Matches in SemOpenAlex for { <https://semopenalex.org/work/W3003917023> ?p ?o ?g. }
- W3003917023 endingPage "105584" @default.
- W3003917023 startingPage "105584" @default.
- W3003917023 abstract "Deep learning lane marking detection algorithms based on vision in a complex scene face many challenges, such as absent markings and shadow and dazzle light. The following are the two particularly significant reasons: (1) the empirical size of the receptive fields in the deep neural network (DNN) is considerably smaller than the theoretical one; and (2) the importance of each channel in DNN is not being considered. To address both problems, we propose an attention module that combines self-attention and channel attention (called AMSC) by using a learnable coefficient in parallel. In addition, we apply AMSC in LargeFOV and propose an attention DNN for lane marking detection (modified LargeFOV). Long-range dependencies amongst pixels and channel dependencies are synchronously modelled to capture the global context and strengthen important features in the modified LargeFOV. In comparison with state-of-the-art methods that model dependencies of pixels and channels, our proposed module manifests certain properties, such as inherent parallel computing advantage and needs fewer parameters and convolution operations. Tests on the CULane dataset show that the modified LargeFOV outperforms recurrent neural network and DenseCRF by 3.7% and 5.6%, respectively, with at least 1.6× faster in computation speed, and the AMSC is 10.4× faster than SCNN with minimal performance loss. The modified LargeFOV outperforms the baseline network based on LargeFOV by 1.27% with negligible computational cost and is 1.6× faster than SCNN-LargeFOV(apply SCNN in LargeFOV) with 0.1% performance loss on TuSimple lane marking challenge dataset." @default.
- W3003917023 created "2020-02-07" @default.
- W3003917023 creator A5010163546 @default.
- W3003917023 creator A5012191915 @default.
- W3003917023 creator A5056940726 @default.
- W3003917023 creator A5057035718 @default.
- W3003917023 date "2020-04-01" @default.
- W3003917023 modified "2023-10-02" @default.
- W3003917023 title "Attention deep neural network for lane marking detection" @default.
- W3003917023 cites W2032438872 @default.
- W3003917023 cites W2039544046 @default.
- W3003917023 cites W2194775991 @default.
- W3003917023 cites W2261067606 @default.
- W3003917023 cites W2288122362 @default.
- W3003917023 cites W2403641464 @default.
- W3003917023 cites W2412782625 @default.
- W3003917023 cites W2745410201 @default.
- W3003917023 cites W2752782242 @default.
- W3003917023 cites W2767512561 @default.
- W3003917023 cites W2780740184 @default.
- W3003917023 cites W2790755431 @default.
- W3003917023 cites W2800988540 @default.
- W3003917023 cites W2884585870 @default.
- W3003917023 cites W2912512389 @default.
- W3003917023 cites W2963758239 @default.
- W3003917023 doi "https://doi.org/10.1016/j.knosys.2020.105584" @default.
- W3003917023 hasPublicationYear "2020" @default.
- W3003917023 type Work @default.
- W3003917023 sameAs 3003917023 @default.
- W3003917023 citedByCount "31" @default.
- W3003917023 countsByYear W30039170232020 @default.
- W3003917023 countsByYear W30039170232021 @default.
- W3003917023 countsByYear W30039170232022 @default.
- W3003917023 countsByYear W30039170232023 @default.
- W3003917023 crossrefType "journal-article" @default.
- W3003917023 hasAuthorship W3003917023A5010163546 @default.
- W3003917023 hasAuthorship W3003917023A5012191915 @default.
- W3003917023 hasAuthorship W3003917023A5056940726 @default.
- W3003917023 hasAuthorship W3003917023A5057035718 @default.
- W3003917023 hasConcept C108583219 @default.
- W3003917023 hasConcept C11413529 @default.
- W3003917023 hasConcept C117797892 @default.
- W3003917023 hasConcept C119857082 @default.
- W3003917023 hasConcept C127162648 @default.
- W3003917023 hasConcept C144024400 @default.
- W3003917023 hasConcept C151730666 @default.
- W3003917023 hasConcept C153180895 @default.
- W3003917023 hasConcept C154945302 @default.
- W3003917023 hasConcept C15744967 @default.
- W3003917023 hasConcept C160633673 @default.
- W3003917023 hasConcept C2779304628 @default.
- W3003917023 hasConcept C2779343474 @default.
- W3003917023 hasConcept C2984842247 @default.
- W3003917023 hasConcept C36289849 @default.
- W3003917023 hasConcept C41008148 @default.
- W3003917023 hasConcept C45347329 @default.
- W3003917023 hasConcept C45374587 @default.
- W3003917023 hasConcept C50644808 @default.
- W3003917023 hasConcept C542102704 @default.
- W3003917023 hasConcept C76155785 @default.
- W3003917023 hasConcept C81363708 @default.
- W3003917023 hasConcept C86803240 @default.
- W3003917023 hasConceptScore W3003917023C108583219 @default.
- W3003917023 hasConceptScore W3003917023C11413529 @default.
- W3003917023 hasConceptScore W3003917023C117797892 @default.
- W3003917023 hasConceptScore W3003917023C119857082 @default.
- W3003917023 hasConceptScore W3003917023C127162648 @default.
- W3003917023 hasConceptScore W3003917023C144024400 @default.
- W3003917023 hasConceptScore W3003917023C151730666 @default.
- W3003917023 hasConceptScore W3003917023C153180895 @default.
- W3003917023 hasConceptScore W3003917023C154945302 @default.
- W3003917023 hasConceptScore W3003917023C15744967 @default.
- W3003917023 hasConceptScore W3003917023C160633673 @default.
- W3003917023 hasConceptScore W3003917023C2779304628 @default.
- W3003917023 hasConceptScore W3003917023C2779343474 @default.
- W3003917023 hasConceptScore W3003917023C2984842247 @default.
- W3003917023 hasConceptScore W3003917023C36289849 @default.
- W3003917023 hasConceptScore W3003917023C41008148 @default.
- W3003917023 hasConceptScore W3003917023C45347329 @default.
- W3003917023 hasConceptScore W3003917023C45374587 @default.
- W3003917023 hasConceptScore W3003917023C50644808 @default.
- W3003917023 hasConceptScore W3003917023C542102704 @default.
- W3003917023 hasConceptScore W3003917023C76155785 @default.
- W3003917023 hasConceptScore W3003917023C81363708 @default.
- W3003917023 hasConceptScore W3003917023C86803240 @default.
- W3003917023 hasLocation W30039170231 @default.
- W3003917023 hasOpenAccess W3003917023 @default.
- W3003917023 hasPrimaryLocation W30039170231 @default.
- W3003917023 hasRelatedWork W2279398222 @default.
- W3003917023 hasRelatedWork W2606416966 @default.
- W3003917023 hasRelatedWork W2731899572 @default.
- W3003917023 hasRelatedWork W2915754718 @default.
- W3003917023 hasRelatedWork W2955560448 @default.
- W3003917023 hasRelatedWork W3000866861 @default.
- W3003917023 hasRelatedWork W3133861977 @default.
- W3003917023 hasRelatedWork W4299822940 @default.
- W3003917023 hasRelatedWork W4312417841 @default.
- W3003917023 hasRelatedWork W4321369474 @default.