Cracks are important indicators of pavement structural and operational conditions. Early pavement crack detection and treatments can help extend pavement service life, reduce fuel consumption, and improve safety and ride quality. Pavement distress surveys have traditionally been performed manually by visually inspecting the roads, which is labor-intensive and time-consuming. Therefore, computer-vision-based automated crack detection has great practical significance in pavement maintenance and traffic safety. Traditional image processing techniques are sensitive to noise in images and are thus likely to miss detecting some cracks due to the crack texture variety, complex lighting conditions, and various similar but irrelevant objects on the road. This paper adopts and enhances DeepLabv3+, a popular deep learning framework for semantic image segmentation, for road pavement crack detection. We propose a multi-scale attention module in the decoder of DeepLabv3+ to generate an attention mask and dynamically assign weights between high-level and low-level feature maps. Compared with fixed weights across different features, the dynamic weights strategy can assign more reasonable weights to different feature maps. Ablation experiments show that the attention mask can effectively help the model better combine multi-scale features and generate more accurate pavement crack segmentation results. The proposed method achieves state-of-the-art results on three benchmarks, including Crack500, DeepCrack, and FMA (Fitchburg Municipal Airport) datasets. We further test it on pavement crack images captured by smartphones, and the results show that it provides a viable approach to road pavement crack segmentation in practice with excellent performance.

As a key area of traffic safety research, crash severity modelling has attracted tremendous attention. Recently, there has been growing interest in applying machine learning (ML) methods in this area. However, the lessons and experience learned so far have not been systematically documented and summarised. This is the first article that surveys studies on ML applications in crash severity modelling and has the following major contributions: (1) it provides a comprehensive and critical review of current research efforts; (2) it summarises the successful experience and main challenges (e.g. data and methodology); and (3) it identifies promising research opportunities towards accurate and reliable crash severity modelling and results interpretation. The review results suggest that imbalanced data remains a major issue. Under- and over-samplings are often used to balance crash severity data despite their limitations. Some studies use local sensitivity analysis (LSA) to interpret ML modelling results but ignore the strict assumptions of LSA and omit the joint effects of risk factors. Moreover, very few studies consider the accuracy and reliability of ML model evaluation metrics. Other issues include spatiotemporal correlations, causality, model transferability and heterogeneity. This paper concludes by providing suggestions on model selection and modification to address the identified issues and recommendations for future research. For example, employing advanced ML methods such as graph convolutional networks (GCN) to model spatiotemporal correlations; exploring innovative ways of applying ML methods; and leveraging new developments in ML (e.g. interpretable ML) to derive causal relationships and interpret modelling results.

In a connected vehicle environment, vehicles are able to communicate and exchange detailed information such as speed, acceleration, and position in real time. Such information exchange is important for improving traffic safety and mobility. This allows vehicles to collaborate with each other, which can significantly improve traffic operations particularly at intersections and freeway ramps. To assess the potential safety and mobility benefits of collaborative driving enabled by connected vehicle technologies, this study developed an optimization-based ramp control strategy and a simulation evaluation platform using VISSIM, MATLAB, and the Car2X module in VISSIM. The ramp control strategy is formulated as a constrained nonlinear optimization problem and solved by the MATLAB optimization toolbox. The optimization model provides individual vehicles with step-by-step control instructions in the ramp merging area. In addition to the optimization-based ramp control strategy, an empirical gradual speed limit control strategy is also formulated. These strategies are evaluated using the developed simulation platform in terms of average speed, average delay time, and throughput and are compared with a benchmark case with no control. The study results indicate that the proposed optimal control strategy can effectively coordinate merging vehicles at freeway on-ramps and substantially improve safety and mobility, especially when the freeway traffic is not oversaturated. The ramp control strategy can be further extended to improve traffic operations at bottlenecks caused by incidents, which cause approximately 25% of traffic congestion in the United States.