A Deep Learning Method to Detect Foreign Objects for Inspecting Power Transmission Lines
Image online monitoring technology has been widely used in transmission lines inspection, but the intelligent and efficient foreign object detection still has a gap with the ideal. In this paper, we propose a deep learning method to detect invading foreign objects for power transmission line inspect...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9096331/ |
| _version_ | 1818433528534138880 |
|---|---|
| author | Jinguo Zhu Yue Guo Fanding Yue Huan Yuan Aijun Yang Xiaohua Wang Mingzhe Rong |
| author_facet | Jinguo Zhu Yue Guo Fanding Yue Huan Yuan Aijun Yang Xiaohua Wang Mingzhe Rong |
| author_sort | Jinguo Zhu |
| collection | DOAJ |
| description | Image online monitoring technology has been widely used in transmission lines inspection, but the intelligent and efficient foreign object detection still has a gap with the ideal. In this paper, we propose a deep learning method to detect invading foreign objects for power transmission line inspection. Specifically, we design our network based on the regression strategy with oriented bounding boxes to accurately predict spatial location and orientation angle of foreign objects, as well as their categories in cluttered backgrounds. Moreover, an easy yet effective Scale Histogram Matching method is proposed to be applied to the publicly available dataset, allowing useful patterns to be exploited to detect tiny foreign objects during the pretraining procedure and boosting detection performance even with limited annotated samples. Besides, we construct an image dataset that contains common foreign objects in transmission line scenarios to evaluate proposed methods, on which experiment results show our full model achieves accuracy with 88.1% mean Average Precision (mAP). Additionally, the efficient and compact network structure allows our network to run in real-time, which provides possibilities for practical use. |
| first_indexed | 2024-12-14T16:22:32Z |
| format | Article |
| id | doaj.art-aed2ed722749411bb47d0333254bc23f |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T16:22:32Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-aed2ed722749411bb47d0333254bc23f2022-12-21T22:54:46ZengIEEEIEEE Access2169-35362020-01-018940659407510.1109/ACCESS.2020.29956089096331A Deep Learning Method to Detect Foreign Objects for Inspecting Power Transmission LinesJinguo Zhu0https://orcid.org/0000-0002-3616-4264Yue Guo1Fanding Yue2Huan Yuan3Aijun Yang4https://orcid.org/0000-0002-0447-7493Xiaohua Wang5https://orcid.org/0000-0002-6551-151XMingzhe Rong6https://orcid.org/0000-0003-3977-6298Department of Electrical Engineering, Xi’an Jiaotong University, Xian, ChinaDepartment of Electrical Engineering, Xi’an Jiaotong University, Xian, ChinaDepartment of Electrical Engineering, Xi’an Jiaotong University, Xian, ChinaDepartment of Electrical Engineering, Xi’an Jiaotong University, Xian, ChinaDepartment of Electrical Engineering, Xi’an Jiaotong University, Xian, ChinaDepartment of Electrical Engineering, Xi’an Jiaotong University, Xian, ChinaDepartment of Electrical Engineering, Xi’an Jiaotong University, Xian, ChinaImage online monitoring technology has been widely used in transmission lines inspection, but the intelligent and efficient foreign object detection still has a gap with the ideal. In this paper, we propose a deep learning method to detect invading foreign objects for power transmission line inspection. Specifically, we design our network based on the regression strategy with oriented bounding boxes to accurately predict spatial location and orientation angle of foreign objects, as well as their categories in cluttered backgrounds. Moreover, an easy yet effective Scale Histogram Matching method is proposed to be applied to the publicly available dataset, allowing useful patterns to be exploited to detect tiny foreign objects during the pretraining procedure and boosting detection performance even with limited annotated samples. Besides, we construct an image dataset that contains common foreign objects in transmission line scenarios to evaluate proposed methods, on which experiment results show our full model achieves accuracy with 88.1% mean Average Precision (mAP). Additionally, the efficient and compact network structure allows our network to run in real-time, which provides possibilities for practical use.https://ieeexplore.ieee.org/document/9096331/Image online monitoring technologypower transmission line inspectiondeep learningoriented bounding boxesscale histogram matching |
| spellingShingle | Jinguo Zhu Yue Guo Fanding Yue Huan Yuan Aijun Yang Xiaohua Wang Mingzhe Rong A Deep Learning Method to Detect Foreign Objects for Inspecting Power Transmission Lines IEEE Access Image online monitoring technology power transmission line inspection deep learning oriented bounding boxes scale histogram matching |
| title | A Deep Learning Method to Detect Foreign Objects for Inspecting Power Transmission Lines |
| title_full | A Deep Learning Method to Detect Foreign Objects for Inspecting Power Transmission Lines |
| title_fullStr | A Deep Learning Method to Detect Foreign Objects for Inspecting Power Transmission Lines |
| title_full_unstemmed | A Deep Learning Method to Detect Foreign Objects for Inspecting Power Transmission Lines |
| title_short | A Deep Learning Method to Detect Foreign Objects for Inspecting Power Transmission Lines |
| title_sort | deep learning method to detect foreign objects for inspecting power transmission lines |
| topic | Image online monitoring technology power transmission line inspection deep learning oriented bounding boxes scale histogram matching |
| url | https://ieeexplore.ieee.org/document/9096331/ |
| work_keys_str_mv | AT jinguozhu adeeplearningmethodtodetectforeignobjectsforinspectingpowertransmissionlines AT yueguo adeeplearningmethodtodetectforeignobjectsforinspectingpowertransmissionlines AT fandingyue adeeplearningmethodtodetectforeignobjectsforinspectingpowertransmissionlines AT huanyuan adeeplearningmethodtodetectforeignobjectsforinspectingpowertransmissionlines AT aijunyang adeeplearningmethodtodetectforeignobjectsforinspectingpowertransmissionlines AT xiaohuawang adeeplearningmethodtodetectforeignobjectsforinspectingpowertransmissionlines AT mingzherong adeeplearningmethodtodetectforeignobjectsforinspectingpowertransmissionlines AT jinguozhu deeplearningmethodtodetectforeignobjectsforinspectingpowertransmissionlines AT yueguo deeplearningmethodtodetectforeignobjectsforinspectingpowertransmissionlines AT fandingyue deeplearningmethodtodetectforeignobjectsforinspectingpowertransmissionlines AT huanyuan deeplearningmethodtodetectforeignobjectsforinspectingpowertransmissionlines AT aijunyang deeplearningmethodtodetectforeignobjectsforinspectingpowertransmissionlines AT xiaohuawang deeplearningmethodtodetectforeignobjectsforinspectingpowertransmissionlines AT mingzherong deeplearningmethodtodetectforeignobjectsforinspectingpowertransmissionlines |