Extraction of power lines and pylons from LiDAR point clouds using a GCN-based method
The routine power line inspection is critical to maintain the reliability, availability, and sustainability of electricity supply. As a key part of inspection, power lines and pylons extraction is essential for resource management and power corridor safety, especially in the mountain regions. In thi...
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://eprints.nottingham.ac.uk/64821/ |
| _version_ | 1848800171073208320 |
|---|---|
| author | Li, Wen Zhang, Ziyue Luo, Zhipeng Xiao, Zhenlong Wang, Cheng Li, Jonathan |
| author_facet | Li, Wen Zhang, Ziyue Luo, Zhipeng Xiao, Zhenlong Wang, Cheng Li, Jonathan |
| author_sort | Li, Wen |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | The routine power line inspection is critical to maintain the reliability, availability, and sustainability of electricity supply. As a key part of inspection, power lines and pylons extraction is essential for resource management and power corridor safety, especially in the mountain regions. In this paper, we proposed a deep learning based method to extract power lines and pylons using ALS point clouds. First, a structure information preserved module is designed to mine the relationship of local neighborhood points. Then, a graph convolutional network (GCN) is used as basic module to extract point features. Finally, three categories, power lines, pylons and other objects are segmented from input point clouds. In addition, we provide an effective data enhancement strategy to generate enough samples to train the proposed model. We evaluated our method using a dataset acquired by our ALS scanning system. Experimental results demonstrate that our method is superior to the state-of-the-art methods on descriptiveness and efficiency. The overall accuracy and mean time are 99.1% and 9.3 seconds, respectively. |
| first_indexed | 2025-11-14T20:47:19Z |
| format | Conference or Workshop Item |
| id | nottingham-64821 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T20:47:19Z |
| publishDate | 2021 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-648212021-03-24T02:05:57Z https://eprints.nottingham.ac.uk/64821/ Extraction of power lines and pylons from LiDAR point clouds using a GCN-based method Li, Wen Zhang, Ziyue Luo, Zhipeng Xiao, Zhenlong Wang, Cheng Li, Jonathan The routine power line inspection is critical to maintain the reliability, availability, and sustainability of electricity supply. As a key part of inspection, power lines and pylons extraction is essential for resource management and power corridor safety, especially in the mountain regions. In this paper, we proposed a deep learning based method to extract power lines and pylons using ALS point clouds. First, a structure information preserved module is designed to mine the relationship of local neighborhood points. Then, a graph convolutional network (GCN) is used as basic module to extract point features. Finally, three categories, power lines, pylons and other objects are segmented from input point clouds. In addition, we provide an effective data enhancement strategy to generate enough samples to train the proposed model. We evaluated our method using a dataset acquired by our ALS scanning system. Experimental results demonstrate that our method is superior to the state-of-the-art methods on descriptiveness and efficiency. The overall accuracy and mean time are 99.1% and 9.3 seconds, respectively. 2021-02-17 Conference or Workshop Item PeerReviewed application/pdf en cc_by https://eprints.nottingham.ac.uk/64821/1/IGARSS_Extraction%20of%20Power%20Lines%20and%20Pylons%20from%20LiDAR%20Point%20Clouds%20Using%20a%20GCN-Based%20Method.pdf Li, Wen, Zhang, Ziyue, Luo, Zhipeng, Xiao, Zhenlong, Wang, Cheng and Li, Jonathan (2021) Extraction of power lines and pylons from LiDAR point clouds using a GCN-based method. In: IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, 26 Sept.-2 Oct. 2020, Waikoloa, HI, USA. Power line，pylon extraction，ALS，point cloud，graph convolutional network http://dx.doi.org/10.1109/IGARSS39084.2020.9323218 10.1109/IGARSS39084.2020.9323218 10.1109/IGARSS39084.2020.9323218 10.1109/IGARSS39084.2020.9323218 |
| spellingShingle | Power line，pylon extraction，ALS，point cloud，graph convolutional network Li, Wen Zhang, Ziyue Luo, Zhipeng Xiao, Zhenlong Wang, Cheng Li, Jonathan Extraction of power lines and pylons from LiDAR point clouds using a GCN-based method |
| title | Extraction of power lines and pylons from LiDAR point clouds using a GCN-based method |
| title_full | Extraction of power lines and pylons from LiDAR point clouds using a GCN-based method |
| title_fullStr | Extraction of power lines and pylons from LiDAR point clouds using a GCN-based method |
| title_full_unstemmed | Extraction of power lines and pylons from LiDAR point clouds using a GCN-based method |
| title_short | Extraction of power lines and pylons from LiDAR point clouds using a GCN-based method |
| title_sort | extraction of power lines and pylons from lidar point clouds using a gcn-based method |
| topic | Power line，pylon extraction，ALS，point cloud，graph convolutional network |
| url | https://eprints.nottingham.ac.uk/64821/ https://eprints.nottingham.ac.uk/64821/ https://eprints.nottingham.ac.uk/64821/ |