By the end of the 2020s, full autonomy in autonomous driving may become commercially viable in certain regions. However, achieving Level 5 autonomy requires crucial collaborations between vehicles and infrastructure, necessitating high-speed data processing and low-latency capabilities. This paper introduces a vehicle tracking algorithm based on roadside LiDAR (light detection and ranging) infrastructure to reduce the latency to 100 ms without compromising the detection accuracy. We first develop a vehicle detection architecture based on ResNet18 that can more effectively detect vehicles at a full frame rate by improving the BEV mapping and the loss function of the optimizer. Then, we propose a new three-stage vehicle tracking algorithm. This algorithm enhances the Hungarian algorithm to better match objects detected in consecutive frames, while time–space logicality and trajectory similarity are proposed to address the short-term occlusion problem. Finally, the system is tested on static scenes in the KITTI dataset and the MATLAB/Simulink simulation dataset. The results show that the proposed framework outperforms other methods, with F1-scores of 96.97% and 98.58% for vehicle detection for the KITTI and MATLAB/Simulink datasets, respectively. For vehicle tracking, the MOTA are 88.12% and 90.56%, and the ID-F1 are 95.16% and 96.43%, which are better optimized than the traditional Hungarian algorithm. In particular, it has a significant improvement in calculation speed, which is important for real-time transportation applications.

Object detection is the fundamental task of vision-based sensors in environmental perception and sensing. To leverage the full potential of roadside 4D MMW radars, an innovative traffic detection method is proposed based on their distinctive data characteristics. First, velocity-based filtering and region of interest (ROI) extraction were employed to filter and associate point data by merging the point cloud frames to enhance the point relationship. Then, the Louvain algorithm was used to divide the graph into modularity by converting the point cloud data into graph structure and amplifying the differences with the Gaussian kernel function. Finally, a detection augmentation method is introduced to address the problems of over-clustering and under-clustering based on the object ID characteristics of 4D MMW radar data. The experimental results showed that the proposed method obtained the highest average precision and F1 score: 98.15% and 98.58%, respectively. In addition, the proposed method showcased the lowest over-clustering and under-clustering errors in various traffic scenarios compared with the other detection methods.

Pavement markings, as a crucial component of traffic guidance and safety facilities, are subject to degradation and abrasion after a period of service. To ensure traffic safety, retroreflectivity and diffuse illumination should be above the minimum thresholds and required to undergo inspection periodically. Therefore, an onboard light detection and ranging (LiDAR) and camera deployment optimization method is proposed for pavement marking distress detection to adapt to complex traffic conditions, such as shadows and changing light. First, LiDAR and camera sensors’ detection capability was assessed based on the sensors’ built-in features. Then, the LiDAR–camera deployment problem was mathematically formulated for pavement marking distress fusion detection. Finally, an improved red fox optimization (RFO) algorithm was developed to solve the deployment optimization problem by incorporating a multi-dimensional trap mechanism and an improved prey position update strategy. The experimental results illustrate that the proposed method achieves 5217 LiDAR points, which fall on a 0.58 m pavement marking per data frame for distress fusion detection, with a relative error of less than 7% between the mathematical calculation and the field test measurements. This empirical accuracy underscores the proposed method’s robustness in real-world scenarios, effectively mitigating the challenges posed by environmental interference.

Ground point identification and segmentation are fundamental to the light detection and ranging (LiDAR) based environment perception because they affect the accuracy and computational efficiency in the following data processing steps. A common problem that results in over- and under-segmentation occurs when the objects of interest are nonhomogeneous, and the sampling density is uneven. This study addresses this issue using grid- and homogeneity-based approaches. This work began with a combined conditional and voxel filtering approach to shrink the spatial range and reduce the amount of point-cloud data. The spatial range was then divided into a concentric circular grid to reduce the complexity of data processing. A dynamic threshold model was used to classify the cloud points to improve the accuracy of ground-point identification on uneven, broken, and sloped roads. Additionally, a point cloud homogeneity model was used to optimize the ground point identification results in areas with vegetation. The experimental study was conducted based on the data provided in the semantic KITTI dataset, wherein comprehensive comparisons were made with state-of-the-art algorithms. The average precision, recall, F1, and running time of the proposed method were 92.5%, 90.89%, 0.92, and 0.146 s, respectively, outperforming most of the selected models in balanced accuracy and computational efficiency.

Pavement marking retroreflectivity and diffuse illumination can degrade due to wear, cracks, and aging. To enable efficient, safe, and cost-effective inspections of pavement markings, and to ensure timely maintenance, regulate driver behavior, and enhance traffic safety, a method using an onboard low-channel LiDAR for detecting and classifying worn pavement marking was proposed. The process begins by applying coordinate transform, ground mapping, and sigmoid function filtering to the collected point cloud data to differentiate pavement markings from asphalt pavement. The sparse point cloud is then divided into grids, formatted into a matrix, and missing values are filled in to generate a grayscale map of the pavement marking matrix. Worn areas are segment using the OTSU and SRG algorithms and classified into four categories: penetrating, invasive, edge, and internal disease. Field tests shown that the method achieved average worn detection precision, recall, and F1-score of 0.8372, 0.8412, and 0.8389, respectively.