Virtual Reality and Convolutional Neural Networks for Railway Catenary Support Components Monitoring

Liu, Wenqiang; Liu, Zhigang; Núñez, Alfredo

doi:10.1109/itsc.2019.8917061

Cited by 7 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The monitoring is achieved using high-definition cameras installed on dedicated inspection vehicles, with image capturing primarily taking place at night to avoid the interference of complex daytime backgrounds. It is worth noting that, while early papers focused on the feasibility of using deep learning-based computer vision to monitor catenary supportive components [20,21], recent works, especially in 2022, have focused more on improving the precision and performance of these approaches for specific components. For example, papers [8,39] have adopted advanced methods to improve the accuracy of insulator defect detection.…”

Section: Monitoring Targetsmentioning

confidence: 99%

Railway Catenary Condition Monitoring: A Systematic Mapping of Recent Research

Chen,

Frøseth,

Derosa

et al. 2024

Sensors

View full text Add to dashboard Cite

In this paper, a different approach to the traditional literature review—literature systematic mapping—is adopted to summarize the progress in the recent research on railway catenary system condition monitoring in terms of aspects such as sensor categories, monitoring targets, and so forth. Importantly, the deep interconnections among these aspects are also investigated through systematic mapping. In addition, the authorship and publication trends are also examined. Compared to a traditional literature review, the literature mapping approach focuses less on the technical details of the research but reflects the research trends, and focuses in a specific field by visualizing them with the help of different plots and figures, which makes it more visually direct and comprehensible than the traditional literature review approach.

show abstract

Section: Monitoring Targetsmentioning

confidence: 99%

Railway Catenary Condition Monitoring: A Systematic Mapping of Recent Research

Chen,

Frøseth,

Derosa

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Tables 3 and 4, whose structure and aim are described in Section III-E, summarise the papers we found within this Railway Area. Catenary Support Device [95], [96], [97] [98], [99], [100], [101], [102], [103], [104], [105], [106], [107], [108], [109], [110] [111], [112], [113], [114], [115], [116] Pantograph & Arcs [117], [118] [101], [119], [120], [121] [122], [123], [124] Catenary Wires [125], [126], [127], [128], [109] [129]…”

Section: Pantograph and Catenarymentioning

confidence: 99%

A Survey on Audio-Video Based Defect Detection Through Deep Learning in Railway Maintenance

et al. 2022

View full text Add to dashboard Cite

Within Artificial Intelligence, Deep Learning (DL) represents a paradigm that has been showing unprecedented performance in image and audio processing by supporting or even replacing humans in defect and anomaly detection. The Railway sector is expected to benefit from DL applications, especially in predictive maintenance applications, where smart audio and video sensors can be leveraged yet kept distinct from safety-critical functions. Such separation is crucial, as it allows for improving system dependability with no impact on its safety certification. This is further supported by the development of DL in other transportation domains, such as automotive and avionics, opening for knowledge transfer opportunities and highlighting the potential of such a paradigm in railways. In order to summarize the recent state-of-the-art while inquiring about future opportunities, this paper reviews DL approaches for the analysis of data generated by acoustic and visual sensors in railway maintenance applications that have been published until August 31st, 2021. In this paper, the current state of the research is investigated and evaluated using a structured and systematic method, in order to highlight promising approaches and successful applications, as well as to identify available datasets, current limitations, open issues, challenges, and recommendations about future research directions.

show abstract

“…These data sources make it possible to increase the level of details about the condition of the railway infrastructure obtained during inspection programs. The literature so far of 3-D point cloud data for railway applications is somewhat limited [15]- [18]. Han et al [19] used 3-D point cloud data to detect the SPCCDs, as shown in Fig.…”

Section: (B)mentioning

confidence: 99%

High-Precision Detection Method for Structure Parameters of Catenary Cantilever Devices Using 3-D Point Cloud Data

Liu

et al. 2021

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

This article proposes an automatic high-precision detection method for structure parameters of catenary cantilever devices (SPCCDs) using 3-D point cloud data. The steps of the proposed detection method are: 1) segmenting and recognizing the components of the catenary cantilever devices, 2) extracting the detection plane and backbone component axis of catenary cantilever devices, and 3) detecting the SPCCD. The effective segmentation of components is critical for structure parameter detection. A point cloud segmentation and recognition method based on three-dimensional convolutional neural networks (3-D CNNs) is introduced to determine the different components of the catenary cantilever devices. Compared with traditional unsupervised clustering procedures for point cloud segmentation, the proposed method can improve the segmentation accuracy, does not require complex tuning procedures of parameters, and improves robustness and stability. Additionally, the segmentation method defines a recognition function, facilitating the analysis of the structural relationship between objects. Furthermore, we proposed an improved projection random sample consensus (RANSAC) method, which can effectively divide the detection plane of catenary cantilever devices to solve the multicantilever device occlusion problem. With RANSAC, it is also possible to precisely extract the backbone component axis and enhance parameter detection accuracy. The experimental results show that the structure angle and steady arm slope's error accuracy can achieve 0.1029 • and 1.19%, respectively, which indicates the proposed approach can precisely detect the SPCCD.

show abstract

Virtual Reality and Convolutional Neural Networks for Railway Catenary Support Components Monitoring

Cited by 7 publications

References 26 publications

Railway Catenary Condition Monitoring: A Systematic Mapping of Recent Research

Railway Catenary Condition Monitoring: A Systematic Mapping of Recent Research

A Survey on Audio-Video Based Defect Detection Through Deep Learning in Railway Maintenance

High-Precision Detection Method for Structure Parameters of Catenary Cantilever Devices Using 3-D Point Cloud Data

Contact Info

Product

Resources

About