Transfer learning using convolutional neural networks for driver distraction recognition
DOI:
https://doi.org/10.21754/tecnia.v28i2.549Keywords:
Transfer learning, Feature Engineering, Distracted driver, Convolutional neural networksAbstract
In the present work it is proposed to identify if a person is distracted or not, when he is driving a vehicle. This can be achieved by classifying images of drivers to determine if they are available or distracted using convolutional neural networks (CNN) and tools to improve the algorithm, which are Learning Transfer and Characteristics Engineering. Kaggle competition images are used to perform the training, in which you can obtain more results and obtain more results. Later the red extractor of characteristics VGG16 was used, which is a pre-trained model, from which it is lowered in its last layers to reduce the overfit and adapt it to our algorithm. The results obtained in the classifier gave us a training efficiency and validation of 99.30% and 99.46% respectively.
Downloads
References
[1] Oficina De Tecnología De Información Ministerio De Transportes Y Comunicaciones. [Consultado 25 Jul 2018]. Disponible en: https://www.mtc.gob.pe/cnsv/estadistica.html
[2] Ministerio de Salud –MINSA, “Situación de los accidentes de tránsito en el Peru”. [Consultado 25 Jul 2018]. Disponible en:https://elcomercio.pe/peru/accidentes-transito-750-personas-murieron-carreteras-peru-2018-noticia-574739
[3] Baheti B, Gajre S y Talbar S 2018 Detection of distracted driver using convolutional neural networken Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops 1032-1038.
[4] Abouelnaga Y, Eraqi H M y Moustafa M N 2017 Real-time distracted driver posture classification.arXiv preprint arXiv:1706.09498.
[5] Torres R, Ohashi O, Carvalho E y Pessin G 2017 A Deep Learning Approach to Detect Distracted Drivers Using a Mobile Phone enInternational Conference on Artificial Neural NetworksSpringer, Cham, 72-79
[6] Hoang Ngan Le T, Zheng Y, Zhu C, Luu K y Savvides M 2016 Multiple Scale Faster-RCNN Approach to Driver's Cell-Phone Usage and Hands on Steering Wheel Detection enProceedings of the IEEE Conferenceon Computer Vision and Pattern Recognition Workshops, 46-53
[7] Koesdwiady A, Bedawi S M, Ou C y Karray F 2017 End-to-end deep learning for driver distraction recognition enInternational Conference Image Analysis and RecognitionSpringer, Cham, 11-18
[8] Yosinski J, Clune J, Bengio Y y Lipson H 2014. How transferable are features in deep neural networks? enAdvances in neural information processing systems3320-3328
[9] Simonyan K y Zisserman A 2014. Very deep convolutional networks for large-scale imagerecognition.arXiv preprint arXiv:1409.1556.
[10] StateFarm: State Farm Distracted Driver Detection. [Consultado 5 Jul 2018]. Disponible en: https://www.kaggle.com/c/state-farm-distracted-driver-detection.
Published
How to Cite
Issue
Section
License
Copyright (c) 2018 TECNIA
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published by TECNIA can be shared under the international Creative Commons license: CC BY 4.0. Permissions beyond this scope can be inquired via email at tecnia@uni.edu.pe.
