Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897772777> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2897772777 endingPage "1498" @default.
- W2897772777 startingPage "1486" @default.
- W2897772777 abstract "As the failure of power line insulators leads to the failure of power transmission systems, an insulator inspection system based on an aerial platform is widely used. Insulator defect detection is performed against complex backgrounds in aerial images, presenting an interesting but challenging problem. Traditional methods, based on handcrafted features or shallow-learning techniques, can only localize insulators and detect faults under specific detection conditions, such as when sufficient prior knowledge is available, with low background interference, at certain object scales, or under specific illumination conditions. This paper discusses the automatic detection of insulator defects using aerial images, accurately localizing insulator defects appearing in input images captured from real inspection environments. We propose a novel deep convolutional neural network (CNN) cascading architecture for performing localization and detecting defects in insulators. The cascading network uses a CNN based on a region proposal network to transform defect inspection into a two-level object detection problem. To address the scarcity of defect images in a real inspection environment, a data augmentation method is also proposed that includes four operations: 1) affine transformation; 2) insulator segmentation and background fusion; 3) Gaussian blur; and 4) brightness transformation. Defect detection precision and recall of the proposed method are 0.91 and 0.96 using a standard insulator dataset, and insulator defects under various conditions can be successfully detected. Experimental results demonstrate that this method meets the robustness and accuracy requirements for insulator defect detection." @default.
- W2897772777 created "2018-10-26" @default.
- W2897772777 creator A5016826662 @default.
- W2897772777 creator A5042675351 @default.
- W2897772777 creator A5054560949 @default.
- W2897772777 creator A5055020171 @default.
- W2897772777 creator A5059081976 @default.
- W2897772777 creator A5082921939 @default.
- W2897772777 date "2020-04-01" @default.
- W2897772777 modified "2023-10-16" @default.
- W2897772777 title "Detection of Power Line Insulator Defects Using Aerial Images Analyzed With Convolutional Neural Networks" @default.
- W2897772777 cites W125693051 @default.
- W2897772777 cites W1978459068 @default.
- W2897772777 cites W2018622255 @default.
- W2897772777 cites W2020620047 @default.
- W2897772777 cites W2027961328 @default.
- W2897772777 cites W2028643357 @default.
- W2897772777 cites W2056352580 @default.
- W2897772777 cites W2069261638 @default.
- W2897772777 cites W2092133582 @default.
- W2897772777 cites W2125556102 @default.
- W2897772777 cites W2137426486 @default.
- W2897772777 cites W2243417253 @default.
- W2897772777 cites W2539675563 @default.
- W2897772777 cites W2550512190 @default.
- W2897772777 cites W2555232156 @default.
- W2897772777 cites W2610166850 @default.
- W2897772777 cites W2614633644 @default.
- W2897772777 cites W2625853594 @default.
- W2897772777 cites W2754556155 @default.
- W2897772777 cites W2769597836 @default.
- W2897772777 cites W2772386856 @default.
- W2897772777 cites W639708223 @default.
- W2897772777 doi "https://doi.org/10.1109/tsmc.2018.2871750" @default.
- W2897772777 hasPublicationYear "2020" @default.
- W2897772777 type Work @default.
- W2897772777 sameAs 2897772777 @default.
- W2897772777 citedByCount "279" @default.
- W2897772777 countsByYear W28977727772019 @default.
- W2897772777 countsByYear W28977727772020 @default.
- W2897772777 countsByYear W28977727772021 @default.
- W2897772777 countsByYear W28977727772022 @default.
- W2897772777 countsByYear W28977727772023 @default.
- W2897772777 crossrefType "journal-article" @default.
- W2897772777 hasAuthorship W2897772777A5016826662 @default.
- W2897772777 hasAuthorship W2897772777A5042675351 @default.
- W2897772777 hasAuthorship W2897772777A5054560949 @default.
- W2897772777 hasAuthorship W2897772777A5055020171 @default.
- W2897772777 hasAuthorship W2897772777A5059081976 @default.
- W2897772777 hasAuthorship W2897772777A5082921939 @default.
- W2897772777 hasConcept C153180895 @default.
- W2897772777 hasConcept C154945302 @default.
- W2897772777 hasConcept C198352243 @default.
- W2897772777 hasConcept C2524010 @default.
- W2897772777 hasConcept C33923547 @default.
- W2897772777 hasConcept C41008148 @default.
- W2897772777 hasConcept C81363708 @default.
- W2897772777 hasConceptScore W2897772777C153180895 @default.
- W2897772777 hasConceptScore W2897772777C154945302 @default.
- W2897772777 hasConceptScore W2897772777C198352243 @default.
- W2897772777 hasConceptScore W2897772777C2524010 @default.
- W2897772777 hasConceptScore W2897772777C33923547 @default.
- W2897772777 hasConceptScore W2897772777C41008148 @default.
- W2897772777 hasConceptScore W2897772777C81363708 @default.
- W2897772777 hasFunder F4320321001 @default.
- W2897772777 hasFunder F4320336025 @default.
- W2897772777 hasIssue "4" @default.
- W2897772777 hasLocation W28977727771 @default.
- W2897772777 hasOpenAccess W2897772777 @default.
- W2897772777 hasPrimaryLocation W28977727771 @default.
- W2897772777 hasRelatedWork W2175746458 @default.
- W2897772777 hasRelatedWork W2613736958 @default.
- W2897772777 hasRelatedWork W2732542196 @default.
- W2897772777 hasRelatedWork W2738221750 @default.
- W2897772777 hasRelatedWork W2760085659 @default.
- W2897772777 hasRelatedWork W2912288872 @default.
- W2897772777 hasRelatedWork W3012978760 @default.
- W2897772777 hasRelatedWork W3081496756 @default.
- W2897772777 hasRelatedWork W3093612317 @default.
- W2897772777 hasRelatedWork W4304820710 @default.
- W2897772777 hasVolume "50" @default.
- W2897772777 isParatext "false" @default.
- W2897772777 isRetracted "false" @default.
- W2897772777 magId "2897772777" @default.
- W2897772777 workType "article" @default.