In this study, we introduce an innovative methodology for the detection of helmet usage violations among motorcyclists, integrating the YOLOv8 object detection algorithm with deep convolutional generative adversarial networks (DCGANs). The objective of this research is to enhance the precision of existing helmet violation detection techniques, which are typically reliant on manual inspection and susceptible to inaccuracies. The proposed methodology involves model training on an extensive dataset comprising both authentic and synthetic images, and demonstrates high accuracy in identifying helmet violations, including scenarios with multiple riders. Data augmentation, in conjunction with synthetic images produced by DCGANs, is utilized to expand the training data volume, particularly focusing on imbalanced classes, thereby facilitating superior model generalization to real-world circumstances. The stand-alone YOLOv8 model exhibited an F1 score of 0.91 for all classes at a confidence level of 0.617, whereas the DCGANs + YOLOv8 model demonstrated an F1 score of 0.96 for all classes at a reduced confidence level of 0.334. These findings highlight the potential of DCGANs in enhancing the accuracy of helmet rule violation detection, thus fostering safer motorcycling practices.

Several studies have developed pedestrian-vehicle interaction models. However, these studies failed to consider pedestrian distraction, which considerably influences the safety of these interactions. Utilizing data from two intersections in Vancouver, Canada, this research uses the Multi-agent Adversarial Inverse Reinforcement Learning (MA-AIRL) framework to make inferences about the behavioral dynamics of distracted and non-distracted pedestrians while interacting with vehicles. Results showed that distracted pedestrians maintained closer proximity to vehicles, moved at reduced speeds, and rarely yielded to oncoming vehicles. In addition, they rarely changed their interaction angles regardless of lateral proximity to vehicles, indicating that they mostly remain unaware of the surrounding environment and have decreased navigational efficiency. Conversely, non-distracted pedestrians executed safer maneuvers, kept greater distances from vehicles, yielded more frequently, and adjusted their speeds accordingly. For example, non-distracted pedestrian-vehicle interactions showed a 46.5% decrease in traffic conflicts severity (as measured by the average Time-to-Collision (TTC) values) and an average 30.2% increase in minimum distances when compared to distracted pedestrian-vehicle interactions. Vehicle drivers also demonstrated different behaviors in response to distracted pedestrians. They often opted to decelerate around distracted pedestrians, indicating recognition of potential risks. Furthermore, the MA-AIRL framework provided different results depending on the type of interactions. The performance of the distracted vehicle–pedestrian model was lower than the non-distracted model, suggesting that predicting non-distracted behavior might be relatively easier. These findings emphasize the importance of refining pedestrian simulation models to include the unique behavioral patterns from pedestrian distractions. This should assist in further examining the safety impacts of pedestrian distraction on the road environment.

Reliability analysis has been usedto account for uncertainties and evaluate the risk of highway geometric designs. Thisapproach estimates the probability of noncompliance,which represents the probability that a particulardesign does not meet the standard requirements. Despite the inherent uncertainty and the existence ofcorrelations between the different input design variables (e.g., perception-reaction time (PRT), vehicle speed (V), deceleration (a), and side friction factor (f_s )), the majority of the studies applying reliability analysis have ignored their correlations. As a result, the design inputs are often modeled in the reliability analysis using their means and standard deviations without considering their actual multivariate joint distributions. The objective of this paper is to quantify the influence of correlations between the different design input variables on reliability-based highway geometric design. The analysis is conducted for three modes of failure: insufficient sight distance, vehicle skidding, and vehicle rollover. Two types of vehicles are selected for the analysis: passenger cars and heavy trucks. Five case studies of the Sea-to-Sky Highway in British Columbia are considered. A series system reliability problem of the three modes of failureis used to account for the joint occurrence of the failure mechanisms. Results show that ignoring the correlations between input variablescan lead to inaccurateestimation of the probability of noncompliance for both the individual modes and the series system probability of failure.The effect of ignoring the correlationfor the vehicle skidding failure modeis more pronounced than the other modes. Moreover, the input variables' correlation significantly changes the multivariate distributions of the performance functions, leading to more extreme events in the failure domain. Therefore, it is of practical interest to direct efforts to quantify the influence of correlation inthe probabilistic geometric design.