LiDAR Point Cloud Recognition of Overhead Catenary System with Deep Learning
High-speed railways have been one of the most popular means of transportation all over the world. As an important part of the high-speed railway power supply system, the overhead catenary system (OCS) directly influences the stable operation of the railway, so regular inspection and maintenance are...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/8/2212 |
| _version_ | 1797570685847994368 |
|---|---|
| author | Shuai Lin Cheng Xu Lipei Chen Siqi Li Xiaohan Tu |
| author_facet | Shuai Lin Cheng Xu Lipei Chen Siqi Li Xiaohan Tu |
| author_sort | Shuai Lin |
| collection | DOAJ |
| description | High-speed railways have been one of the most popular means of transportation all over the world. As an important part of the high-speed railway power supply system, the overhead catenary system (OCS) directly influences the stable operation of the railway, so regular inspection and maintenance are essential. Now manual inspection is too inefficient and high-cost to fit the requirements for high-speed railway operation, and automatic inspection becomes a trend. The 3D information in the point cloud is useful for geometric parameter measurement in the catenary inspection. Thus it is significant to recognize the components of OCS from the point cloud data collected by the inspection equipment, which promotes the automation of parameter measurement. In this paper, we present a novel method based on deep learning to recognize point clouds of OCS components. The method identifies the context of each single frame point cloud by a convolutional neural network (CNN) and combines some single frame data based on classification results, then inputs them into a segmentation network to identify OCS components. To verify the method, we build a point cloud dataset of OCS components that contains eight categories. The experimental results demonstrate that the proposed method can detect OCS components with high accuracy. Our work can be applied to the real OCS components detection and has great practical significance for OCS automatic inspection. |
| first_indexed | 2024-03-10T20:28:39Z |
| format | Article |
| id | doaj.art-011083670e9745819beb0125d468604a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:28:39Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-011083670e9745819beb0125d468604a2023-11-19T21:34:20ZengMDPI AGSensors1424-82202020-04-01208221210.3390/s20082212LiDAR Point Cloud Recognition of Overhead Catenary System with Deep LearningShuai Lin0Cheng Xu1Lipei Chen2Siqi Li3Xiaohan Tu4College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, ChinaCollege of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, ChinaCollege of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, ChinaCollege of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, ChinaCollege of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, ChinaHigh-speed railways have been one of the most popular means of transportation all over the world. As an important part of the high-speed railway power supply system, the overhead catenary system (OCS) directly influences the stable operation of the railway, so regular inspection and maintenance are essential. Now manual inspection is too inefficient and high-cost to fit the requirements for high-speed railway operation, and automatic inspection becomes a trend. The 3D information in the point cloud is useful for geometric parameter measurement in the catenary inspection. Thus it is significant to recognize the components of OCS from the point cloud data collected by the inspection equipment, which promotes the automation of parameter measurement. In this paper, we present a novel method based on deep learning to recognize point clouds of OCS components. The method identifies the context of each single frame point cloud by a convolutional neural network (CNN) and combines some single frame data based on classification results, then inputs them into a segmentation network to identify OCS components. To verify the method, we build a point cloud dataset of OCS components that contains eight categories. The experimental results demonstrate that the proposed method can detect OCS components with high accuracy. Our work can be applied to the real OCS components detection and has great practical significance for OCS automatic inspection.https://www.mdpi.com/1424-8220/20/8/2212catenary inspectiondeep learningLiDAROCSpoint cloud recognition |
| spellingShingle | Shuai Lin Cheng Xu Lipei Chen Siqi Li Xiaohan Tu LiDAR Point Cloud Recognition of Overhead Catenary System with Deep Learning Sensors catenary inspection deep learning LiDAR OCS point cloud recognition |
| title | LiDAR Point Cloud Recognition of Overhead Catenary System with Deep Learning |
| title_full | LiDAR Point Cloud Recognition of Overhead Catenary System with Deep Learning |
| title_fullStr | LiDAR Point Cloud Recognition of Overhead Catenary System with Deep Learning |
| title_full_unstemmed | LiDAR Point Cloud Recognition of Overhead Catenary System with Deep Learning |
| title_short | LiDAR Point Cloud Recognition of Overhead Catenary System with Deep Learning |
| title_sort | lidar point cloud recognition of overhead catenary system with deep learning |
| topic | catenary inspection deep learning LiDAR OCS point cloud recognition |
| url | https://www.mdpi.com/1424-8220/20/8/2212 |
| work_keys_str_mv | AT shuailin lidarpointcloudrecognitionofoverheadcatenarysystemwithdeeplearning AT chengxu lidarpointcloudrecognitionofoverheadcatenarysystemwithdeeplearning AT lipeichen lidarpointcloudrecognitionofoverheadcatenarysystemwithdeeplearning AT siqili lidarpointcloudrecognitionofoverheadcatenarysystemwithdeeplearning AT xiaohantu lidarpointcloudrecognitionofoverheadcatenarysystemwithdeeplearning |