Comparison of Major LiDAR Data-Driven Feature Extraction Methods for Autonomous Vehicles

Fernandes, Duarte; Névoa, Rafael; Silva, António José Linhares; Simões, Cláudia; Monteiro, João L.; Nováis, Paulo; Melo, Pedro O. S. Vaz de

doi:10.1007/978-3-030-45691-7_54

Cited by 4 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By emitting and receiving laser pulses and calculating the time-of-flight, Lidar can obtain the distances to the objects. Due to its high precision and wide range [ 7 ], Lidar is widely used in autonomous driving applications such as vehicle positioning, obstacle detection, and map generation [ 8 , 9 ]. However, for applications in the context of urban rail transit, such as train distance measurement, Lidars have certain drawbacks.…”

Section: Introductionmentioning

confidence: 99%

Train Distance Estimation for Virtual Coupling Based on Monocular Vision

Hao,

Tang,

Gao

2024

Sensors

View full text Add to dashboard Cite

By precisely controlling the distance between two train sets, virtual coupling (VC) enables flexible coupling and decoupling in urban rail transit. However, relying on train-to-train communication for obtaining the train distance can pose a safety risk in case of communication malfunctions. In this paper, a distance-estimation framework based on monocular vision is proposed. First, key structure features of the target train are extracted by an object-detection neural network, whose strategies include an additional detection head in the feature pyramid, labeling of object neighbor areas, and semantic filtering, which are utilized to improve the detection performance for small objects. Then, an optimization process based on multiple key structure features is implemented to estimate the distance between the two train sets in VC. For the validation and evaluation of the proposed framework, experiments were implemented on Beijing Subway Line 11. The results show that for train sets with distances between 20 m and 100 m, the proposed framework can achieve a distance estimation with an absolute error that is lower than 1 m and a relative error that is lower than 1.5%, which can be a reliable backup for communication-based VC operations.

show abstract

Section: Introductionmentioning

confidence: 99%

Train Distance Estimation for Virtual Coupling Based on Monocular Vision

Hao,

Tang,

Gao

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…The basic theory of Lidar is to calculate the distance to objects by emitting and receiving laser pulses and measuring their return time. Due to its high precision and extended range [10], Lidar is widely used in applications such as precise positioning, obstacle avoidance, map creation, and autonomous driving [11,12]. However, for distance estimation in turnout areas of urban rail transit, the train body cannot be detected robustly by on-board Lidar, and this poses significant threats to operation safety.…”

Section: Introductionmentioning

confidence: 99%

Train Distance Estimation in Turnout Area Based on Monocular Vision

Hao,

Tang,

Gao

2023

Sensors

View full text Add to dashboard Cite

Train distance estimation in a turnout area is an important task for the autonomous driving of urban railway transit, since this function can assist trains in sensing the positions of other trains within the turnout area and prevent potential collision accidents. However, because of large incident angles on object surfaces and far distances, Lidar or stereo vision cannot provide satisfactory precision for such scenarios. In this paper, we propose a method for train distance estimation in a turnout area based on monocular vision: firstly, the side windows of trains in turnout areas are detected by instance segmentation based on YOLOv8; secondly, the vertical directions, the upper edges and lower edges of side windows of the train are extracted by feature extraction; finally, the distance to the target train is calculated with an appropriated pinhole camera model. The proposed method is validated by practical data captured from Hong Kong Metro Tsuen Wan Line. A dataset of 2477 images is built to train the instance segmentation neural network, and the network is able to attain an MIoU of 92.43% and a MPA of 97.47% for segmentation. The accuracy of train distance estimation is then evaluated in four typical turnout area scenarios with ground truth data from on-board Lidar. The experiment results indicate that the proposed method achieves a mean RMSE of 0.9523 m for train distance estimation in four typical turnout area scenarios, which is sufficient for determining the occupancy of crossover in turnout areas.

show abstract

“…Graph Neural Network (GNN) is considered more effective in dealing with non-Euclidean data than CNN [1,2] . In a typical GNN pipeline, the raw pointcloud is first transformed into a graph, where key points are treated as vertices and the relationships between them as edges.…”

Section: Introductionmentioning

confidence: 99%

PointGAT: Graph attention networks for 3D object detection

Zhou

Wang

Liu

et al. 2022

Intell. and Converged Netw.

View full text Add to dashboard Cite

3D object detection is a critical technology in many applications, and among the various detection methods, pointcloud-based methods have been the most popular research topic in recent years. Since Graph Neural Network (GNN) is considered to be effective in dealing with pointclouds, in this work, we combined it with the attention mechanism and proposed a 3D object detection method named PointGAT. Our proposed PointGAT outperforms previous approaches on the KITTI test dataset. Experiments in real campus scenarios also demonstrate the potential of our method for further applications.

show abstract

Comparison of Major LiDAR Data-Driven Feature Extraction Methods for Autonomous Vehicles

Cited by 4 publications

References 9 publications

Train Distance Estimation for Virtual Coupling Based on Monocular Vision

Train Distance Estimation for Virtual Coupling Based on Monocular Vision

Train Distance Estimation in Turnout Area Based on Monocular Vision

PointGAT: Graph attention networks for 3D object detection

Contact Info

Product

Resources

About