A Method for Surveying Road Pavement Distress Based on Front-View Image Data Using a Lightweight Segmentation Approach

Abstract

The utilization of low-cost video data is becoming more prevalent in pavement surveys to meet the increasing demand for timely distress detection and repair. Semantic segmentation algorithms can effectively segment pavement features and distresses simultaneously. Previous studies on pavement distress segmentation have primarily focused on cracks, and most multiobjective segmentation algorithms are not accurate or efficient. This paper presents a new method for pavement segmentation using a lightweight network segmentation model that employs DeepLabV3+ with MobileNetV2 as the backbone and a convolution block attention module to extract effective information in the encoder. The authors constructed a self-created data set called ChongQing University Pavement management (CQUPM), which includes five pavement features and six types of distress. Based on the CQUPM data set and a publicly available data set, RTK, the proposed model demonstrates superior accuracy and complexity compared to DeepLabv3+, U-Net, and Segformer-b3. Its lightweight nature is particularly noteworthy, with a parameter size of only about 1/10 to 1/4 that of other models based on the same data set. The case analysis highlights the exceptional performance of the proposed model, especially in scenarios where multiple types of pavement distress overlap. Furthermore, the model excels in edge segmentation and shows good generalization performance, indicating strong potential for practical applications. Maintenance management organizations at the grassroots level, in certain regions or serving specific projects, often face significant daily workloads. Routine survey work is primarily reliant on manual labor due to the high acquisition and operating costs of detection equipment. The segmentation model, trained on a small data set constructed from front-view images, can complete the survey of 2–3 lanes at a time. This model enables the detection of pavement type, pavement marking, and distress information. The model’s excellent generalization capabilities and the small data set lower the technical threshold of the application. This approach can be applied to other transportation infrastructures to address similar management problems. By using low-cost video recording devices to capture video data and quickly construct small data sets, training, and applications based on semantic segmentation techniques, problems can be identified in a timely manner without relying on human labor. This method has strong potential for replication.