Matches in SemOpenAlex for { <https://semopenalex.org/work/W2806604911> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2806604911 endingPage "452" @default.
- W2806604911 startingPage "443" @default.
- W2806604911 abstract "This paper describes a deep learning-based approach for driver distraction recognition. The proposed strategy consists of applying transfer learning to overcome the scarcity of training images. More specifically, ResNet-50 model pre-trained on ImageNet is used as the basis for a more specific training aimed at classifying three driving behaviors: normal driving, texting while driving, and talking on the phone while driving. We propose different training strategies using two different datasets composed of images collected from the Internet and from real world simulations. The experimental results show that the best performance is achieved when the model is fine-tuned using a combination of images from both datasets. Specifically, the proposed system achieves accuracies of 98% and 95% when tested separately on the simulation and the Internet datasets, respectively. In addition, we evaluate the proposed system under different light conditions and show its robustness to light variations. In the worst case, the proposed system loses only 5.09% in accuracy when compared to its performance without light variations." @default.
- W2806604911 created "2018-06-13" @default.
- W2806604911 creator A5029492894 @default.
- W2806604911 creator A5031518818 @default.
- W2806604911 creator A5070046659 @default.
- W2806604911 date "2018-01-01" @default.
- W2806604911 modified "2023-10-17" @default.
- W2806604911 title "Transfer Learning Based Strategy for Improving Driver Distraction Recognition" @default.
- W2806604911 cites W1500404728 @default.
- W2806604911 cites W150109995 @default.
- W2806604911 cites W1987654648 @default.
- W2806604911 cites W2052770734 @default.
- W2806604911 cites W208765980 @default.
- W2806604911 cites W2094577405 @default.
- W2806604911 cites W2103978011 @default.
- W2806604911 cites W2108097371 @default.
- W2806604911 cites W2117539524 @default.
- W2806604911 cites W2119605622 @default.
- W2806604911 cites W2130012476 @default.
- W2806604911 cites W2134738818 @default.
- W2806604911 cites W2151103935 @default.
- W2806604911 cites W2161969291 @default.
- W2806604911 cites W2165698076 @default.
- W2806604911 cites W2183341477 @default.
- W2806604911 cites W2194775991 @default.
- W2806604911 cites W2253429366 @default.
- W2806604911 cites W2540183746 @default.
- W2806604911 cites W2556398113 @default.
- W2806604911 cites W2733839197 @default.
- W2806604911 doi "https://doi.org/10.1007/978-3-319-93000-8_50" @default.
- W2806604911 hasPublicationYear "2018" @default.
- W2806604911 type Work @default.
- W2806604911 sameAs 2806604911 @default.
- W2806604911 citedByCount "9" @default.
- W2806604911 countsByYear W28066049112019 @default.
- W2806604911 countsByYear W28066049112020 @default.
- W2806604911 countsByYear W28066049112021 @default.
- W2806604911 countsByYear W28066049112022 @default.
- W2806604911 countsByYear W28066049112023 @default.
- W2806604911 crossrefType "book-chapter" @default.
- W2806604911 hasAuthorship W2806604911A5029492894 @default.
- W2806604911 hasAuthorship W2806604911A5031518818 @default.
- W2806604911 hasAuthorship W2806604911A5070046659 @default.
- W2806604911 hasConcept C104317684 @default.
- W2806604911 hasConcept C110875604 @default.
- W2806604911 hasConcept C119857082 @default.
- W2806604911 hasConcept C136764020 @default.
- W2806604911 hasConcept C138885662 @default.
- W2806604911 hasConcept C150899416 @default.
- W2806604911 hasConcept C154945302 @default.
- W2806604911 hasConcept C169760540 @default.
- W2806604911 hasConcept C185592680 @default.
- W2806604911 hasConcept C2776378700 @default.
- W2806604911 hasConcept C2776465824 @default.
- W2806604911 hasConcept C2778707766 @default.
- W2806604911 hasConcept C41008148 @default.
- W2806604911 hasConcept C41895202 @default.
- W2806604911 hasConcept C55493867 @default.
- W2806604911 hasConcept C63479239 @default.
- W2806604911 hasConcept C86803240 @default.
- W2806604911 hasConceptScore W2806604911C104317684 @default.
- W2806604911 hasConceptScore W2806604911C110875604 @default.
- W2806604911 hasConceptScore W2806604911C119857082 @default.
- W2806604911 hasConceptScore W2806604911C136764020 @default.
- W2806604911 hasConceptScore W2806604911C138885662 @default.
- W2806604911 hasConceptScore W2806604911C150899416 @default.
- W2806604911 hasConceptScore W2806604911C154945302 @default.
- W2806604911 hasConceptScore W2806604911C169760540 @default.
- W2806604911 hasConceptScore W2806604911C185592680 @default.
- W2806604911 hasConceptScore W2806604911C2776378700 @default.
- W2806604911 hasConceptScore W2806604911C2776465824 @default.
- W2806604911 hasConceptScore W2806604911C2778707766 @default.
- W2806604911 hasConceptScore W2806604911C41008148 @default.
- W2806604911 hasConceptScore W2806604911C41895202 @default.
- W2806604911 hasConceptScore W2806604911C55493867 @default.
- W2806604911 hasConceptScore W2806604911C63479239 @default.
- W2806604911 hasConceptScore W2806604911C86803240 @default.
- W2806604911 hasLocation W28066049111 @default.
- W2806604911 hasOpenAccess W2806604911 @default.
- W2806604911 hasPrimaryLocation W28066049111 @default.
- W2806604911 hasRelatedWork W1984378874 @default.
- W2806604911 hasRelatedWork W1994564109 @default.
- W2806604911 hasRelatedWork W2051187670 @default.
- W2806604911 hasRelatedWork W2169604921 @default.
- W2806604911 hasRelatedWork W2190916350 @default.
- W2806604911 hasRelatedWork W2601152024 @default.
- W2806604911 hasRelatedWork W3133744144 @default.
- W2806604911 hasRelatedWork W3206583471 @default.
- W2806604911 hasRelatedWork W4221034725 @default.
- W2806604911 hasRelatedWork W626594146 @default.
- W2806604911 isParatext "false" @default.
- W2806604911 isRetracted "false" @default.
- W2806604911 magId "2806604911" @default.
- W2806604911 workType "book-chapter" @default.