Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092263114> ?p ?o ?g. }
- W3092263114 endingPage "4726" @default.
- W3092263114 startingPage "4716" @default.
- W3092263114 abstract "Vehicle taillight detection is essential to analyze and predict driver intention in collision avoidance systems. In this article, we propose an end-to-end framework that locates the rear brake and turn signals from video stream in real-time. The system adopts the fast YOLOv3-tiny as the backbone model and three improvements have been made to increase the detection accuracy on taillight semantics, i.e., additional output layer for multi-scale detection, spatial pyramid pooling (SPP) module for richer deep features, and focal loss for alleviation of class imbalance and hard sample classification. Experimental results demonstrate that the integration of multi-scale features as well as hard examples mining greatly contributes to the turn light detection. The detection accuracy is significantly increased by 7.36%, 32.04% and 21.65% (absolute gain) for brake, left-turn and right-turn signals, respectively. In addition, we construct the taillight detection dataset, with brake and turn signals are specified with bounding boxes, which may help nourishing the development of this realm." @default.
- W3092263114 created "2020-10-15" @default.
- W3092263114 creator A5005877741 @default.
- W3092263114 creator A5011650323 @default.
- W3092263114 creator A5021597928 @default.
- W3092263114 creator A5037865550 @default.
- W3092263114 creator A5048592975 @default.
- W3092263114 creator A5061907283 @default.
- W3092263114 creator A5065467108 @default.
- W3092263114 date "2021-07-01" @default.
- W3092263114 modified "2023-10-14" @default.
- W3092263114 title "A Highly Efficient Vehicle Taillight Detection Approach Based on Deep Learning" @default.
- W3092263114 cites W1536680647 @default.
- W3092263114 cites W1929630580 @default.
- W3092263114 cites W2047177684 @default.
- W3092263114 cites W2078783643 @default.
- W3092263114 cites W2102605133 @default.
- W3092263114 cites W2109255472 @default.
- W3092263114 cites W2118045339 @default.
- W3092263114 cites W2183341477 @default.
- W3092263114 cites W2194775991 @default.
- W3092263114 cites W2220750102 @default.
- W3092263114 cites W2345006952 @default.
- W3092263114 cites W2515328799 @default.
- W3092263114 cites W2530263920 @default.
- W3092263114 cites W2551797136 @default.
- W3092263114 cites W2565639579 @default.
- W3092263114 cites W2570343428 @default.
- W3092263114 cites W2581399701 @default.
- W3092263114 cites W2768487043 @default.
- W3092263114 cites W2794383732 @default.
- W3092263114 cites W2891287759 @default.
- W3092263114 cites W2899145720 @default.
- W3092263114 cites W2899511360 @default.
- W3092263114 cites W2908941882 @default.
- W3092263114 cites W2911056633 @default.
- W3092263114 cites W2926133619 @default.
- W3092263114 cites W2942950293 @default.
- W3092263114 cites W2959716986 @default.
- W3092263114 cites W2963037989 @default.
- W3092263114 cites W2963150697 @default.
- W3092263114 cites W2963351448 @default.
- W3092263114 cites W2970618130 @default.
- W3092263114 cites W2982770724 @default.
- W3092263114 cites W2986357608 @default.
- W3092263114 cites W2991275230 @default.
- W3092263114 cites W2998868424 @default.
- W3092263114 cites W3008115128 @default.
- W3092263114 cites W3016601897 @default.
- W3092263114 cites W3035460133 @default.
- W3092263114 cites W3048201280 @default.
- W3092263114 doi "https://doi.org/10.1109/tits.2020.3027421" @default.
- W3092263114 hasPublicationYear "2021" @default.
- W3092263114 type Work @default.
- W3092263114 sameAs 3092263114 @default.
- W3092263114 citedByCount "20" @default.
- W3092263114 countsByYear W30922631142021 @default.
- W3092263114 countsByYear W30922631142022 @default.
- W3092263114 countsByYear W30922631142023 @default.
- W3092263114 crossrefType "journal-article" @default.
- W3092263114 hasAuthorship W3092263114A5005877741 @default.
- W3092263114 hasAuthorship W3092263114A5011650323 @default.
- W3092263114 hasAuthorship W3092263114A5021597928 @default.
- W3092263114 hasAuthorship W3092263114A5037865550 @default.
- W3092263114 hasAuthorship W3092263114A5048592975 @default.
- W3092263114 hasAuthorship W3092263114A5061907283 @default.
- W3092263114 hasAuthorship W3092263114A5065467108 @default.
- W3092263114 hasConcept C108583219 @default.
- W3092263114 hasConcept C115961682 @default.
- W3092263114 hasConcept C127413603 @default.
- W3092263114 hasConcept C142575187 @default.
- W3092263114 hasConcept C147037132 @default.
- W3092263114 hasConcept C153180895 @default.
- W3092263114 hasConcept C154945302 @default.
- W3092263114 hasConcept C171146098 @default.
- W3092263114 hasConcept C190839683 @default.
- W3092263114 hasConcept C205649164 @default.
- W3092263114 hasConcept C22212356 @default.
- W3092263114 hasConcept C2524010 @default.
- W3092263114 hasConcept C2776151529 @default.
- W3092263114 hasConcept C2777113093 @default.
- W3092263114 hasConcept C2780156472 @default.
- W3092263114 hasConcept C2780999251 @default.
- W3092263114 hasConcept C31972630 @default.
- W3092263114 hasConcept C33923547 @default.
- W3092263114 hasConcept C41008148 @default.
- W3092263114 hasConcept C58640448 @default.
- W3092263114 hasConcept C63584917 @default.
- W3092263114 hasConcept C70437156 @default.
- W3092263114 hasConcept C79403827 @default.
- W3092263114 hasConceptScore W3092263114C108583219 @default.
- W3092263114 hasConceptScore W3092263114C115961682 @default.
- W3092263114 hasConceptScore W3092263114C127413603 @default.
- W3092263114 hasConceptScore W3092263114C142575187 @default.
- W3092263114 hasConceptScore W3092263114C147037132 @default.
- W3092263114 hasConceptScore W3092263114C153180895 @default.
- W3092263114 hasConceptScore W3092263114C154945302 @default.
- W3092263114 hasConceptScore W3092263114C171146098 @default.