A classification model for power corridors based on the improved PointNet++ network
Aiming at the existing deep learning classification model for power corridor point cloud still need to improve the classification efficiency and the robustness of the classification model to meet the requirements of practical applications. An improved classification model based on PointNet++ is prop...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-01-01
|
| Series: | Geocarto International |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/10106049.2023.2297556 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850163770789199872 |
|---|---|
| author | Li Bo Liu Siyuan Wang Xiangfeng Zou Cunyu |
| author_facet | Li Bo Liu Siyuan Wang Xiangfeng Zou Cunyu |
| author_sort | Li Bo |
| collection | DOAJ |
| description | Aiming at the existing deep learning classification model for power corridor point cloud still need to improve the classification efficiency and the robustness of the classification model to meet the requirements of practical applications. An improved classification model based on PointNet++ is proposed. Based on the fact that the main features of the power corridor scene are power lines, poles, and vegetation, the initial data are first optimally filtered, and then the ensemble abstraction module of the classical PointNet++ is modified to better adapt to the power corridor scene. Finally, h-Swish is used as the activation function to realize the accurate classification of the features of the power corridor scene, and the training time of deep learning is also greatly reduced. The experimental results show that the improved algorithm achieves an average F1 value of 97.58%, which is 3.62 percentage points higher than the classical PointNet++. Therefore, the algorithm has great potential in point cloud classification. |
| format | Article |
| id | doaj-art-9a72391c99c84a64b047c738155ed439 |
| institution | OA Journals |
| issn | 1010-6049 1752-0762 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geocarto International |
| spelling | doaj-art-9a72391c99c84a64b047c738155ed4392025-08-20T02:22:09ZengTaylor & Francis GroupGeocarto International1010-60491752-07622024-01-0139110.1080/10106049.2023.2297556A classification model for power corridors based on the improved PointNet++ networkLi Bo0Liu Siyuan1Wang Xiangfeng2Zou Cunyu3Shenyang Institute of Engineering, Shenyang, ChinaShenyang Institute of Engineering, Shenyang, ChinaShenyang Institute of Engineering, Shenyang, ChinaShenyang Institute of Engineering, Shenyang, ChinaAiming at the existing deep learning classification model for power corridor point cloud still need to improve the classification efficiency and the robustness of the classification model to meet the requirements of practical applications. An improved classification model based on PointNet++ is proposed. Based on the fact that the main features of the power corridor scene are power lines, poles, and vegetation, the initial data are first optimally filtered, and then the ensemble abstraction module of the classical PointNet++ is modified to better adapt to the power corridor scene. Finally, h-Swish is used as the activation function to realize the accurate classification of the features of the power corridor scene, and the training time of deep learning is also greatly reduced. The experimental results show that the improved algorithm achieves an average F1 value of 97.58%, which is 3.62 percentage points higher than the classical PointNet++. Therefore, the algorithm has great potential in point cloud classification.https://www.tandfonline.com/doi/10.1080/10106049.2023.2297556Deep learningPointNet++Power corridorActivation function |
| spellingShingle | Li Bo Liu Siyuan Wang Xiangfeng Zou Cunyu A classification model for power corridors based on the improved PointNet++ network Geocarto International Deep learning PointNet++ Power corridor Activation function |
| title | A classification model for power corridors based on the improved PointNet++ network |
| title_full | A classification model for power corridors based on the improved PointNet++ network |
| title_fullStr | A classification model for power corridors based on the improved PointNet++ network |
| title_full_unstemmed | A classification model for power corridors based on the improved PointNet++ network |
| title_short | A classification model for power corridors based on the improved PointNet++ network |
| title_sort | classification model for power corridors based on the improved pointnet network |
| topic | Deep learning PointNet++ Power corridor Activation function |
| url | https://www.tandfonline.com/doi/10.1080/10106049.2023.2297556 |
| work_keys_str_mv | AT libo aclassificationmodelforpowercorridorsbasedontheimprovedpointnetnetwork AT liusiyuan aclassificationmodelforpowercorridorsbasedontheimprovedpointnetnetwork AT wangxiangfeng aclassificationmodelforpowercorridorsbasedontheimprovedpointnetnetwork AT zoucunyu aclassificationmodelforpowercorridorsbasedontheimprovedpointnetnetwork AT libo classificationmodelforpowercorridorsbasedontheimprovedpointnetnetwork AT liusiyuan classificationmodelforpowercorridorsbasedontheimprovedpointnetnetwork AT wangxiangfeng classificationmodelforpowercorridorsbasedontheimprovedpointnetnetwork AT zoucunyu classificationmodelforpowercorridorsbasedontheimprovedpointnetnetwork |