Lane-Level and Full-Cycle Multivehicle Tracking Using Low-Channel Roadside LiDAR

Liu, Hui; Lin, Ciyun; Gong, Bowen; Liu, Hongchao

doi:10.1109/tim.2023.3289544

Cited by 4 publications

(3 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The next step is to perform object classification to classify the road users into pedestrians, bicycles, and vehicles [8,10]. Finally, the vehicle is tracked to monitor its trajectory and status [9,28]. However, the roadside object detection methods described above are mainly based on point cloud features, and their algorithms run slowly.…”

Section: Vehicle Detection and Tracking With Roadside Lidarmentioning

confidence: 99%

“…Currently, the most typical application of LiDAR is for detecting road and traffic information when installed in AVs. However, with ongoing advancements in vehicle-toinfrastructure (V2I) technology, there has been a surge in research focusing on the use of roadside LiDAR for vehicle detection and tracking [8][9][10]. Despite the great promise of these studies, most remain at the research stage, encountering challenges in real-time applications.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Vehicle Detection and Tracking with Roadside LiDAR Using Improved ResNet18 and the Hungarian Algorithm

Lin,

Sun,

et al. 2023

Sensors

View full text Add to dashboard Cite

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.

show abstract

Section: Vehicle Detection and Tracking With Roadside Lidarmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Vehicle Detection and Tracking with Roadside LiDAR Using Improved ResNet18 and the Hungarian Algorithm

Lin,

Sun,

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Lidar, especially the time-of-flight (TOF) variant, is widely used in autonomous vehicles to acquire point cloud data, aiding in object detection, localization, and map construction. Integrating lidar into roadside infrastructure is emerging, and some studies have been conducted using roadside lidar [1][2][3][4][5][6][7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Placement Method of Multiple Lidars for Roadside Infrastructure in Urban Environments

Kim,

Jo,

Yun

et al. 2023

Sensors

View full text Add to dashboard Cite

Sensors on autonomous vehicles have inherent physical constraints. To address these limitations, several studies have been conducted to enhance sensing capabilities by establishing wireless communication between infrastructure and autonomous vehicles. Various sensors are strategically positioned within the road infrastructure, providing essential sensory data to these vehicles. The primary challenge lies in sensor placement, as it necessitates identifying optimal locations that minimize blind spots while maximizing the sensor’s coverage area. Therefore, to solve this problem, a method for positioning multiple sensor systems in road infrastructure is proposed. By introducing a voxel grid, the problem is formulated as an optimization challenge, and a genetic algorithm is employed to find a solution. Experimental findings using lidar sensors are presented to demonstrate the efficacy of this proposed approach.

show abstract

Long-Distance and Real-Time Vehicle Detection on Highway Using RCF Network and PPHT Based on Ultraweak FBG Array

Liu,

Xie,

Yue

et al. 2024

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Lane-Level and Full-Cycle Multivehicle Tracking Using Low-Channel Roadside LiDAR

Cited by 4 publications

References 58 publications

Vehicle Detection and Tracking with Roadside LiDAR Using Improved ResNet18 and the Hungarian Algorithm

Vehicle Detection and Tracking with Roadside LiDAR Using Improved ResNet18 and the Hungarian Algorithm

Placement Method of Multiple Lidars for Roadside Infrastructure in Urban Environments

Long-Distance and Real-Time Vehicle Detection on Highway Using RCF Network and PPHT Based on Ultraweak FBG Array

Contact Info

Product

Resources

About