Abstract
Abstract In recent years, the use of drones to assess the safety status of insulators in power transmission systems has become a trend. To facilitate the application of intelligent algorithms on drone platforms, this paper proposes a lightweight insulator string defect detection method based on an improved YOLOv5. Firstly, to decrease the parameter count in the YOLOv5 backbone module, we opted for GhostNet. Considering the limitations of GhostNet in feature extraction, a lightweight attention mechanism is designed and integrated with GhostNet to enhance the accuracy of capturing defect features in insulator strings. Additionally, to further reduce parameters in the neck part of the YOLOv5 model, Ghost Convolution is introduced. Experimental results demonstrate that the proposed model performs excellently on the insulator string dataset and meets the requirements for real-time defect detection of insulators using drones.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
