Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304080467> ?p ?o ?g. }
- W4304080467 abstract "The defect diagnosis of modern infrastructures is crucial to public safety. In this work, we propose a complete crack inspection system with three main components, including the autonomous system setup, the geographic-information-system-based 3D reconstruction, and the database construction as well as domain adaptive algorithms design. To fulfill the unsupervised domain adaptation (UDA) task of cracks recognition in infrastructural inspections, we propose a robust unsupervised domain adaptive learning strategy termed Crack-DA to increase the generalization capacity of the model in unseen test circumstances. Specifically, firstly, we propose leveraging the self-supervised depth information to help the learning of semantics. Secondly, we propose using the edge information to suppress the non-edge background objects and noises. Thirdly, we propose using the data augmentation-based consistency learning to increase the prediction robustness. Finally, we use the disparity in depth to evaluate the domain gap in semantics and explicitly consider the domain gap in the optimization of the network. Also, we propose a source database consisting of 11,298 crack images with detailed pixel-level labels for network training in domain adaptations. Extensive experiments on UAV-captured highway cracks and real-site UAV inspections of building cracks demonstrate the robustness and effectiveness of the proposed domain adaptive crack recognition approach." @default.
- W4304080467 created "2022-10-10" @default.
- W4304080467 creator A5073973915 @default.
- W4304080467 date "2022-10-10" @default.
- W4304080467 modified "2023-10-01" @default.
- W4304080467 title "Robust Industrial UAV/UGV-Based Unsupervised Domain Adaptive Crack Recognitions with Depth and Edge Awareness: From System and Database Constructions to Real-Site Inspections" @default.
- W4304080467 cites W1966301784 @default.
- W4304080467 cites W2088049833 @default.
- W4304080467 cites W2106097225 @default.
- W4304080467 cites W2150066425 @default.
- W4304080467 cites W2160438804 @default.
- W4304080467 cites W2412782625 @default.
- W4304080467 cites W2435937386 @default.
- W4304080467 cites W2560023338 @default.
- W4304080467 cites W2597358295 @default.
- W4304080467 cites W2765854388 @default.
- W4304080467 cites W2899242765 @default.
- W4304080467 cites W2912272978 @default.
- W4304080467 cites W2912350898 @default.
- W4304080467 cites W2962872526 @default.
- W4304080467 cites W2963351448 @default.
- W4304080467 cites W2964118266 @default.
- W4304080467 cites W2964266557 @default.
- W4304080467 cites W2964309882 @default.
- W4304080467 cites W2979396152 @default.
- W4304080467 cites W2987563462 @default.
- W4304080467 cites W2991216808 @default.
- W4304080467 cites W2999443853 @default.
- W4304080467 cites W3002978252 @default.
- W4304080467 cites W3029808435 @default.
- W4304080467 cites W3035433720 @default.
- W4304080467 cites W3096678291 @default.
- W4304080467 cites W3110486195 @default.
- W4304080467 cites W3117515147 @default.
- W4304080467 cites W3138516171 @default.
- W4304080467 cites W3163893908 @default.
- W4304080467 cites W3169120894 @default.
- W4304080467 cites W3185864054 @default.
- W4304080467 cites W3186015572 @default.
- W4304080467 cites W3188511781 @default.
- W4304080467 cites W3195692323 @default.
- W4304080467 cites W3205123041 @default.
- W4304080467 cites W3211126960 @default.
- W4304080467 cites W3217288639 @default.
- W4304080467 cites W4230769173 @default.
- W4304080467 cites W4287124998 @default.
- W4304080467 cites W601144718 @default.
- W4304080467 cites W3118410762 @default.
- W4304080467 cites W3120008738 @default.
- W4304080467 doi "https://doi.org/10.1145/3503161.3548304" @default.
- W4304080467 hasPublicationYear "2022" @default.
- W4304080467 type Work @default.
- W4304080467 citedByCount "4" @default.
- W4304080467 countsByYear W43040804672022 @default.
- W4304080467 crossrefType "proceedings-article" @default.
- W4304080467 hasAuthorship W4304080467A5073973915 @default.
- W4304080467 hasConcept C104317684 @default.
- W4304080467 hasConcept C119857082 @default.
- W4304080467 hasConcept C124101348 @default.
- W4304080467 hasConcept C134306372 @default.
- W4304080467 hasConcept C154945302 @default.
- W4304080467 hasConcept C162307627 @default.
- W4304080467 hasConcept C185592680 @default.
- W4304080467 hasConcept C2776434776 @default.
- W4304080467 hasConcept C31972630 @default.
- W4304080467 hasConcept C33923547 @default.
- W4304080467 hasConcept C36503486 @default.
- W4304080467 hasConcept C41008148 @default.
- W4304080467 hasConcept C55493867 @default.
- W4304080467 hasConcept C63479239 @default.
- W4304080467 hasConcept C77088390 @default.
- W4304080467 hasConcept C8038995 @default.
- W4304080467 hasConcept C95623464 @default.
- W4304080467 hasConceptScore W4304080467C104317684 @default.
- W4304080467 hasConceptScore W4304080467C119857082 @default.
- W4304080467 hasConceptScore W4304080467C124101348 @default.
- W4304080467 hasConceptScore W4304080467C134306372 @default.
- W4304080467 hasConceptScore W4304080467C154945302 @default.
- W4304080467 hasConceptScore W4304080467C162307627 @default.
- W4304080467 hasConceptScore W4304080467C185592680 @default.
- W4304080467 hasConceptScore W4304080467C2776434776 @default.
- W4304080467 hasConceptScore W4304080467C31972630 @default.
- W4304080467 hasConceptScore W4304080467C33923547 @default.
- W4304080467 hasConceptScore W4304080467C36503486 @default.
- W4304080467 hasConceptScore W4304080467C41008148 @default.
- W4304080467 hasConceptScore W4304080467C55493867 @default.
- W4304080467 hasConceptScore W4304080467C63479239 @default.
- W4304080467 hasConceptScore W4304080467C77088390 @default.
- W4304080467 hasConceptScore W4304080467C8038995 @default.
- W4304080467 hasConceptScore W4304080467C95623464 @default.
- W4304080467 hasLocation W43040804671 @default.
- W4304080467 hasOpenAccess W4304080467 @default.
- W4304080467 hasPrimaryLocation W43040804671 @default.
- W4304080467 hasRelatedWork W1999222583 @default.
- W4304080467 hasRelatedWork W2035976912 @default.
- W4304080467 hasRelatedWork W2042311553 @default.
- W4304080467 hasRelatedWork W2109974539 @default.
- W4304080467 hasRelatedWork W2125927971 @default.
- W4304080467 hasRelatedWork W2146875012 @default.
- W4304080467 hasRelatedWork W2541791370 @default.