LSKAFF-YOLO: Large Separable Kernel Attentional Feature Fusion Network for Transmission Tower Detection in High-Resolution Satellite Remote Sensing Images
High-resolution satellite remote sensing technology provides an effective solution for the efficient and stable inspection of high-voltage transmission lines. The accurate extraction of transmission towers is crucial for leveraging satellite imagery in transmission line monitoring. This article addr...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11096014/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849239022196490240 |
|---|---|
| author | Xiaojin Yan Zhixuan Li Yongjie Zhai Ke Liu Ke Zhang Zhenbing Zhao |
| author_facet | Xiaojin Yan Zhixuan Li Yongjie Zhai Ke Liu Ke Zhang Zhenbing Zhao |
| author_sort | Xiaojin Yan |
| collection | DOAJ |
| description | High-resolution satellite remote sensing technology provides an effective solution for the efficient and stable inspection of high-voltage transmission lines. The accurate extraction of transmission towers is crucial for leveraging satellite imagery in transmission line monitoring. This article addresses the challenges in detecting transmission towers, which are often obscured by complex backgrounds, variable object sizes, and small-scale objects. We propose the large separable kernel attentional feature fusion (LSKAFF)-YOLO network to enhance the precision of transmission tower extraction. This model incorporates LSKA-AFF module into the backbone network to extend the receptive field. By effectively leveraging the contextual information of satellite remote sensing images, it provides richer feature details for transmission tower positioning. Moreover, a progressive path aggregation network replaces the original neck network, mitigating information loss or degradation during feature transfer and interaction, thereby realizing multiscale feature fusion of transmission towers. To comprehensively evaluate the model’s performance, this study constructs Gao Fen tower dataset, a multiscene high-resolution satellite remote sensing transmission tower dataset, using GaoFen-2 and GaoFen-7 images, with references to publicly available datasets satellite remote sensing power tower dataset. The experimental results show that LSKAFF-YOLO attains mAP0.5 values of 88.8<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> and 94.6<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula>, precision of 80.5<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> and 89.3<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula>, recall of 89.2<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> and 93.5<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula>, and F1-score of 0.85 and 0.91, respectively. LSKAFF-YOLO outperforms other existing methods in terms of precision and overall performance in transmission tower detection. |
| format | Article |
| id | doaj-art-52f1845e6d06446a960a0eeca95e5fa2 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-52f1845e6d06446a960a0eeca95e5fa22025-08-20T04:01:15ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118192081922210.1109/JSTARS.2025.359267111096014LSKAFF-YOLO: Large Separable Kernel Attentional Feature Fusion Network for Transmission Tower Detection in High-Resolution Satellite Remote Sensing ImagesXiaojin Yan0https://orcid.org/0009-0001-6235-0159Zhixuan Li1https://orcid.org/0009-0002-6338-7743Yongjie Zhai2https://orcid.org/0000-0003-2997-5840Ke Liu3Ke Zhang4https://orcid.org/0000-0003-3271-3585Zhenbing Zhao5https://orcid.org/0000-0003-2290-0598School of Control and Computer Engineering, North China Electric Power University, Baoding, ChinaSchool of Electronic and Control Engineering, North China Institute of Aerospace Engineering, Langfang, ChinaSchool of Control and Computer Engineering, North China Electric Power University, Baoding, ChinaSchool of Remote Sensing and Information Engineering and Collaborative Innovation Center of Space Remote Sensing Information Processing and Application, North China Institute of Aerospace Engineering, Langfang, ChinaDepartment of Electronics and Communication Engineering and Hebei Key Laboratory of Power Internet of Things Technology, North China Electric Power University, Baoding, ChinaDepartment of Electronics and Communication Engineering and Hebei Key Laboratory of Power Internet of Things Technology, North China Electric Power University, Baoding, ChinaHigh-resolution satellite remote sensing technology provides an effective solution for the efficient and stable inspection of high-voltage transmission lines. The accurate extraction of