Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385066103> ?p ?o ?g. }
- W4385066103 endingPage "6552" @default.
- W4385066103 startingPage "6552" @default.
- W4385066103 abstract "Ship fires are one of the main factors that endanger the safety of ships; because the ship is far away from land, the fire can be difficult to extinguish and could often cause huge losses. The engine room has many pieces of equipment and is the principal place of fire; however, due to its complex internal environment, it can bring many difficulties to the task of fire detection. The traditional detection methods have their own limitations, but fire detection using deep learning technology has the characteristics of high detection speed and accuracy. In this paper, we improve the YOLOv7-tiny model to enhance its detection performance. Firstly, partial convolution (PConv) and coordinate attention (CA) mechanisms are introduced into the model to improve its detection speed and feature extraction ability. Then, SIoU is used as a loss function to accelerate the model's convergence and improve accuracy. Finally, the experimental results on the dataset of the ship engine room fire made by us shows that the mAP@0.5 of the improved model is increased by 2.6%, and the speed is increased by 10 fps, which can meet the needs of engine room fire detection." @default.
- W4385066103 created "2023-07-23" @default.
- W4385066103 creator A5008904028 @default.
- W4385066103 creator A5035775512 @default.
- W4385066103 creator A5042081498 @default.
- W4385066103 creator A5049142955 @default.
- W4385066103 creator A5072949279 @default.
- W4385066103 creator A5077323251 @default.
- W4385066103 date "2023-07-20" @default.
- W4385066103 modified "2023-09-27" @default.
- W4385066103 title "Fire Detection in Ship Engine Rooms Based on Deep Learning" @default.
- W4385066103 cites W1536680647 @default.
- W4385066103 cites W1972058229 @default.
- W4385066103 cites W1996199746 @default.
- W4385066103 cites W2067168684 @default.
- W4385066103 cites W2067642987 @default.
- W4385066103 cites W2750851957 @default.
- W4385066103 cites W2752782242 @default.
- W4385066103 cites W2807860345 @default.
- W4385066103 cites W2810638178 @default.
- W4385066103 cites W2883780447 @default.
- W4385066103 cites W2884585870 @default.
- W4385066103 cites W2910201170 @default.
- W4385066103 cites W2912143961 @default.
- W4385066103 cites W2936299508 @default.
- W4385066103 cites W2962766617 @default.
- W4385066103 cites W2962858109 @default.
- W4385066103 cites W2963037989 @default.
- W4385066103 cites W2963058975 @default.
- W4385066103 cites W2963150697 @default.
- W4385066103 cites W2969400198 @default.
- W4385066103 cites W2982083293 @default.
- W4385066103 cites W2997747012 @default.
- W4385066103 cites W3023815152 @default.
- W4385066103 cites W3035414587 @default.
- W4385066103 cites W3106250896 @default.
- W4385066103 cites W3177052299 @default.
- W4385066103 cites W3206904836 @default.
- W4385066103 cites W4206054559 @default.
- W4385066103 cites W4229055310 @default.
- W4385066103 cites W4297537745 @default.
- W4385066103 cites W4298110846 @default.
- W4385066103 cites W4316339986 @default.
- W4385066103 cites W4320497212 @default.
- W4385066103 cites W639708223 @default.
- W4385066103 doi "https://doi.org/10.3390/s23146552" @default.
- W4385066103 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37514845" @default.
- W4385066103 hasPublicationYear "2023" @default.
- W4385066103 type Work @default.
- W4385066103 citedByCount "0" @default.
- W4385066103 crossrefType "journal-article" @default.
- W4385066103 hasAuthorship W4385066103A5008904028 @default.
- W4385066103 hasAuthorship W4385066103A5035775512 @default.
- W4385066103 hasAuthorship W4385066103A5042081498 @default.
- W4385066103 hasAuthorship W4385066103A5049142955 @default.
- W4385066103 hasAuthorship W4385066103A5072949279 @default.
- W4385066103 hasAuthorship W4385066103A5077323251 @default.
- W4385066103 hasBestOaLocation W43850661031 @default.
- W4385066103 hasConcept C108583219 @default.
- W4385066103 hasConcept C127413603 @default.
- W4385066103 hasConcept C138885662 @default.
- W4385066103 hasConcept C14036430 @default.
- W4385066103 hasConcept C154945302 @default.
- W4385066103 hasConcept C170154142 @default.
- W4385066103 hasConcept C171146098 @default.
- W4385066103 hasConcept C201995342 @default.
- W4385066103 hasConcept C2776401178 @default.
- W4385066103 hasConcept C2776439729 @default.
- W4385066103 hasConcept C2780451532 @default.
- W4385066103 hasConcept C2780836893 @default.
- W4385066103 hasConcept C41008148 @default.
- W4385066103 hasConcept C41895202 @default.
- W4385066103 hasConcept C44154836 @default.
- W4385066103 hasConcept C45347329 @default.
- W4385066103 hasConcept C50644808 @default.
- W4385066103 hasConcept C52622490 @default.
- W4385066103 hasConcept C78458016 @default.
- W4385066103 hasConcept C78519656 @default.
- W4385066103 hasConcept C86803240 @default.
- W4385066103 hasConceptScore W4385066103C108583219 @default.
- W4385066103 hasConceptScore W4385066103C127413603 @default.
- W4385066103 hasConceptScore W4385066103C138885662 @default.
- W4385066103 hasConceptScore W4385066103C14036430 @default.
- W4385066103 hasConceptScore W4385066103C154945302 @default.
- W4385066103 hasConceptScore W4385066103C170154142 @default.
- W4385066103 hasConceptScore W4385066103C171146098 @default.
- W4385066103 hasConceptScore W4385066103C201995342 @default.
- W4385066103 hasConceptScore W4385066103C2776401178 @default.
- W4385066103 hasConceptScore W4385066103C2776439729 @default.
- W4385066103 hasConceptScore W4385066103C2780451532 @default.
- W4385066103 hasConceptScore W4385066103C2780836893 @default.
- W4385066103 hasConceptScore W4385066103C41008148 @default.
- W4385066103 hasConceptScore W4385066103C41895202 @default.
- W4385066103 hasConceptScore W4385066103C44154836 @default.
- W4385066103 hasConceptScore W4385066103C45347329 @default.
- W4385066103 hasConceptScore W4385066103C50644808 @default.
- W4385066103 hasConceptScore W4385066103C52622490 @default.
- W4385066103 hasConceptScore W4385066103C78458016 @default.