Matches in SemOpenAlex for { <https://semopenalex.org/work/W3134070854> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W3134070854 abstract "The damage or corrosion of the anti-vibration hammer will endanger the safe operation in the high-voltage transmission line. In this paper, the images of transmission line acquired during UAV patrol inspection are used as a research object. A deep learning method is proposed to improve the detection accuracy and defect identification of anti-vibration hammer in the influence of light variation, complex background, and small targets. Firstly, the original images are enhanced by using a Retinex algorithm to reduce the influence of light variation and shadow. Then the anti-vibration hammers are detected by using a deep learning framework called Faster Region-based Convolutional Neural Network (Faster R-CNN), in which the Feature Pyramid Networks (FPN) is used to extract and fuse the multi-scale feature of the image. A two-stage cascade Region Proposal Network (RPN) is designed to generate regions proposal. In the first stage, a standard RPN is used and the anchor is the proposal obtained by the sliding window. In the second stage RPN, the output proposal from the first RPN is as the new anchor position and a more accurate proposal can be obtained. Finally, the proposed boxes and the original feature map are sent to the subsequent network to complete the final defects classification and position regression of the anti-vibration hammer. Experimental results show that the proposed method improves the detection accuracy in 4 kinds of anti-vibration hammer defects, which has a good reference for the popularization of intelligent inspection of high-voltage transmission lines." @default.
- W3134070854 created "2021-03-15" @default.
- W3134070854 creator A5030064573 @default.
- W3134070854 creator A5052135542 @default.
- W3134070854 creator A5054864172 @default.
- W3134070854 date "2020-09-01" @default.
- W3134070854 modified "2023-10-18" @default.
- W3134070854 title "Defect Detection of Anti-vibration Hammer Based on Improved Faster R-CNN" @default.
- W3134070854 doi "https://doi.org/10.1109/ifeea51475.2020.00186" @default.
- W3134070854 hasPublicationYear "2020" @default.
- W3134070854 type Work @default.
- W3134070854 sameAs 3134070854 @default.
- W3134070854 citedByCount "3" @default.
- W3134070854 countsByYear W31340708542021 @default.
- W3134070854 countsByYear W31340708542022 @default.
- W3134070854 crossrefType "proceedings-article" @default.
- W3134070854 hasAuthorship W3134070854A5030064573 @default.
- W3134070854 hasAuthorship W3134070854A5052135542 @default.
- W3134070854 hasAuthorship W3134070854A5054864172 @default.
- W3134070854 hasConcept C119599485 @default.
- W3134070854 hasConcept C121332964 @default.
- W3134070854 hasConcept C127413603 @default.
- W3134070854 hasConcept C13655849 @default.
- W3134070854 hasConcept C138885662 @default.
- W3134070854 hasConcept C141353440 @default.
- W3134070854 hasConcept C142575187 @default.
- W3134070854 hasConcept C153180895 @default.
- W3134070854 hasConcept C154945302 @default.
- W3134070854 hasConcept C198394728 @default.
- W3134070854 hasConcept C24890656 @default.
- W3134070854 hasConcept C2524010 @default.
- W3134070854 hasConcept C2776401178 @default.
- W3134070854 hasConcept C31972630 @default.
- W3134070854 hasConcept C33923547 @default.
- W3134070854 hasConcept C41008148 @default.
- W3134070854 hasConcept C41895202 @default.
- W3134070854 hasConcept C66938386 @default.
- W3134070854 hasConcept C761482 @default.
- W3134070854 hasConcept C76155785 @default.
- W3134070854 hasConcept C81363708 @default.
- W3134070854 hasConceptScore W3134070854C119599485 @default.
- W3134070854 hasConceptScore W3134070854C121332964 @default.
- W3134070854 hasConceptScore W3134070854C127413603 @default.
- W3134070854 hasConceptScore W3134070854C13655849 @default.
- W3134070854 hasConceptScore W3134070854C138885662 @default.
- W3134070854 hasConceptScore W3134070854C141353440 @default.
- W3134070854 hasConceptScore W3134070854C142575187 @default.
- W3134070854 hasConceptScore W3134070854C153180895 @default.
- W3134070854 hasConceptScore W3134070854C154945302 @default.
- W3134070854 hasConceptScore W3134070854C198394728 @default.
- W3134070854 hasConceptScore W3134070854C24890656 @default.
- W3134070854 hasConceptScore W3134070854C2524010 @default.
- W3134070854 hasConceptScore W3134070854C2776401178 @default.
- W3134070854 hasConceptScore W3134070854C31972630 @default.
- W3134070854 hasConceptScore W3134070854C33923547 @default.
- W3134070854 hasConceptScore W3134070854C41008148 @default.
- W3134070854 hasConceptScore W3134070854C41895202 @default.
- W3134070854 hasConceptScore W3134070854C66938386 @default.
- W3134070854 hasConceptScore W3134070854C761482 @default.
- W3134070854 hasConceptScore W3134070854C76155785 @default.
- W3134070854 hasConceptScore W3134070854C81363708 @default.
- W3134070854 hasLocation W31340708541 @default.
- W3134070854 hasOpenAccess W3134070854 @default.
- W3134070854 hasPrimaryLocation W31340708541 @default.
- W3134070854 hasRelatedWork W10677893 @default.
- W3134070854 hasRelatedWork W13715941 @default.
- W3134070854 hasRelatedWork W14517147 @default.
- W3134070854 hasRelatedWork W1679810 @default.
- W3134070854 hasRelatedWork W2455099 @default.
- W3134070854 hasRelatedWork W3060714 @default.
- W3134070854 hasRelatedWork W318772 @default.
- W3134070854 hasRelatedWork W4097755 @default.
- W3134070854 hasRelatedWork W4190492 @default.
- W3134070854 hasRelatedWork W8261557 @default.
- W3134070854 isParatext "false" @default.
- W3134070854 isRetracted "false" @default.
- W3134070854 magId "3134070854" @default.
- W3134070854 workType "article" @default.