Automated deep learning system for power line inspection image analysis and processing: Architecture and design issues
The continuous growth in the scale of unmanned aerial vehicle (UAV) applications in transmission line inspection has resulted in a corresponding increase in the demand for UAV inspection image processing. Owing to its excellent performance in computer vision, deep learning has been applied to UAV in...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2023-10-01
|
| Series: | Global Energy Interconnection |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S209651172300083X |
| _version_ | 1797637587740917760 |
|---|---|
| author | Daoxing Li Xiaohui Wang Jie Zhang Zhixiang Ji |
| author_facet | Daoxing Li Xiaohui Wang Jie Zhang Zhixiang Ji |
| author_sort | Daoxing Li |
| collection | DOAJ |
| description | The continuous growth in the scale of unmanned aerial vehicle (UAV) applications in transmission line inspection has resulted in a corresponding increase in the demand for UAV inspection image processing. Owing to its excellent performance in computer vision, deep learning has been applied to UAV inspection image processing tasks such as power line identification and insulator defect detection. Despite their excellent performance, electric power UAV inspection image processing models based on deep learning face several problems such as a small application scope, the need for constant retraining and optimization, and high R&D monetary and time costs due to the black-box and scene data-driven characteristics of deep learning. In this study, an automated deep learning system for electric power UAV inspection image analysis and processing is proposed as a solution to the aforementioned problems. This system design is based on the three critical design principles of generalizability, extensibility, and automation. Pre-trained models, fine-tuning (downstream task adaptation), and automated machine learning, which are closely related to these design principles, are reviewed. In addition, an automated deep learning system architecture for electric power UAV inspection image analysis and processing is presented. A prototype system was constructed and experiments were conducted on the two electric power UAV inspection image analysis and processing tasks of insulator self-detonation and bird nest recognition. The models constructed using the prototype system achieved 91.36% and 86.13% mAP for insulator self-detonation and bird nest recognition, respectively. This demonstrates that the system design concept is reasonable and the system architecture feasible |
| first_indexed | 2024-03-11T12:50:28Z |
| format | Article |
| id | doaj.art-37e4888775104651846dd3301424c631 |
| institution | Directory Open Access Journal |
| issn | 2096-5117 |
| language | English |
| last_indexed | 2024-03-11T12:50:28Z |
| publishDate | 2023-10-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Global Energy Interconnection |
| spelling | doaj.art-37e4888775104651846dd3301424c6312023-11-04T04:18:36ZengKeAi Communications Co., Ltd.Global Energy Interconnection2096-51172023-10-0165614633Automated deep learning system for power line inspection image analysis and processing: Architecture and design issuesDaoxing Li0Xiaohui Wang1Jie Zhang2Zhixiang Ji3China Electric Power Research Institute Co., Ltd, Haidian District, Beijing 100192, PR ChinaChina Electric Power Research Institute Co., Ltd, Haidian District, Beijing 100192, PR ChinaSichuan Electric Power Research Institute SGCC, Chengdu 610041, PR ChinaChina Electric Power Research Institute Co., Ltd, Haidian District, Beijing 100192, PR ChinaThe continuous growth in the scale of unmanned aerial vehicle (UAV) applications in transmission line inspection has resulted in a corresponding increase in the demand for UAV inspection image processing. Owing to its excellent performance in computer vision, deep learning has been applied to UAV inspection image processing tasks such as power line identification and insulator defect detection. Despite their excellent performance, electric power UAV inspection image processing models based on deep learning face several problems such as a small application scope, the need for constant retraining and optimization, and high R&D monetary and time costs due to the black-box and scene data-driven characteristics of deep learning. In this study, an automated deep learning system for electric power UAV inspection image analysis and processing is proposed as a solution to the aforementioned problems. This system design is based on the three critical design principles of generalizability, extensibility, and automation. Pre-trained models, fine-tuning (downstream task adaptation), and automated machine learning, which are closely related to these design principles, are reviewed. In addition, an automated deep learning system architecture for electric power UAV inspection image analysis and processing is presented. A prototype system was constructed and experiments were conducted on the two electric power UAV inspection image analysis and processing tasks of insulator self-detonation and bird nest recognition. The models constructed using the prototype system achieved 91.36% and 86.13% mAP for insulator self-detonation and bird nest recognition, respectively. This demonstrates that the system design concept is reasonable and the system architecture feasiblehttp://www.sciencedirect.com/science/article/pii/S209651172300083XTransmission line inspectionDeep learningAutomated machine learningImage analysis and processing |
| spellingShingle | Daoxing Li Xiaohui Wang Jie Zhang Zhixiang Ji Automated deep learning system for power line inspection image analysis and processing: Architecture and design issues Global Energy Interconnection Transmission line inspection Deep learning Automated machine learning Image analysis and processing |
| title | Automated deep learning system for power line inspection image analysis and processing: Architecture and design issues |
| title_full | Automated deep learning system for power line inspection image analysis and processing: Architecture and design issues |
| title_fullStr | Automated deep learning system for power line inspection image analysis and processing: Architecture and design issues |
| title_full_unstemmed | Automated deep learning system for power line inspection image analysis and processing: Architecture and design issues |
| title_short | Automated deep learning system for power line inspection image analysis and processing: Architecture and design issues |
| title_sort | automated deep learning system for power line inspection image analysis and processing architecture and design issues |
| topic | Transmission line inspection Deep learning Automated machine learning Image analysis and processing |
| url | http://www.sciencedirect.com/science/article/pii/S209651172300083X |
| work_keys_str_mv | AT daoxingli automateddeeplearningsystemforpowerlineinspectionimageanalysisandprocessingarchitectureanddesignissues AT xiaohuiwang automateddeeplearningsystemforpowerlineinspectionimageanalysisandprocessingarchitectureanddesignissues AT jiezhang automateddeeplearningsystemforpowerlineinspectionimageanalysisandprocessingarchitectureanddesignissues AT zhixiangji automateddeeplearningsystemforpowerlineinspectionimageanalysisandprocessingarchitectureanddesignissues |