Recently, deep learning (DL) methods have been intensively studied in pavement distress detection research. To build an effective yet robust DL-based distress detection model, both the training data and DL model structure need to be carefully prepared. This paper discusses the main influencing factors that affect the performance of DL models in pavement distress detection and aims to explore possible ways to improve the model performance. An open-source pavement image dataset and three promising object detection methods were selected for model development and evaluation. A series of experiments were conducted with different settings of model structures and data manipulation. According to the experiment results, selection of detection methods, data size, and annotation consistency have significant impact on detection performance. DL models YOLO and Faster R-CNN were found to yield the same level of performance, while CenterNet notably underperformed on the test dataset. Distress classes with a larger number of instances were found to be able to yield better performances. With the new annotation data carefully marked up and verified by experienced pavement raters, the accuracy score using the F1 index was found to be 0.84, which was a very sound improvement compared with the 0.7 of the original annotation. Data augmentation methods were found to be able to significantly improve the detection accuracy. Based on the experiment results, we believe the focus should be placed on the development of high-quality training datasets and thin object detection methods in the future.
Pavement surface distresses are analyzed by transportation agencies to determine section performance across their pavement networks. To efficiently collect and evaluate thousands of lane-miles, automated processes utilizing image-capturing techniques and detection algorithms are applied to perform these tasks. However, the precision of this novel technology often leads to inaccuracies that must be verified by pavement engineers. Developments in artificial intelligence and machine learning (AI/ML) can aid in the progress of more robust and precise detection algorithms. Deep learning models are efficient for visual distress identification of pavement. With the use of 2D/3D pavement images, surface distress analysis can help train models to efficiently detect and classify surface distresses that may be caused by traffic loading, weather, aging, and other environmental factors. The formation of these distresses is developing at a higher rate in coastal regions, where extreme weather phenomena are more frequent and intensive. This study aims to develop a YOLOv5 model with 2D/3D images collected in the states of Louisiana, Mississippi, and Texas in the U.S. to establish a library of data on pavement sections near the Gulf of Mexico. Images with a resolution of 4096 × 2048 are annotated by utilizing bounding boxes based on a class list of nine distress and non-distress objects. Along with emphasis on efforts to detect cracks in the presence of background noise on asphalt pavements, six scenarios for augmentation were made to evaluate the model’s performance based on flip probability in the horizontal and vertical directions. The YOLOv5 models are able to detect defined distresses consistently, with the highest mAP50 scores ranging from 0.437 to 0.462 throughout the training scenarios.
4 June 2024 in Transportation Research Record: Journal of the Transportation Research Board
Automated methods have been widely used by highway agencies to collect pavement condition data. However, there are still accuracy and precision issues associated with the reliability of the existing automated data collection methods. Therefore, this research aims to develop data quality check procedures to improve the reliability of automated pavement condition data for highway agencies. The study comprises three main components: identification of data quality check indexes; establishment of data quality thresholds; and implementation of data quality check procedures. Annual pavement rating data collected by a vendor using automated technologies and manual audit data from an independent third party were utilized to develop thresholds and test the procedures. Three districts, including two urban and one rural districts in Texas, were selected for the data quality check implementation. The results indicate that the proposed procedures, along with defined indexes and thresholds, efficiently identify pavements with data quality issues at both the section level and the county level. By pinpointing problematic areas, highway agencies can allocate resources for quick quality checks, enhancing the accuracy and precision of automated pavement condition data. The study can help highway agencies enhance the accuracy and precision of automated pavement condition data, ultimately leading to improvements in their pavement conditions.