Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.15099 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916584096792576 |
|---|---|
| author | Zhang, Shengdong Zhang, Xiaoqin Ren, Wenqi Shen, Linlin Wan, Shaohua Zhang, Jun Jiang, Yujing M |
| author_facet | Zhang, Shengdong Zhang, Xiaoqin Ren, Wenqi Shen, Linlin Wan, Shaohua Zhang, Jun Jiang, Yujing M |
| contents | Ensuring a stable power supply in rural areas relies heavily on effective inspection of power equipment, particularly transmission lines (TLs). However, detecting TLs from aerial imagery can be challenging when dealing with misalignments between visible light (RGB) and infrared (IR) images, as well as mismatched high- and low-level features in convolutional networks. To address these limitations, we propose a novel Hierarchical Multi-Modal Enhancement Network (HMMEN) that integrates RGB and IR data for robust and accurate TL detection. Our method introduces two key components: (1) a Mutual Multi-Modal Enhanced Block (MMEB), which fuses and enhances hierarchical RGB and IR feature maps in a coarse-to-fine manner, and (2) a Feature Alignment Block (FAB) that corrects misalignments between decoder outputs and IR feature maps by leveraging deformable convolutions. We employ MobileNet-based encoders for both RGB and IR inputs to accommodate edge-computing constraints and reduce computational overhead. Experimental results on diverse weather and lighting conditionsfog, night, snow, and daytimedemonstrate the superiority and robustness of our approach compared to state-of-the-art methods, resulting in fewer false positives, enhanced boundary delineation, and better overall detection performance. This framework thus shows promise for practical large-scale power line inspections with unmanned aerial vehicles. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_15099 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bringing RGB and IR Together: Hierarchical Multi-Modal Enhancement for Robust Transmission Line Detection Zhang, Shengdong Zhang, Xiaoqin Ren, Wenqi Shen, Linlin Wan, Shaohua Zhang, Jun Jiang, Yujing M Computer Vision and Pattern Recognition Machine Learning Ensuring a stable power supply in rural areas relies heavily on effective inspection of power equipment, particularly transmission lines (TLs). However, detecting TLs from aerial imagery can be challenging when dealing with misalignments between visible light (RGB) and infrared (IR) images, as well as mismatched high- and low-level features in convolutional networks. To address these limitations, we propose a novel Hierarchical Multi-Modal Enhancement Network (HMMEN) that integrates RGB and IR data for robust and accurate TL detection. Our method introduces two key components: (1) a Mutual Multi-Modal Enhanced Block (MMEB), which fuses and enhances hierarchical RGB and IR feature maps in a coarse-to-fine manner, and (2) a Feature Alignment Block (FAB) that corrects misalignments between decoder outputs and IR feature maps by leveraging deformable convolutions. We employ MobileNet-based encoders for both RGB and IR inputs to accommodate edge-computing constraints and reduce computational overhead. Experimental results on diverse weather and lighting conditionsfog, night, snow, and daytimedemonstrate the superiority and robustness of our approach compared to state-of-the-art methods, resulting in fewer false positives, enhanced boundary delineation, and better overall detection performance. This framework thus shows promise for practical large-scale power line inspections with unmanned aerial vehicles. |
| title | Bringing RGB and IR Together: Hierarchical Multi-Modal Enhancement for Robust Transmission Line Detection |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2501.15099 |