To address the critical need for collision risk warning at unsignalized intersections, this study proposes an advanced predictive system combining YOLOv8 for object detection, Deep SORT for tracking, and Bi-LSTM networks for trajectory prediction. To adapt YOLOv8 for complex intersection scenarios, several architectural enhancements were incorporated. The RepLayer module replaced the original C2f module in the backbone, integrating large-kernel depthwise separable convolution to better capture contextual information in cluttered environments. The GIoU loss function was introduced to improve bounding box regression accuracy, mitigating the issues related to missed or incorrect detections due to occlusion and overlapping objects. Furthermore, a Global Attention Mechanism (GAM) was implemented in the neck network to better learn both location and semantic information, while the ReContext gradient composition feature pyramid replaced the traditional FPN, enabling more effective multi-scale object detection. Additionally, the CSPNet structure in the neck was substituted with Res-CSP, enhancing feature fusion flexibility and improving detection performance in complex traffic conditions. For tracking, the Deep SORT algorithm was optimized with enhanced appearance feature extraction, reducing the identity switches caused by occlusions and ensuring the stable tracking of vehicles, pedestrians, and non-motorized vehicles. The Bi-LSTM model was employed for trajectory prediction, capturing long-range dependencies to provide accurate forecasting of future positions. The collision risk was quantified using the predictive collision risk area (PCRA) method, categorizing risks into three levels (danger, warning, and caution) based on the predicted overlaps in trajectories. In the experimental setup, the dataset used for training the model consisted of 30,000 images annotated with bounding boxes around vehicles, pedestrians, and non-motorized vehicles. Data augmentation techniques such as Mosaic, Random_perspective, Mixup, HSV adjustments, Flipud, and Fliplr were applied to enrich the dataset and improve model robustness. In real-world testing, the system was deployed as part of the G310 highway safety project, where it achieved a mean Average Precision (mAP) of over 90% for object detection. Over a one-month period, 120 warning events involving vehicles, pedestrians, and non-motorized vehicles were recorded. Manual verification of the warnings indicated a prediction accuracy of 97%, demonstrating the system’s reliability in identifying potential collisions and issuing timely warnings. This approach represents a significant advancement in enhancing safety at unsignalized intersections in urban traffic environments.

The merging area is one of the most accident-prone areas on highways. After an accident occurs, the risk will propagate along the main road over a certain range and time. Therefore, the study of the propagation mechanism of accident risk will help to quantify the driving risk in this region. An effective risk prediction model is important for improving traffic control measures in this specific area. In this study, simulation experiments were conducted in SUMO (Simulation of Urban Mobility) to obtain the accident and risk propagation data in merging areas. Firstly, the Gaussian plume model was optimized for the merging area situation to determine and divide the impact range of the accidents. Then, different accident scenarios in the merging area and downstream were simulated with different input flow rates to study the time and speed of risk propagation in the three-level affected areas. Finally, LSTM (long short-term memory) and RNN (recurrent neural network) models were built to predict the accident risk in the merging area. The results showed that the LSTM model had higher accuracy. This study provides an innovative insight into the propagation process of merging area accidents. It is of benefit to the development of post-accident control measures.

This study focuses on identifying accident-prone areas and analyzing the factors contributing to the distribution of traffic accidents near highway ramps. A combined method of kernel density estimation, spatial autocorrelation analysis, and multivariate logistic regression analysis helped to identify accident hotspots. Through data collection and analysis, the clustering characteristics of traffic accidents in the diversion and merging areas were identified. Four levels of accident-prone areas were divided according to the accident rates. The factors influencing the spatial distribution of accidents were analyzed. The results showed that traffic accidents in the diversion area were concentrated near the exit, but the accidents in merging areas had a wider range of distribution. The analysis of this phenomenon was conducted using the multinomial logit model results. The important factors of different accident-prone areas were clarified. The temperature, the accident lane, weather conditions, and the time of day had significant impacts on the spatial distribution of traffic accidents. The study’s findings provide an important decision-making basis for highway accident prevention management.