XLXiaohua Luo

Xiaohua Luo

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Xiaohua Luo has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Evaluation of Deep Learning Strategies Using Two Different Image Data Sets for Automated Pavement Distress Detection Methodology

    by Yongsheng Bai, Feng Wang, Haitao Gong, Xiaohua Luo

    This paper investigates strategies to enhance the performance of deep learning models in pavement distress detection by utilizing two distinct datasets collected and annotated from different sources (vendors). The datasets consist of two- and three-dimensional images scanned from asphalt/concrete pavements and manually labeled for multiple surface distresses. Despite using the same base model to train individually, the performance of new models varies between the two datasets for the same pavement type. It remains a question whether transfer learning, knowledge distillation, or data merging will improve weaker models by leveraging stronger ones and increase the models’ robustness across different data sources. Experiments are conducted using these strategies to assess their applicability for single-source data (e.g., from a single vendor) and their generalization for multiple sources (e.g., from two or more vendors). This paper bridges a knowledge gap by qualitatively and quantitatively evaluating the effects of these strategies on current pavement distress detection practices using image data. Optimal approaches, such as fine-tuning or data merging, are recommended for various use cases aimed at real applications.

  • Open Access

    A Multi-Resolution Attention U-Net for Pavement Distress Segmentation in 3D Images: Architecture and Data-Driven Insights

    by Haitao Gong, Jueqiang Tao, Xiaohua Luo, Feng Wang

    High-resolution 3D pavement images have become a valuable data source for automated surface distress detection and assessment. However, accurately identifying and segmenting cracks from pavement images remains challenging, due to factors such as low contrast and hair-like thinness. This study investigates key factors affecting segmentation performance and proposes a novel deep learning architecture designed to enhance segmentation robustness under these challenging conditions. The proposed model integrates a multi-resolution feature extraction stream with gated attention mechanisms to improve spatial awareness and selectively fuse information across feature levels. Our extensive experiments on a 3D pavement dataset demonstrated that the proposed method outperformed several state-of-the-art architectures, including FCN, U-Net, DeepLab, DeepCrack, and CrackFormer. Compared with U-Net, it improved F1 from 0.733 to 0.780. The gains were most pronounced on thin cracks, with F1 from 0.531 to 0.626. Our paired t-tests across folds showed the method is statistically better than U-Net and DeepCrack on Recall, IoU, Dice, and F1. These findings highlight the effectiveness of the attention-guided, multi-scale feature fusion method for robust crack segmentation using 3D pavement data.


  • Enhancing Reliability in Automated Pavement Condition Data with a Data Quality Check Approach for Highway Agencies

    by Xiaohua Luo, Jueqiang Tao, Feng Wang, Ajmain Faieq, Haitao Gong, Feng Hong

    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.


  • Automated Pavement Crack Detection with Deep Learning Methods: What Are the Main Factors and How to Improve the Performance?

    by Haitao Gong, Jelena Tešić, Jueqiang Tao, Xiaohua Luo, Feng Wang

    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.


  • Improving Data Quality of Automated Pavement Condition Data Collection: Summary of State of the Practices of Transportation Agencies and Views of Professionals

    by Xiaohua Luo, Haitao Gong, Jueqiang Tao, Feng Wang, Jana Minifie, Xin Qiu

    Automated or semi-automated pavement condition data collection is replacing manual data collection in many state and local highway agencies due to its advantages of reducing labor, time, and cost. However, the practical experience of highway agencies indicates that there are still data quality issues with the pavement condition data collected using existing image and sensor-based data collection technologies. This study aims to investigate the implementation experiences and issues of automated or semi-automated pavement condition surveys. An online questionnaire survey was conducted, along with scheduled virtual/phone interviews to gather information from government, industry, and academia about the state of the practice and state of the art. Open questions about the data quality and quality control & quality assurance (QC/QA) were used to receive first-hand inputs from highway agencies and pavement experts. The study has compiled the following observations: (1) Highway agencies urgently need a uniform data collection protocol for automated data collection; (2) the current QA requires too much human intervention; (3) cost ($100–$200 per mile) is a significant burden for state and local agencies; (4) the main issues regarding data quality are data inconsistencies and discrepancies; (5) agencies expect a greater accuracy once the image processing algorithms are improved using artificial intelligence technologies; and (6) existing automated data collection methods are not available for project-level data collection.


  • Factor analysis of maintenance decisions for warranty pavement projects using mixed-effects logistic regression

    by Xiaohua Luo, Feng Wang, Ningning Wang, Xin Qiu, Farshad Amini, Jueqiang Tao

    Since its inception in 2000, Mississippi’s pavement warranty programme has been used to manage the maintenance activities of the warranty pavement projects. To determine whether a specific maintenance treatment is required on a warranty pavement section, distress measurements are taken and compared against warranty distress thresholds for each distress type. Then, the decisions of what maintenance treatments and scopes should be applied are made by following the warranty specifications. This study aims to identify factors that influence past maintenance decisions and predict future maintenance needs for warranty projects based on past decisions. Statistical methods were employed to identify the relationship between the maintenance decisions and relevant factors based on the historical data of the warranty projects. Moreover, logistic regressions were performed to develop a comprehensive maintenance decision-making prediction model for the warranty pavements. The analysis results showed that the distress measurements at low and medium severity levels in numerical variables and project location and distress type in categorical variables have stronger effects than the others on decisions. The mixed-effects logistic regression model could provide a high accuracy in predicting the remedial actions, which could further provide a trend prediction for the maintenance decision of a warranty pavement section.


  • Evaluation of Warranty and Nonwarranty Pavement Performance Using Survival Analysis

    by Xiaohua Luo, Feng Wang, Ningning Wang, Xin Qiu, Jueqiang Tao

    Pavement warranties are an innovative contracting procedure to protect investment in pavement construction and maintenance. The Mississippi Department of Transportation (MDOT) has managed its pavement warranty program since 2000, and there have been questions regarding the effectiveness of the pavement warranty program in Mississippi and in other states as well. Therefore, in this study, the nonparametric survival analysis method was employed to evaluate the performance of the warranty versus nonwarranty pavements. Asphalt pavement distress data retrieved from MDOT’s pavement management system were used to compute the survival probabilities of warranty and nonwarranty pavements with similar ages of service time. The results showed that the survival probabilities of the warranty pavements were significantly higher than those of nonwarranty pavements, indicating the superior performance of the warranty pavements in Mississippi. This study has provided a practical framework to process field-surveyed pavement distress data to evaluate the effectiveness of a pavement warranty program.