Online Pantograph-Catenary Contact Point Detection in Complicated Background Based on Multiple Strategies
Monitoring train operation status is one of the most important tasks for ensuring rail operation safety. Pantograph and catenary (PAC) are collecting systems of the electric current from traction power supply system, and the stability of the contact between pantograph and catenary guarantees the sta...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9281353/ |
| _version_ | 1818928678847905792 |
|---|---|
| author | Xuan Yang Ning Zhou Yueping Liu Wei Quan Xuemin Lu Weihua Zhang |
| author_facet | Xuan Yang Ning Zhou Yueping Liu Wei Quan Xuemin Lu Weihua Zhang |
| author_sort | Xuan Yang |
| collection | DOAJ |
| description | Monitoring train operation status is one of the most important tasks for ensuring rail operation safety. Pantograph and catenary (PAC) are collecting systems of the electric current from traction power supply system, and the stability of the contact between pantograph and catenary guarantees the stable power. However, most existing contact point (CPT) detection methods are always difficult to achieve precise positioning results, especially in complicated background. This article proposes a novel fast and accurate contact point detection method based on multiple strategies, which combine three modules. First, an improved kernelized correlation filter model in real-time tracking module was adopted to track the contact region. Then the pixel-level detection module was used to detect contact point in contact region via the proposed contact point regression residual network (CPRR-Net). Finally, a filter-based optimization module was added to correct the contact position using the Kalman filter. This work additionally employed a new rail dataset PAC-TPL2020 to prove the effectiveness and feasibility of the proposed multiple strategies in real-world scenarios, and the experimental results demonstrated the robustness and high accuracy (97.07% within 3 pixels and 99.97% within 5 pixels) of our model. It is noteworthy that our mothed runs at 65 frames per second for monitoring PAC contact points. |
| first_indexed | 2024-12-20T03:32:44Z |
| format | Article |
| id | doaj.art-855ca7f6fbce4f0a8d01cd524afaf6b3 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T03:32:44Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-855ca7f6fbce4f0a8d01cd524afaf6b32022-12-21T19:54:57ZengIEEEIEEE Access2169-35362020-01-01822039422040710.1109/ACCESS.2020.30425359281353Online Pantograph-Catenary Contact Point Detection in Complicated Background Based on Multiple StrategiesXuan Yang0https://orcid.org/0000-0002-7246-8548Ning Zhou1Yueping Liu2Wei Quan3https://orcid.org/0000-0001-7926-9501Xuemin Lu4https://orcid.org/0000-0001-7534-9790Weihua Zhang5State Key Laboratory of Traction Power, Southwest Jiaotong University, Chengdu, ChinaState Key Laboratory of Traction Power, Southwest Jiaotong University, Chengdu, ChinaState Key Laboratory of Traction Power, Southwest Jiaotong University, Chengdu, ChinaSchool of Electrical Engineering, Southwest Jiaotong University, Chengdu, ChinaSchool of Electrical Engineering, Southwest Jiaotong University, Chengdu, ChinaState Key Laboratory of Traction Power, Southwest Jiaotong University, Chengdu, ChinaMonitoring train operation status is one of the most important tasks for ensuring rail operation safety. Pantograph and catenary (PAC) are collecting systems of the electric current from traction power supply system, and the stability of the contact between pantograph and catenary guarantees the stable power. However, most existing contact point (CPT) detection methods are always difficult to achieve precise positioning results, especially in complicated background. This article proposes a novel fast and accurate contact point detection method based on multiple strategies, which combine three modules. First, an improved kernelized correlation filter model in real-time tracking module was adopted to track the contact region. Then the pixel-level detection module was used to detect contact point in contact region via the proposed contact point regression residual network (CPRR-Net). Finally, a filter-based optimization module was added to correct the contact position using the Kalman filter. This work additionally employed a new rail dataset PAC-TPL2020 to prove the effectiveness and feasibility of the proposed multiple strategies in real-world scenarios, and the experimental results demonstrated the robustness and high accuracy (97.07% within 3 pixels and 99.97% within 5 pixels) of our model. It is noteworthy that our mothed runs at 65 frames per second for monitoring PAC contact points.https://ieeexplore.ieee.org/document/9281353/Condition monitoringcontact pointdeep convolutional neural networkimage processingpantograph and catenary system |
| spellingShingle | Xuan Yang Ning Zhou Yueping Liu Wei Quan Xuemin Lu Weihua Zhang Online Pantograph-Catenary Contact Point Detection in Complicated Background Based on Multiple Strategies IEEE Access Condition monitoring contact point deep convolutional neural network image processing pantograph and catenary system |
| title | Online Pantograph-Catenary Contact Point Detection in Complicated Background Based on Multiple Strategies |
| title_full | Online Pantograph-Catenary Contact Point Detection in Complicated Background Based on Multiple Strategies |
| title_fullStr | Online Pantograph-Catenary Contact Point Detection in Complicated Background Based on Multiple Strategies |
| title_full_unstemmed | Online Pantograph-Catenary Contact Point Detection in Complicated Background Based on Multiple Strategies |
| title_short | Online Pantograph-Catenary Contact Point Detection in Complicated Background Based on Multiple Strategies |
| title_sort | online pantograph catenary contact point detection in complicated background based on multiple strategies |
| topic | Condition monitoring contact point deep convolutional neural network image processing pantograph and catenary system |
| url | https://ieeexplore.ieee.org/document/9281353/ |
| work_keys_str_mv | AT xuanyang onlinepantographcatenarycontactpointdetectionincomplicatedbackgroundbasedonmultiplestrategies AT ningzhou onlinepantographcatenarycontactpointdetectionincomplicatedbackgroundbasedonmultiplestrategies AT yuepingliu onlinepantographcatenarycontactpointdetectionincomplicatedbackgroundbasedonmultiplestrategies AT weiquan onlinepantographcatenarycontactpointdetectionincomplicatedbackgroundbasedonmultiplestrategies AT xueminlu onlinepantographcatenarycontactpointdetectionincomplicatedbackgroundbasedonmultiplestrategies AT weihuazhang onlinepantographcatenarycontactpointdetectionincomplicatedbackgroundbasedonmultiplestrategies |