Matches in SemOpenAlex for { <https://semopenalex.org/work/W3159901775> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3159901775 abstract "In order to solve the problems of low accuracy and slow recognition speed of traffic signs, a multi-layer and multi-scale convolutional neural network recognition algorithm is proposed in this paper. Under the premise that the algorithm has high recognition accuracy, the traffic sign recognition model can be quickly established. This paper firstly improves the feature extraction method in the single-scale convolutional neural network to extract the global features and local features of the traffic sign image. Meanwhile, the features generated by different levels are fused into multi-scale features and transmitted to the full- connection layer classifier to improve the accuracy of traffic sign recognition. Then, the output data of the convolutional layer is processed by batch normalization (Batch Normalization) method, by normalizing the mean value and variance of each hidden layer ˈ the occurrence of gradient explosion or disappearance is reduced, the training convergence speed is increased, also the training time is reduced. Finally, the validity of the proposed algorithm is tested in German traffic signs benchmark database (GTSRB). Experimental results show that the proposed algorithm can not only maintains high accuracy, but also performs well in training time and recognition time. Also, the fast recognition algorithm of multi-layer and multi-scale convolutional neural network has good generalization ability and real-time performance, providing important technical support for the reliability and safety of intelligent driving." @default.
- W3159901775 created "2021-05-10" @default.
- W3159901775 creator A5035367145 @default.
- W3159901775 creator A5054271527 @default.
- W3159901775 date "2020-12-01" @default.
- W3159901775 modified "2023-10-16" @default.
- W3159901775 title "Fast Traffic Sign Recognition Algorithm Based on Multi-scale Convolutional Neural Network" @default.
- W3159901775 cites W1585377561 @default.
- W3159901775 cites W2012742472 @default.
- W3159901775 cites W2018123791 @default.
- W3159901775 cites W2074643422 @default.
- W3159901775 cites W2108069432 @default.
- W3159901775 cites W2110591696 @default.
- W3159901775 cites W2125085157 @default.
- W3159901775 cites W2134656853 @default.
- W3159901775 cites W2182198985 @default.
- W3159901775 cites W2792806930 @default.
- W3159901775 doi "https://doi.org/10.1109/cbd51900.2020.00031" @default.
- W3159901775 hasPublicationYear "2020" @default.
- W3159901775 type Work @default.
- W3159901775 sameAs 3159901775 @default.
- W3159901775 citedByCount "1" @default.
- W3159901775 countsByYear W31599017752023 @default.
- W3159901775 crossrefType "proceedings-article" @default.
- W3159901775 hasAuthorship W3159901775A5035367145 @default.
- W3159901775 hasAuthorship W3159901775A5054271527 @default.
- W3159901775 hasConcept C108583219 @default.
- W3159901775 hasConcept C11413529 @default.
- W3159901775 hasConcept C134306372 @default.
- W3159901775 hasConcept C136886441 @default.
- W3159901775 hasConcept C139676723 @default.
- W3159901775 hasConcept C144024400 @default.
- W3159901775 hasConcept C153180895 @default.
- W3159901775 hasConcept C154945302 @default.
- W3159901775 hasConcept C19165224 @default.
- W3159901775 hasConcept C2983860417 @default.
- W3159901775 hasConcept C33923547 @default.
- W3159901775 hasConcept C41008148 @default.
- W3159901775 hasConcept C50644808 @default.
- W3159901775 hasConcept C52622490 @default.
- W3159901775 hasConcept C6528762 @default.
- W3159901775 hasConcept C81363708 @default.
- W3159901775 hasConcept C95623464 @default.
- W3159901775 hasConceptScore W3159901775C108583219 @default.
- W3159901775 hasConceptScore W3159901775C11413529 @default.
- W3159901775 hasConceptScore W3159901775C134306372 @default.
- W3159901775 hasConceptScore W3159901775C136886441 @default.
- W3159901775 hasConceptScore W3159901775C139676723 @default.
- W3159901775 hasConceptScore W3159901775C144024400 @default.
- W3159901775 hasConceptScore W3159901775C153180895 @default.
- W3159901775 hasConceptScore W3159901775C154945302 @default.
- W3159901775 hasConceptScore W3159901775C19165224 @default.
- W3159901775 hasConceptScore W3159901775C2983860417 @default.
- W3159901775 hasConceptScore W3159901775C33923547 @default.
- W3159901775 hasConceptScore W3159901775C41008148 @default.
- W3159901775 hasConceptScore W3159901775C50644808 @default.
- W3159901775 hasConceptScore W3159901775C52622490 @default.
- W3159901775 hasConceptScore W3159901775C6528762 @default.
- W3159901775 hasConceptScore W3159901775C81363708 @default.
- W3159901775 hasConceptScore W3159901775C95623464 @default.
- W3159901775 hasFunder F4320321001 @default.
- W3159901775 hasFunder F4320321408 @default.
- W3159901775 hasFunder F4320322605 @default.
- W3159901775 hasLocation W31599017751 @default.
- W3159901775 hasOpenAccess W3159901775 @default.
- W3159901775 hasPrimaryLocation W31599017751 @default.
- W3159901775 hasRelatedWork W11300528 @default.
- W3159901775 hasRelatedWork W13076802 @default.
- W3159901775 hasRelatedWork W14579021 @default.
- W3159901775 hasRelatedWork W2582698 @default.
- W3159901775 hasRelatedWork W2834797 @default.
- W3159901775 hasRelatedWork W3506425 @default.
- W3159901775 hasRelatedWork W3540334 @default.
- W3159901775 hasRelatedWork W654939 @default.
- W3159901775 hasRelatedWork W6680660 @default.
- W3159901775 hasRelatedWork W9190101 @default.
- W3159901775 isParatext "false" @default.
- W3159901775 isRetracted "false" @default.
- W3159901775 magId "3159901775" @default.
- W3159901775 workType "article" @default.