transmission towers is crucial for leveraging satellite imagery in transmission line monitoring. This article addresses the challenges in detecting transmission towers, which are often obscured by complex backgrounds, variable object sizes, and small-scale objects. We propose the large separable kernel attentional feature fusion (LSKAFF)-YOLO network to enhance the precision of transmission tower extraction. This model incorporates LSKA-AFF module into the backbone network to extend the receptive field. By effectively leveraging the contextual information of satellite remote sensing images, it provides richer feature details for transmission tower positioning. Moreover, a progressive path aggregation network replaces the original neck network, mitigating information loss or degradation during feature transfer and interaction, thereby realizing multiscale feature fusion of transmission towers. To comprehensively evaluate the model’s performance, this study constructs Gao Fen tower dataset, a multiscene high-resolution satellite remote sensing transmission tower dataset, using GaoFen-2 and GaoFen-7 images, with references to publicly available datasets satellite remote sensing power tower dataset. The experimental results show that LSKAFF-YOLO attains mAP0.5 values of 88.8<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> and 94.6<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula>, precision of 80.5<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> and 89.3<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula>, recall of 89.2<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> and 93.5<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula>, and F1-score of 0.85 and 0.91, respectively. LSKAFF-YOLO outperforms other existing methods in terms of precision and overall performance in transmission tower detection.https://ieeexplore.ieee.org/document/11096014/Deep learningfeature fusionhigh-resolution satellite remote sensing imageslarge separable kernel attentiontransmission tower detection |
| spellingShingle | Xiaojin Yan Zhixuan Li Yongjie Zhai Ke Liu Ke Zhang Zhenbing Zhao LSKAFF-YOLO: Large Separable Kernel Attentional Feature Fusion Network for Transmission Tower Detection in High-Resolution Satellite Remote Sensing Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Deep learning feature fusion high-resolution satellite remote sensing images large separable kernel attention transmission tower detection |
| title | LSKAFF-YOLO: Large Separable Kernel Attentional Feature Fusion Network for Transmission Tower Detection in High-Resolution Satellite Remote Sensing Images |
| title_full | LSKAFF-YOLO: Large Separable Kernel Attentional Feature Fusion Network for Transmission Tower Detection in High-Resolution Satellite Remote Sensing Images |
| title_fullStr | LSKAFF-YOLO: Large Separable Kernel Attentional Feature Fusion Network for Transmission Tower Detection in High-Resolution Satellite Remote Sensing Images |
| title_full_unstemmed | LSKAFF-YOLO: Large Separable Kernel Attentional Feature Fusion Network for Transmission Tower Detection in High-Resolution Satellite Remote Sensing Images |
| title_short | LSKAFF-YOLO: Large Separable Kernel Attentional Feature Fusion Network for Transmission Tower Detection in High-Resolution Satellite Remote Sensing Images |
| title_sort | lskaff yolo large separable kernel attentional feature fusion network for transmission tower detection in high resolution satellite remote sensing images |
| topic | Deep learning feature fusion high-resolution satellite remote sensing images large separable kernel attention transmission tower detection |
| url | https://ieeexplore.ieee.org/document/11096014/ |
| work_keys_str_mv | AT xiaojinyan lskaffyololargeseparablekernelattentionalfeaturefusionnetworkfortransmissiontowerdetectioninhighresolutionsatelliteremotesensingimages AT zhixuanli lskaffyololargeseparablekernelattentionalfeaturefusionnetworkfortransmissiontowerdetectioninhighresolutionsatelliteremotesensingimages AT yongjiezhai lskaffyololargeseparablekernelattentionalfeaturefusionnetworkfortransmissiontowerdetectioninhighresolutionsatelliteremotesensingimages AT keliu lskaffyololargeseparablekernelattentionalfeaturefusionnetworkfortransmissiontowerdetectioninhighresolutionsatelliteremotesensingimages AT kezhang lskaffyololargeseparablekernelattentionalfeaturefusionnetworkfortransmissiontowerdetectioninhighresolutionsatelliteremotesensingimages AT zhenbingzhao lskaffyololargeseparablekernelattentionalfeaturefusionnetworkfortransmissiontowerdetectioninhighresolutionsatelliteremotesensingimages |