ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Driver Drowsiness Detection based on 3D Convolution Neural Network with Optimized Window Size
Cited 1 time in scopus Download 28 time Share share facebook twitter linkedin kakaostory
Authors
Namkyoo Kang, Seungeun Han, Seungyeon Kim, SeungJoon Kwon, Yeongjae Choi, Yong-Tae Lee, Seung-Ik Lee
Issue Date
2022-10
Citation
International Conference on Information and Communication Technology Convergence (ICTC) 2022, pp.425-428
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.1109/ICTC55196.2022.9952988
Project Code
22IH1100, Development of immersive contents technologies for life safety experience education, Kwon Seung Joon
Abstract
Since driver drowsiness is one of the most significant causes of traffic accidents, it has been a key issue to detect driver's drowsiness. This paper introduces a driver drowsiness detection based on an optimized 3D convolutional network with only facial features. Our main contributions are that (1) we use only partial information from face images to detect driver drowsiness and (2) propose the best window size for drowsiness detection over video frames that allows us to take appropriate and enough contextual information into consideration to predict driver's drowsiness. In order to figure out what duration of the input video frames gives the best results for a 3D convolutional network, we conduct extensive experiments on the window sizes ranging from 5 to 128 frames together with several window overlapping options. Our approach has achieved an accuracy of 94.74% on the National Tsinghua University Driver Drowsiness Detection (NTHU-DDD) dataset, outperforming other 3D convolutional network-based state-of-art approaches.
KSP Keywords
3D convolutional networks, Contextual information, Convolution neural network(CNN), Face Image, Partial information, State-of-art, Traffic accident, Window Size, driver drowsiness detection, driver's drowsiness, facial features