design a general feature extraction model to extract pavement crack features, which leads to the poor effect of the automatic detection model based on machine learning. According to the pavement distress identification manual proposed by the Federal Highway Administration (FHWA), these categories have three different types of cracks, such as fatigue, longitudinal crack, and transverse cracks. The detection model based on machine learning needs artificial design of pavement crack characteristics. Traditional artificial detection has some problems, such as low efficiency and missing detection. If these cracks cannot be found and repaired in time, it will have a negative impact on the safe driving of vehicles. Severe weather and long-term driving of vehicles lead to various cracks on asphalt pavement.
