The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
우리는 영상에서 운전자의 졸음을 감지하기 위한 심층신경망(DNN)을 개발합니다. 비디오 프레임에서 추출된 운전자의 얼굴을 입력으로 받는 제안된 DNN 모델은 CNN(Convolutional Neural Network), ConvCGRNN(Convolutional Control Gate-Based Recurrent Neural Network) 및 투표 레이어의 세 가지 구성 요소로 구성됩니다. CNN은 전역 얼굴에서 얼굴 표현을 학습한 다음 ConvCGRNN에 공급되어 시간적 종속성을 학습합니다. 투표 계층은 졸음 상태를 예측하기 위해 많은 하위 분류기의 앙상블처럼 작동합니다. NTHU-DDD 데이터 세트에 대한 실험 결과는 우리 모델이 후처리 없이 84.81%의 경쟁력 있는 정확도를 달성할 뿐만 아니라 약 100fps의 빠른 속도로 실시간으로 작동할 수 있음을 보여줍니다.
Toan H. VU
National Central University
An DANG
National Central University
Jia-Ching WANG
National Central University,Pervasive Artificial Intelligence Research (PAIR) Labs
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Toan H. VU, An DANG, Jia-Ching WANG, "A Deep Neural Network for Real-Time Driver Drowsiness Detection" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 12, pp. 2637-2641, December 2019, doi: 10.1587/transinf.2019EDL8079.
Abstract: We develop a deep neural network (DNN) for detecting driver drowsiness in videos. The proposed DNN model that receives driver's faces extracted from video frames as inputs consists of three components - a convolutional neural network (CNN), a convolutional control gate-based recurrent neural network (ConvCGRNN), and a voting layer. The CNN is to learn facial representations from global faces which are then fed to the ConvCGRNN to learn their temporal dependencies. The voting layer works like an ensemble of many sub-classifiers to predict drowsiness state. Experimental results on the NTHU-DDD dataset show that our model not only achieve a competitive accuracy of 84.81% without any post-processing but it can work in real-time with a high speed of about 100 fps.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDL8079/_p
부
@ARTICLE{e102-d_12_2637,
author={Toan H. VU, An DANG, Jia-Ching WANG, },
journal={IEICE TRANSACTIONS on Information},
title={A Deep Neural Network for Real-Time Driver Drowsiness Detection},
year={2019},
volume={E102-D},
number={12},
pages={2637-2641},
abstract={We develop a deep neural network (DNN) for detecting driver drowsiness in videos. The proposed DNN model that receives driver's faces extracted from video frames as inputs consists of three components - a convolutional neural network (CNN), a convolutional control gate-based recurrent neural network (ConvCGRNN), and a voting layer. The CNN is to learn facial representations from global faces which are then fed to the ConvCGRNN to learn their temporal dependencies. The voting layer works like an ensemble of many sub-classifiers to predict drowsiness state. Experimental results on the NTHU-DDD dataset show that our model not only achieve a competitive accuracy of 84.81% without any post-processing but it can work in real-time with a high speed of about 100 fps.},
keywords={},
doi={10.1587/transinf.2019EDL8079},
ISSN={1745-1361},
month={December},}
부
TY - JOUR
TI - A Deep Neural Network for Real-Time Driver Drowsiness Detection
T2 - IEICE TRANSACTIONS on Information
SP - 2637
EP - 2641
AU - Toan H. VU
AU - An DANG
AU - Jia-Ching WANG
PY - 2019
DO - 10.1587/transinf.2019EDL8079
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2019
AB - We develop a deep neural network (DNN) for detecting driver drowsiness in videos. The proposed DNN model that receives driver's faces extracted from video frames as inputs consists of three components - a convolutional neural network (CNN), a convolutional control gate-based recurrent neural network (ConvCGRNN), and a voting layer. The CNN is to learn facial representations from global faces which are then fed to the ConvCGRNN to learn their temporal dependencies. The voting layer works like an ensemble of many sub-classifiers to predict drowsiness state. Experimental results on the NTHU-DDD dataset show that our model not only achieve a competitive accuracy of 84.81% without any post-processing but it can work in real-time with a high speed of about 100 fps.
ER -