An Automated Rail Extraction Framework for Low-Density LiDAR Data Without Sensor Configuration Information

Ren, Yihao; Ai, Chengbo; Lu, Pan; Dai, Zhenyu; Wang, Hao

doi:10.1109/jsen.2022.3177698

Cited by 8 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers have proposed different approaches to achieve this extraction, used density cluster in raw data to obtain the maximum connected region as track bed, 17 used installation parameters to directly cut out this area. 4 However, these treatments are not robust in actual processing. Compared to the aforementioned methods, LPR algorithm offers a more efficient processing approach by solely relying on the rail height parameter, h. This reduces the dependence on intricate installation parameters and allows for adaptive adjustments based on the data from each frame.…”

Section: Methodsmentioning

confidence: 99%

“…The point cluster C also contains a small amount of clustered free noise data, as depicted in C1 and C2 in Figure 5. In other extraction methods, 4 using density cluster purely cannot gather the discrete rail point belonged to the same rail into one point cluster. This is because point cloud collected by LiDAR is sensitive to occlusion.…”

Section: Methodsmentioning

confidence: 99%

“…To evaluate the overall performance of the proposed rail extraction algorithm based on QSHD rail descriptor (RE-QSHD), here we compare the results of RE-QSHD with the other extraction method based on height difference (RE-1) 4 by simulation experiment. RE-1 is developed for short-line deployment of MLS systems with low density data and few available configuration parameters.…”

Section: Simulationmentioning

confidence: 99%

“…Current algorithms mainly rely on high-density point cloud dataset and height difference variation characteristics of rail to realize rail extraction. 4 Although they have achieved certain extraction effects, they usually ignore the processing performance and deployment conditions of the algorithm in actual use. Railway network itself is complicated, and there are a lot of infrastructures similar to railway tracks.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A real-time automatic rail extraction algorithm for low-density mobile laser scanning data

Hu,

Huang

2024

Proceedings of the Institution of Mechanical Engineers, Part F:

View full text Add to dashboard Cite

Automatic detection of railroad infrastructure using Mobile Laser Scanning systems is a key technology for both advanced rail driver assistance and intelligent track maintenance. The recent research into railway facility extraction or condition monitoring usually relies on high-density point cloud dataset with known sensor parameters but ignores the processing performance in actual deployment and has high requirements for the acquisition device. To address these limitations, a novel rail extraction algorithm is proposed for processing Mobile Laser Scanning data in real time during acquisition, which could extract rail features by a hierarchical coarse-to-fine method with basic structural parameters. Using the geometric and global statistical characteristics of rail in raw data, a new rail descriptor is defined based on the quantitative statistics of points satisfying height difference in generalized local neighborhood. The approach is evaluated experimentally by a simulated real-time acquisition data and compared with a reference method. The experimental results show that the proposed algorithm has a finer extraction effect and good real-time performance.

show abstract

Section: Methodsmentioning

confidence: 99%