To reduce the false detection rate of vehicle targets caused by occlusion, an improved method of vehicle detection in different traffic scenarios based on an improved YOLO v5 network is proposed. The proposed method uses the Flip-Mosaic algorithm to enhance the network’s perception of small targets. A multi-type vehicle target dataset collected in different scenarios was set up. The detection model was trained based on the dataset. The experimental results showed that the Flip-Mosaic data enhancement algorithm can improve the accuracy of vehicle detection and reduce the false detection rate.

Roadside light detection and ranging (LiDAR) is an emerging traffic data collection device and has recently been deployed in different transportation areas. The current data processing algorithms for roadside LiDAR are usually developed assuming normal weather conditions. Adverse weather conditions, such as windy and snowy conditions, could be challenges for data processing. This paper examines the performance of the state-of-the-art data processing algorithms developed for roadside LiDAR under adverse weather and then composed an improved background filtering and object clustering method in order to process the roadside LiDAR data, which was proven to perform better under windy and snowy weather. The testing results showed that the accuracy of the background filtering and point clustering was greatly improved compared to the state-of-the-art methods. With this new approach, vehicles can be identified with relatively high accuracy under windy and snowy weather.

Tracking road users with high resolution is important for connected vehicles. Due to the complicated environments, tracking objects with a single sensor could not meet the requirements of high-resolution trajectories due to occlusions. How to acquire accurate and complete trajectories based on multisource data is a major challenge for researchers and engineers. This article developed a novel tracking method based on the fusion of roadside light detection and ranging (LiDAR) and camera. According to the relationship between the number of points and distance, the adaptive weight coefficient related to 3-D trajectory information was determined. The performance of the proposed method was evaluated at five selected sites. The proposed tracking method had high performance in terms of speed calculation, tracking range, the rate of object loss, and the repairing rate of disconnected trajectories. The proposed method can benefit many transportation areas, such as traffic volume counting, vehicle speed tracking, and traffic safety analysis.

Trajectory data has gained increasing attention in the transportation industry due to its capability of providing valuable spatiotemporal information. Recent advancements have introduced a new type of multi-model all-traffic trajectory data which provides high-frequency trajectories of various road users, including vehicles, pedestrians, and bicyclists. This data offers enhanced accuracy, higher frequency, and full detection penetration, making it ideal for microscopic traffic analysis. In this study, we compare and evaluate trajectory data collected from two prevalent roadside sensors: LiDAR and camera (computer vision). The comparison is conducted at the same intersection and over the same time period. Our findings reveal that current LiDAR-based trajectory data exhibits a broader detection range and is less affected by poor lighting conditions compared to computer vision-based data. Both sensors demonstrate acceptable performance for volume counting during daylight hours, but LiDAR-based data maintains more consistent accuracy at night, particularly in pedestrian counting. Furthermore, our analysis demonstrates that, after applying smoothing techniques, both LiDAR and computer vision systems accurately measure vehicle speeds, while vision-based data show greater fluctuations in pedestrian speed measurements. Overall, this study provides insights into the advantages and disadvantages of LiDAR-based and computer vision-based trajectory data, serving as a valuable reference for researchers, engineers, and other trajectory data users in selecting the most appropriate sensor for their specific needs.

In transportation, LiDAR sensors have been primarily used in surveying and autonomous driving as a major onboard sensing device to detect field objects. Recently, with reduced price and increased demand from real-time and trajectory-level traffic detection, LiDAR technology sees great potential for becoming a mainstream means of infrastructure-based traffic detection other than only being used onboard. In addition to its many advanced features, LiDAR is much less impacted by illumination conditions compared to video sensors and significant in data processing speed, which makes it ideal for real-time traffic detection. The research team has conducted a wealth of studies to investigate the feasibility of installing LiDAR sensors at the roadside to obtain trajectories of automobiles and pedestrians at a frequency of 10 Hz. While our findings on how to process roadside LiDAR data have been presented in other literatures, this paper reveals our findings on another important issue regarding roadside LiDAR application – installation strategies to achieve the best performance. The authors first developed a theoretical approach based on the analysis of the built-in features of the applied LiDAR sensors and followed the results to install the sensors in our testbed. Then, experimental studies were conducted onsite and examined the theoretical results accordingly. As a result, a technical guidance for proper installation of LiDAR sensors at the roadside for the best real-time and trajectory-level traffic detection was produced. This study helps researchers and practitioners in better preparing for future deployment of roadside LiDAR sensors as part of the connected vehicles and infrastructures.

This study addresses the complex challenges associated with road traffic flow prediction and congestion management through the enhancement of the attention-based spatiotemporal graph convolutional network (ASTGCN) algorithm. Leveraging toll data and real-time traffic flow information from Orange County, California, the algorithm undergoes refinement to adeptly capture abrupt changes in road traffic dynamics and identify instances of acute congestion. The optimization of the graph structure is approached from both macro and micro perspectives, incorporating key factors such as road toll information, node connectivity, and spatial distances. A novel graph self-learning module is introduced to facilitate real-time adjustments, while an attention mechanism is seamlessly integrated into the spatiotemporal graph convolution module. The resultant model, termed AASTGNet, exhibits superior predictive accuracy compared to existing methodologies, with MAE, RMSE, and MAPE values of 8.6204, 14.0779, and 0.2402, respectively. This study emphasizes the importance of incorporating tolling schemes in road traffic flow prediction, addresses static graph structure limitations, and adapts dynamically to temporal variations and unexpected road events. The findings contribute to advancing the field of traffic prediction and congestion management, providing valuable insights for future research and practical applications.