Lane information is an essential part of high-resolution micro-traffic data (HRMTD). Most of the lane detection algorithms for Light Detection and Ranging (LiDAR) are applied to high-density onboard LiDAR and airborne LiDAR, which cannot be used directly to process low-density roadside LiDAR data. In this article, an algorithm for lane detection applied to low-density roadside LiDAR is proposed, which includes three steps: ground recognition, lane marking point extraction, and pavement lane marking points clustering. Firstly, an improved algorithm for ground recognition is proposed to get normal ground points (NGPs). Then, the lane marking points are extracted from the no lane marking points based on the difference of laser intensity. Finally, we divided the ground within the range of LiDAR scanning into different stripes, and search the maximum linear density of the stripe to extract the lane markings. The average distance error (ADE) of lane detection results is less than 0.1m by fusing and comparing the test results with the aerial photographs. The proposed algorithm is also proved to be robust in multiple test locations and the results can be used to assist high-precision vehicle positioning in vehicle-to-infrastructure (V2I) cooperation application within the intelligent transportation system.

Further detection will increase traffic safety by perceiving unexpected traffic incidents earlier, allowing more time to make decisions and implement these decisions. Therefore, this article attempts to extend the detection range by using a low-channel roadside light detection and range sensor (LiDAR) sensor due to its low price and widespread employment in the future. The proposed method contains two major parts: static background construction and traffic objects detection. For static background construction, successive point cloud frames data were used to cover the most LiDAR scanning horizontal–vertical angle and obtain background information ultimately. Furthermore, the constructed static background was optimized to reduce the missing of the far range points and the occurrence of noise points. For vehicle and road user detection, the density-based spatial clustering of applications with noise (DBSCAN) algorithm was used to identify the near-range traffic objects. For far-range traffic objects detection, the trajectories of objects were extracted based on their moving direction and distance, and a fast Fourier transform (FFT) algorithm was used to filter the noise point and identify the vehicle and road user points. The experimental results show that the static background construction with the proposed method is more effective and uses fewer point cloud data. The average maximum detection range can be up to 100, 100, and 85 m for vehicles, cyclists, and pedestrians, respectively. The average precision (AP) and recall are 95.71% and 90.62%, respectively, which are better than the previous studies.

A light detection and ranging (LiDAR) sensor can obtain richer and more detailed traffic flow information than traditional traffic detectors, which could be valuable data input for various novel intelligent transportation applications. However, the point cloud generated by LiDAR scanning not only includes road user points but also other surrounding object points. It is necessary to remove the worthless points from the point cloud by using a suitable background filtering algorithm to accelerate the micro-level traffic data extraction. This paper presents a background point filtering algorithm using a slice-based projection filtering (SPF) method. First, a 3-D point cloud is projected to 2-D polar coordinates to reduce the point data dimensions and improve the processing efficiency. Then, the point cloud is classified into four categories in a slice unit: Valuable object points (VOPs), worthless object points (WOPs), abnormal ground points (AGPs), and normal ground points (NGPs). Based on the point cloud classification results, the traffic objects (pedestrians and vehicles) and their surrounding information can be easily identified from an individual frame of the point cloud. We proposed an artificial neuron network (ANN)-based model to improve the adaptability of the algorithm in dealing with the road gradient and LiDAR-employing inclination. The experimental results showed that the algorithm of this paper successfully extracted the valuable points, such as road users and curbstones. Compared to the random sample consensus (RANSAC) algorithm and 3-D density-statistic-filtering (3-D-DSF) algorithm, the proposed algorithm in this paper demonstrated better performance in terms of the run-time and background filtering accuracy.

More and more scholars are committed to light detection and ranging (LiDAR) as a roadside sensor to obtain traffic flow data. Filtering and clustering are common methods to extract pedestrians and vehicles from point clouds. This kind of method ignores the impact of environmental information on traffic. The segmentation process is a crucial part of detailed scene understanding, which could be especially helpful for locating, recognizing, and classifying objects in certain scenarios. However, there are few studies on the segmentation of low-channel (16 channels in this paper) roadside 3D LiDAR. This paper presents a novel segmentation (slice-based) method for point clouds of roadside LiDAR. The proposed method can be divided into two parts: the instance segmentation part and semantic segmentation part. The part of the instance segmentation of point cloud is based on the regional growth method, and we proposed a seed point generation method for low-channel LiDAR data. Furthermore, we optimized the instance segmentation effect under occlusion. The part of semantic segmentation of a point cloud is realized by classifying and labeling the objects obtained by instance segmentation. For labeling static objects, we represented and classified a certain object through the related features derived from its slices. For labeling moving objects, we proposed a recurrent neural network (RNN)-based model, of which the accuracy could be up to 98.7%. The result implies that the slice-based method can obtain a good segmentation effect and the slice has good potential for point cloud segmentation.

The ability to track multiple objects is crucial for roadside units to provide high-precision, trajectory-based traffic data, especially for connected vehicles that require complementary and long-range traffic information to improve road safety. Occlusion and continuous tracking are major challenges that have hindered the achievement of obtaining accurate, uninterrupted, and consistent multi-object tracking using roadside LiDAR technology. This paper presents a lane-level and full-cycle multi-vehicle tracking (MVT) method that utilizes low-channel roadside LiDAR. Firstly, a lane-level map was created by analyzing multiple frames of traffic object detection results. Then, we introduced an association method based on a search process and a microscopic motion model, while considering the lane-level map as a constraint. The search process aims to identify all previous tracks that might be linked to the target vehicle, while the microscopic motion model ensures finding a correct historical track for association. Additionally, a detection optimization approach utilizing the lane-level map was also proposed to enhance the tracking performance. Lastly, we created a new roadside tracking dataset for experimental studies by using Velodyne VLP-16 LiDAR sensors. The results showed that our algorithm achieved the highest accuracy and the strongest anti-occlusion performance compared to other popular algorithms such as SORT, OC-SORT, and ByteTrack. It is therefore a very suitable method for obtaining complete vehicle tracks using roadside LiDAR technology. The dataset and source code are available at https://github.com/moxigual/LMAT.

Roadside light detection and range sensor (LiDAR) is a way to enhance the perception capabilities of connected autonomous vehicles (CAVs) using the vehicle-to-infrastructure (V2I) cooperation system by providing complementary and beyond visual range information. However, occlusion remains challenging in roadside LiDAR required to be considered in deployment. Therefore, this article proposes a roadside LiDAR deployment optimization framework that considers the spatial-temporal occlusion arising from vehicles on urban streets. First, a pose deployment optimization model was constructed to maximize the utilization of the laser beams and minimize the spatial-temporal occlusion. Also, a network deployment problem was formulated considering the coverage intensity and cost performance with the pose deployment constraints. Then, a stagewise greedy algorithm combined with a particle swarm optimization (GA-PSO) algorithm was proposed and an elitist preservation genetic algorithm (EGA) was improved to optimize the roadside LiDAR layout and pose in the traffic network. Experiment results showed that the detection accuracy of the proposed method can reach 90.6%, outperforming current methods in different traffic conditions. Furthermore, the proposed method enables more complete target point cloud outlines capturing under various traffic and occlusion conditions.