ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Study on Training Convolutional Neural Network to Detect Distraction and Drowsiness
Cited 2 time in scopus Download 8 time Share share facebook twitter linkedin kakaostory
저자
김휘, 최현균, 장병태
발행일
201807
출처
IEEE Region 10 Symposium (TENSYMP) 2018, pp.253-257
DOI
https://dx.doi.org/10.1109/TENCONSpring.2018.8692015
초록
Most critical reason of the crash causal chain was caused by the driver. In other to reduce such human factors, it is necessary to use multiple pieces of information acquired by monitoring driver. In this paper, we propose a method to detect both distraction and drowsiness using a single convolutional neural network, and show that data composition should be different depending on the relationship of two or more class properties. In our experiments, we show driver distraction and drowsiness are reliably classified without decreasing accuracy and frames per seconds.
KSP 제안 키워드
Convolution neural network(CNN), Driver distraction, Human Factors, causal chain